The Value of Experiments in Assortment Optimization
Mohammadreza Ahmadnejadsaein, Amine Bennouna, Omar El Housni
AI 速览：研究在多项 logit 模型下，利用少量固定实验 assortment 的顾客选择数据，如何设计实验与最终 assortment 选择规则以最小化最坏情况遗憾。
Retailers can learn customer preferences by experimenting with different assortments. However, the cost of each experiment and the operational burden of repeatedly changing product offerings can make extensive experimentation impractical. We study how much a retailer can improve its final assortment decision using customer observations from one (or a very small number of) fixed experimental assortments. We consider the multinomial logit model, where product revenues are known but customer preferences are unknown. In this setting, we jointly design the experimental assortment and the rule for selecting a final assortment from observed customer choices to minimize worst-case regret: the expected revenue loss of the final assortment relative to an optimal assortment under the true preferences, maximized over possible customer preferences. We first characterize exactly the minimax regret and an optimal assortment when no experimentation is possible. We then show, surprisingly, that offering a single experimental assortment to just one customer can already substantially reduce regret, depending on how the products' revenues compare. We derive the exact minimax regret and an optimal experimental policy in this setting. When a single fixed experimental assortment is offered to many customers, we give a geometric characterization of the limiting minimax regret and construct an asymptotically optimal policy. Depending on product revenues, this single experiment can yield no improvement over no experimentation or nearly complete regret reduction. Finally, we extend our analysis to multiple experimental assortments chosen in advance, characterizing the limiting minimax regret, constructing asymptotically optimal policies, and identifying which collections of assortments allow worst-case regret to vanish as the number of customer observations grows.
We propose a novel quantum algorithm for solving linear optimization problems by quantum-mechanical simulation of the central path. While interior point methods follow the central path with an iterative algorithm that works with successive linearizations of the perturbed KKT conditions, we perform a simulation working directly with the nonlinear complementarity equations. Using a two-stage quantum eigenpath traversal schedule, this approach yields an algorithm for solving linear optimization problems involving $m$ constraints and $n$ variables to $\varepsilon$-optimality using $\widetilde{O}\!\left((m+n)^{3/2}\,\varepsilon^{-1}+(m+n)^{1/2}\,\varepsilon^{-3/2}\right)$ queries to an oracle that evaluates a potential function. In the standard gate model (i.e., without access to quantum RAM), our algorithm can obtain $\varepsilon$-precise solutions to LO problems using at most $$\widetilde{O}\!\left(\left[\frac{(m+n)^{3/2}}{\varepsilon} + \frac{(m+n)^{1/2}}{\varepsilon^{3/2}}\right] \cdot \mathrm{nnz}(A)\right)$$ elementary gates, where $\mathrm{nnz}(A)$ is the total number of non-zero elements found in the constraint matrix.
Adaptive search with path-constrained mobile sensors using multi-arm bandits
Abraham P. Vinod, Parth K. Thaker, Gautam Dasarathy, Stefano Di Cairano
AI 速览：将能量受限移动传感器团队的主动路径选择建模为多臂老虎机问题，提出带置信界与路径覆盖构造的自适应搜索算法，并给出有限时间与任意时间概率正确性保证及匹配下界的检测时间上界。
We study a constrained sequential decision problem for detecting regions of interest from noisy online measurements collected by a team of energy-constrained mobile sensors. The sensor motion is restricted to a precomputed set of feasible paths that satisfy mobility constraints, limited available energy by requiring return to charging stations, and avoidance of known obstacles. We cast the resulting active path selection as a multi-armed bandit problem and propose an iterative search algorithm that adaptively assigns paths using confidence bounds computed from the collected data. We also propose a graph-based method to construct low-cardinality path covers under the team's constraints. We establish finite-time and anytime probabilistic correctness guarantees for the proposed algorithm, derive non-asymptotic upper bounds on the times required to detect all regions of interest and to label all nodes, and show that these bounds match algorithm-independent lower bounds up to constant factors for a broad class of problem instances. Using numerical simulations, we illustrate the behavior of the proposed approach and the effect of path redundancy and team size on search performance.
First-Order Bilevel Optimization for Non-truthful Auction Design
Shing-Hei Ho, April Niu, Ellen Vitercik, Kai Wang
AI 速览：将非真实拍卖设计建模为含多个策略跟随者的 Stackelberg 博弈，提出全一阶算法优化收益并给出非渐近收敛保证。
Automated mechanism design has enabled the learning of complex auction mechanisms using neural networks. However, designing non-truthful auctions remains challenging because bidders' equilibrium strategies depend on the auction mechanism and thus evolve as the mechanism is optimized. In this work, we formulate auction design as a Stackelberg game with multiple strategic followers and develop a fully first-order algorithm for revenue optimization in non-truthful auctions. We establish non-asymptotic guarantees for hypergradient approximation and show that, under standard smoothness and strong-monotonicity assumptions, our method reaches an $O(ε)$-stationary point using $\tilde{\mathcal{O}}(ε^{-2})$ first-order oracle calls. Experiments on symmetric and asymmetric single-item auctions, as well as multi-item auctions, show that our method converges faster than second- and zeroth-order baselines and scales better as the number of bidders increases. Our method also discovers auctions that achieve revenue close to truthful baselines. These results provide a scalable framework for automated mechanism design beyond truthful auctions.
Finite-Sample LTI System Identification from a Misspecified Finite Model Set
Nicolas Chatzikiriakos, Andrea Iannelli
AI 速览：研究真实LTI系统不在有限假设类内时，有限样本辨识的估计目标、失败概率下界及指数加权算法的鲁棒性上界。
We consider the problem of finite-sample identification of an unknown LTI system from a finite hypothesis class. In contrast to existing results that assume the hypothesis class contains the true system, we consider the misspecified setting, where the true system does not belong to the hypothesis class. We first characterize the resulting estimation target and its dependence on the data-generation scheme. We then establish a finite-sample lower bound on the failure probability that any identification algorithm must incur. Finally, we analyze the robustness of an existing exponential weighting-based identification algorithm to the misspecification and derive a finite-sample upper bound on its failure probability. Our results illustrate when using a misspecified finite hypothesis class can provide an advantage over identification without prior knowledge of the candidate systems.
Gaussian Approximation and Multiplier Bootstrap for Federated Linear Stochastic Approximation
Ilya Levin, Maksim Shuklin, Eric Moulines, Paul Mangold, Sergey Samsonov
AI 速览：该论文为联邦线性随机逼近建立Berry-Esseen型界与联邦高斯近似，并据此提出一种无需显式估计渐近协方差矩阵的在线乘子自助推断方法。
In this paper, we establish Berry-Esseen-type bounds for federated linear stochastic approximation (LSA). Our results provide the first federated Gaussian approximations for LSA that explicitly capture communication-computation trade-offs and heterogeneity-aware error terms, quantifying the effects of local step size, number of local updates, and heterogeneity on convergence rates. We present results for both (i) constant step size regime and (ii) decreasing step size with an increasing number of local iterations, recovering the recent rates of Bonnerjee et al. [2025] as a special case. As a primary application of our results, we develop an online multiplier bootstrap procedure for inference on the last iterate, which avoids explicit estimation of the asymptotic covariance matrix, and obtain non-asymptotic validity guarantees for this procedure.
Vanilla gradient methods are often highly sensitive to the choice of stepsize, which typically requires manual tuning. Adaptive methods alleviate this issue, with AdaGrad being a prominent example. In this work, we first show that, in composite convex optimization, AdaGrad may fail to exploit the Hölder-smoothness of the differentiable term, as its stepsizes may decrease too rapidly, leading to convergence rates arbitrarily close to the nonsmooth $\mathcal O(n^{-1/2})$ rate. Motivated by this limitation, we study AdaGrad-Diff, a block-wise extension of the UniSgd method considered by \cite{rodomanov2024universality}, which accumulates successive gradient differences rather than gradients themselves. In the deterministic Lipschitz-smooth setting, we prove summability of squared gradient differences without assuming bounded iterates, yielding weak convergence to a minimizer in Hilbert spaces. Moreover, we show that, under $ν$-Hölder-smoothness, stepsizes decay no faster than $n^{-(1-ν)/2}$, thereby avoiding AdaGrad's failure mechanism and recovering the standard $\mathcal O(n^{-(1+ν)/2})$ rate. The same approach recovers known stochastic convergence rates under a unified condition covering bounded variance and interpolation. Numerical experiments demonstrate that the proposed method is more robust than AdaGrad in several practically relevant settings.
Privacy accounting bounds the cumulative privacy cost of Differentially Private Stochastic Gradient Descent but does not determine how to allocate a fixed budget across iterations. We formulate the complete Gaussian noise-variance schedule as an open-loop control under a composed zero-Concentrated Differential Privacy constraint, explicitly accounting for schedule selection. For expected quadratic terminal tracking, we prove that every local minimizer exhausts the certified budget, yielding an exact-budget simplex formulation. We introduce Privacy-Budget Adjoint Mirror Descent (PB-AMD), combining pathwise adjoint gradients with entropic updates that preserve positivity, charge floors, and the prescribed budget. Under regularity and coercivity assumptions, we establish existence and budget stability of optimal schedules, design-to-training utility stability, and deterministic, stochastic, and sample-average stationarity guarantees. A linear-quadratic reduction yields an explicit square-root allocation law. Experiments demonstrate tracking improvements over several allocation rules and predictive improvements over uniform allocation in a learning-rate restart setting, where learning-rate allocation performs similarly. Comparisons at a common stationarity tolerance show lower schedule-optimization times than projected gradient descent on the tested problems. The framework connects certified privacy accounting with optimization through nonlinear training dynamics.
Modern machine learning models are often overparameterized, i.e., have more parameters than training data. This typically implies that the loss function admits multiple minimizers so that training methods (and their hyperparameter choices) have significant influence on the computed solution. We study this so-called implicit bias phenomenon in the context of training deep linear diagonal networks. Previous work has shown that the gradient flow for learning such networks converges to (almost) sparse solutions when initialized small. For an arbitrary number of layers, we extend this analysis to the practically more realistic (stochastic) gradient descent iterations. Our approach identifies (stochastic) gradient descent as a perturbed (stochastic) mirror gradient descent. This allows us to establish convergence and characterize the limiting solution, relating it to weighted $\ell_1$-minimization. Moreover, we provide sufficient conditions on the step sizes and quantify the influence of the step sizes on the implicit bias.
AdaGrad-style methods can simultaneously adapt to both the order and constants of smoothness in centralized optimization. However, existing extensions to federated optimization with heterogeneous client objectives and multiple local steps require the smoothness order to be specified in advance. We address this limitation with AdaFed, a federated method that adapts across several regimes under a single choice of parameters. In the deterministic setting, AdaFed achieves an $O(1/T)$ convergence rate for both smooth nonconvex and smooth convex objectives, and an $O(1/\sqrt{T})$ rate for Lipschitz nonsmooth convex objectives up to logarithmic factors. Under a light-tailed stochastic-gradient noise assumption, these guarantees extend to the stochastic setting with additional logarithmic factors and noise-dependent terms. Experiments across the three problem classes further support our theoretical findings.
Jaume Reixach, Wanru Chen, Jiaming Wu, Balázs Kulcsár
Electric vehicles produce no tailpipe emissions, but charging them produces emissions that depend on the time-varying generation mix of the electricity consumed. We study an Electric Vehicle Routing Problem with a carbon-aware objective that accounts for charging-related emissions alongside conventional routing costs. The problem determines routing, charging, and waiting decisions, allowing charging demand to be shifted toward periods with lower grid carbon intensity. Because these decisions depend on forecasts of future carbon intensity, we propose a decision-focused learning approach so that the training of the model employed for predicting the carbon intensity of the grid over time is solver-aware. In particular, we train a linear predictor using approximate SPO+ directions and employ a time-limited Large Neighborhood Search followed by exact postprocessing as the underlying solver. Experiments on realistic Germany-based instances show that explicitly considering charging-related emissions reduces realized emissions by 28.76% on average relative to carbon-blind optimization, although at the expense of higher non-carbon operating cost. Moreover, decision-focused training reduces realized total cost by 2.30% on average relative to conventional prediction-focused learning and performs better on 75.5% of the test instances, despite substantially lower pointwise predictive accuracy. Finally, we show that its average advantage remains positive across varied solver configurations and carbon-cost weights.
Most modern optimizers form their momentum as an exponential moving average (EMA) of past gradients, forgetting every direction at one fixed rate. However, the inputs a deep network sees during training can be highly anisotropic, with a few directions queried frequently while most are seen rarely. Preconditioning methods address this anisotropy by wrapping extra processing around this buffer and leave the momentum update itself unchanged. We propose Activation-Keyed Momentum (AK-Momentum), which builds direction-awareness into the momentum update rule. The gradient of a linear layer splits into an input activation that acts as a $\textit{key}$ and an output-side error that acts as a $\textit{value}$. Keying on that activation, AK-Momentum updates the momentum buffer by the canonical delta rule, so each direction is forgotten at a rate set by how often it appears. We prove that it is a valid momentum, that it applies the input-side curvature correction without matrix inversion, and that it clears stale directions faster than EMA under both a fixed and a drifting optimum. It is a drop-in replacement for the momentum buffer of any optimizer, its coefficient transfers across widths under $μ$P, and its extra compute stays between $22.2\%$ and $25.0\%$ of a gated-MLP block's linear cost with no persistent memory. In FineWeb-Edu pretraining, AdamW with AK-Momentum (AK-AdamW) reaches AdamW's validation loss in up to $46.64 \pm 4.52\%$ fewer steps at 67M and $22.14 \pm 0.81\%$ at 370M over three seeds, and the gain persists at 1B on a Chinchilla-optimal budget. A Muon baseline tuned under the same protocol sits above AK-AdamW at both language-model scales, and the gain holds for SGD, ResNet-18, and ViT-Tiny on CIFAR-10. Training-time diagnostics confirm the predicted mechanism, better gradient tracking and healthier input directions. Code is available at https://github.com/euijinh/AK-Momentum.
Pekka Malo, Lauri Viitasaari, Antti Suominen, Eeva Vilkkumaa, Olli Tahvonen
In many control problems, actions consume a resource budget, such as a wear allowance, and the probability of exhausting it within a given horizon must stay below a tolerance. A simple, widely used approach is to augment the state with the remaining budget, subtract an interior barrier from the utility and penalize exhaustion, so that policy-gradient methods can be applied unchanged. We clip the combined one-step reward from below at a level m to keep the returns of exploratory policies finite. The clip level is a price of failure risk, since the clipped value decomposes exactly into the utility before failure, the cost of the interior margin and m times a geometric failure risk. Consequently, an approximately optimal policy maximizes utility net of margin cost among policies with no greater risk. Its risk exceeds that of any comparison policy by at most order 1/m and can be certified from its value or from validation data. Our main result proves exponential convergence of the population policy-gradient flow for every parameter regularizer that is convex along generalized geodesics and sufficiently strong relative to the price. This extends the mean-field analysis from relative entropy to weight decay and to finite networks. Relative entropy adds parameter noise and a pull toward a prior, whereas weight decay provides only the pull. Action regularization bounds changes in failure risk by the relative entropy to a reference policy. The bounds are evaluated on an exact maintenance benchmark, a fuel-tank controller, a solvable flow and a benchmark-suite task.
Julien Grand-Clément, Joon Kwon, Francesco Orabona
A central topic in online and stochastic optimization is to design algorithms that do not require tuning of hyperparameters. Successful strategies in online learning include AdaGrad-style learning rates, Conic Blackwell algorithms, and parameter-free algorithms. However, these classes require different, often difficult, analyses. We develop a unifying family of Online Convex Optimization (OCO) algorithms that require no user-tuned learning rate on convex domains that may be unbounded. The construction lifts the domain to a cone by adding one scalar coordinate, an idea going back to Blackwell (1954). The lifted subgradients are orthogonal to the corresponding lifted decisions, leaving the comparator scale free to optimize in the regret analysis. Applying Follow-the-Regularized-Leader (FTRL) and Online Mirror Descent (OMD) on the cone recovers Conic Blackwell Algorithm (CBA) and Conic Blackwell Algorithm Plus (CBA$^+$) on bounded domains in Hilbert spaces and extends them to finite-dimensional normed spaces with a strongly convex squared norm. For arbitrary nonempty closed convex domains in these spaces, a known gradient bound yields parameter-free regret guarantees. Surprisingly, on an unconstrained Hilbert space, the construction recovers the Krichevsky--Trofimov (KT) coin-betting algorithm exactly. We also give a parameter-free algorithm for unconstrained domains that requires no gradient bound.
Wind Farm Layout Optimization places turbines to maximize the expected energy under a wind rose, each turbine lowering the wind downwind. In the EndoWake model the wind field is a variable, propagated by linear inequalities, and layouts are certified by branch-and-check. On a ladder of grids it certifies the $10\times10$ grid and leaves the larger grids open after one hour. We tighten the relaxation by a convexification computed rather than derived: every pattern of turbines inside a small tile of the grid is enumerated once with its power and enters the master as a column. The device is valid because the wind field is antitone, and exact, for the cubic power curve, with a Benders cut at integer layouts. Reduced-cost fixing and propagation between overlapping tiles shrink the master before the tree search, and the tree repeats the fixing at every improving incumbent. The incumbent comes from a tile heuristic or an LP dive. On the same computer as the branch-and-check, the $12\times12$ and $14\times14$ grids close in 48 and 395 seconds. The $16\times16$ grid is certified on five seeds from random starts, one job per seed, the heuristic on a GPU, in 1413 seconds under the uniform rose and 6484 seconds under a non-uniform one. Times are medians. A pre-specified test set of 36 unseen instances with forbidden cells confirms the advantage in the axial setting. Certified means closed at the solver's gap of $10^{-4}$: the optimum lies within it plus a residual of at most 0.00042%.
Training language models whose parameters and optimizer state exceed a single node's memory requires sharding these tensors across devices. Under tensor parallelism (TP) or fully sharded data parallelism (FSDP), matrix-aware optimizers such as Muon introduce communication to perform global matrix operations across shards. We propose Dobb (Distributed Optimizer with Block-diagonal Eigenbases), a matrix-aware optimizer designed to compute updates locally within parameter shards. Dobb approximates the input-activation second moment with diagonal blocks and tracks a complete basis within each block. It projects momentum into these bases, applies sign normalization to the coefficients, and reconstructs the update. When each block lies within one shard under TP or FSDP, Dobb applies its matrix update locally, requiring no communication beyond data-parallel synchronization of the activation second moments. We benchmark Dobb against Dion, a distributed matrix-aware optimizer designed to retain the benefits of orthonormalized updates while reducing communication. On GPT-2 XL (1.56B parameters), Dobb with 16 blocks reaches a validation loss of 2.476, compared with 2.511 for Dion at rank fraction 1/16. Under FSDP on 32 H100 GPUs, Dobb reduces the amortized optimizer-call time from 124.1 ms for Dion to 9.2 ms.
Chenxi Li, Yao Shu, Siyang Gao, Shuang Qiu, Guangxin Jiang
Many applications of multi-objective reinforcement learning (MORL) require policies that balance conflicting objectives while satisfying safety constraints. We study safe MORL with zero constraint violation throughout learning, covering both cumulative and stepwise constraints. A key challenge is to explore sufficiently under unknown dynamics and constraint costs without violating the constraints. For a given preference over objectives, we develop an algorithm to learn a safe Pareto optimal policy by combining optimistic reward estimates with pessimistic cost bounds. With high probability, every policy executed over $T$ episodes incurs zero constraint violation. The algorithm returns a safe Markov policy induced by the averaged occupancy measure and achieves an $\widetilde{O}(1/\sqrt{T})$ suboptimality gap under smooth Tchebycheff scalarization. We further develop a preference-free algorithm that first explores safely without a prespecified preference and then computes a safe policy for any given preference without further interaction. Over $T$ exploration episodes and $K$ planning iterations, it retains the same safety guarantee and achieves an $\widetilde{O}(1/\sqrt{T}+1/\sqrt{K})$ suboptimality gap. Both algorithms require knowledge of a policy that strictly satisfies the constraints and its costs. We then relax these requirements, incurring at most constant cumulative violation. To our knowledge, we provide the first sample-efficient MORL algorithms that guarantee safety for every executed policy.
This paper considers coordinating a heterogeneous team of unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) traversing a domain containing an unknown number of potentially hazardous targets. The UAVs provide aerial sensing using onboard optical cameras, adapting their trajectories to ground routes and target information. We formulate the aerial search problem using ergodic control, which distributes sensing effort according to a spatial information density to balance exploration and target localization. The formulation incorporates dynamic camera field-of-view footprints and pose-dependent probabilistic detection models. Angles-only measurements are processed through Bayesian inference and marginalization over data-association hypotheses to obtain a Poisson multi-Bernoulli (PMB) approximation of the target posterior, representing both detected and undetected targets. This belief directs aerial sensing toward unexplored regions along the ground routes and viewpoints that improve target localization. Ground planning combines chance-constrained target avoidance, enforced through confidence sets, with a void-probability objective that favors routes unlikely to contain threats. We solve each team's optimization problem in a fully decentralized manner using a nested SCvx*--C-ADMM scheme, with outer sequential convex programming iterations and inner distributed consensus optimization, accounting for nonlinearities, nonseparable objectives, and continuous-time inter-agent separation constraints. A closed-loop scheme updates both fleets' trajectories as information becomes available and permits ground motion when the remaining route risk falls below a prescribed threshold. Numerical case studies examine sensing geometry and target uncertainty, compare decentralized and centralized solvers, and demonstrate full closed-loop collaboration between multiple UAVs and UGVs.
Reinforcement learning with verifiable rewards (RLVR) makes a language model solve more problems on the first try and fewer when given many tries: it raises pass@1 while the base model overtakes it at large sampling budget k. Is this a failure of RL to add reasoning, or a transient that more training removes? We settle the question with a theorem. The reversal is a price, and we compute its exact rate. Modeling RLVR as an exponential tilt of a base policy over strategies shared across prompts, we prove that under exclusive specialization every update that raises pass@1 strictly lowers the success of some prompt; a strictly positive price on prompts (Stiemke duality) is the exact condition, and being merely the best strategy on a prompt is provably not enough. When the loss reaches the hardest prompts, it forces a pass@k crossover, and the number of crossings is at most the sign variation of the shift in per-prompt success, a totally positive bound that is tight and that recovers the known single-crossover result as its order-preserving case. The crossover is not a bug to patch: a constrained update traces the exact pass@1 versus pass@k frontier, and removing the crossover entirely costs the entire pass@1 gain. The same tilt identity yields entropy collapse and the entropy-performance law with an identifiable exponent, unifying two literatures under one mechanism. Reinforcement cannot widen the reasoning frontier; it can only move along it, at a price we make measurable by a diagnostic that reads the bound, the order-preserving test, and the price from any evaluation log. There is no free lunch, only a price.
Chan-Eui Song, Jeremy J. Michalek, Christopher McComb
Engineering design frequently involves redesigning a prior solution to adapt to changes in context, such as material prices or system requirements. Redesign often leverages simulators too complex and/or computationally intensive for traditional numerical solvers, which lack engineering knowledge and context, to ensure global solution quality. Large language models (LLMs) can interpret semantic information, including engineering knowledge about the system and changes in context, to help guide search, and recent studies have shown that incorporating this knowledge into optimization can improve search performance. However, how best to combine LLMs with numerical solvers in redesign remains unclear. We develop and test an integrated LLM-optimization approach for redesign and compare three methods for leveraging LLMs (warm start, variable fixing and ReAct) and four black-box solvers (Bayesian optimization, genetic algorithms, mesh adaptive direct search and random search) on an electric vehicle battery pack cost minimization case study across four types of redesign scenarios. We find that the integrated approach can match feasible design discovery of the numerical-solver baselines with 80% fewer simulator evaluations while tripling the fraction of runs that find near-optimal solutions. We find that the best LLM-solver integration approach and the way the prior solution is leveraged depend on the structure of the design requirement change, and that the benefit of increasing LLM model size grows with the extent to which the LLM controls the search. These results show clear potential for LLMs in redesign tasks for guiding or replacing numerical solvers.
We study Gibbs averaging of finite Markov chains with a prescribed stationary distribution $π$. Given a transition matrix $P$ and the Gibbs kernel $G$ induced by a state-space partition, we prove that $GPG$ is an information projection for every admissible Bregman generator $φ$, with divergences defined using transition probabilities relative to $π$. A Pythagorean identity characterizes this projection and recovers the relative entropy and weighted Frobenius cases. A dual characterization identifies $GPG$ as a kernel closest to stationarity among those with the same projection chain as $P$; for relative entropy, it maximizes the entropy rate. The identities also give monotonicity under partition coarsening. For every reversible ergodic baseline $P$, Gibbs averaging cannot increase the squared weighted Frobenius distance to stationarity at any positive integer time, and the inequality is strict unless $P=GPG$. The corresponding mixing time therefore cannot increase. To choose the partition, we identify the divergence of $G$ from stationarity as the exact worst-case divergence of $GPG$ over all $π$-stationary baselines $P$. This objective depends only on the block masses. We give an exact algorithm for concave block costs, including those arising from relative entropy and power generators $φ(u)=u^p$ with $1<p<2$, and a greedy approximation algorithm with a provable guarantee for $p>2$. For power generators $φ(u)=u^p$ with $p>1$, the objective is proportional to Tsallis entropy of order $2-p$: its minimization favors imbalanced block masses when $1<p<2$ and balanced block masses when $p>2$, while all $k$-block partitions have the same objective value when $p=2$. A numerical experiment compares the resulting projected chains with a local Metropolis sampler on a multi-modal $π$.
We study online allocation with increasing returns, where an uncertain number of customers arrive sequentially and can be irrevocably assigned to any product with remaining capacity. Each assignment earns a base reward plus a bonus that is nondecreasing in the number of previous assignments to the same product. Prior work has focused primarily on fixed or diminishing returns. Under increasing returns, the central challenge is that concentrating assignments can unlock large future rewards, while a different product may be preferable if arrivals stop early. We show that classical approaches, including greedy and natural LP-based rounding algorithms, can perform arbitrarily poorly, even with homogeneous bonuses. We evaluate performance through competitive ratios relative to the hindsight offline optimum. For homogeneous bonuses, we establish a tight competitive ratio of $1/2$. For arbitrary heterogeneous bonuses, however, no online algorithm can guarantee a competitive ratio greater than $1/m$, where $m$ is the number of products. By imposing discrete concavity on the bonus functions, we limit the concentration of rewards in later assignments and restore constant guarantees. Under this structure, we develop a re-solving framework that repeatedly selects a planning horizon, constructs a feasible allocation plan from the current state, and executes its assignments in a specific order. For arbitrary arrival distributions, we design distribution-oblivious deterministic and randomized algorithms with competitive ratios of $0.2537$ and $0.3864$, respectively. For known increasing-failure-rate (IFR) arrival distributions, we exploit distributional information to obtain a deterministic $1/2$-competitive algorithm.
In this paper, we introduce a practical GPU-enhanced matrix-free first-order method for solving large-scale conic programming problems, which we refer to as PDCS, standing for the Primal-Dual Conic Programming Solver. Problems that it solves include linear programs, second-order cone programs, convex quadratic programs, and exponential cone programs. The method avoids matrix factorizations and uses sparse matrix-vector multiplication as its core operation, which is memory-efficient and well suited for GPU acceleration. It builds on a variant of the primal-dual hybrid gradient method (PDHG) called reflected restarted Halpern PDHG with averaging, which we prove converges on general conic programs, and further incorporates several practical enhancements. Its GPU implementation, cuPDCS, uses customized computational schemes that assign cones of different types and sizes to different levels of the GPU architecture. Numerical experiments demonstrate that cuPDCS is generally more efficient than state-of-the-art commercial solvers and other first-order methods on large-scale conic program applications, including Fisher market equilibrium problems, Lasso regression, and multi-period portfolio optimization. cuPDCS also exhibits better scalability, efficiency, and robustness compared to other first-order methods on the conic program benchmark dataset CBLIB. These advantages are more pronounced in large-scale settings.
Understanding the loss-landscape geometry near a minimum is key to explaining the implicit bias of gradient-based methods in non-convex optimization problems such as deep neural network training and deep matrix factorization. A central quantity for characterizing this geometry is the maximum eigenvalue of the Hessian of the loss. Currently, its precise role has been obfuscated because no exact expressions for this sharpness measure were known in general settings. In this paper, we present the first exact expression for the maximum eigenvalue of the Hessian of the squared-error loss at any minimizer in deep matrix factorization problems, resolving an open question posed by Mulayoff and Michaeli [2020]. This expression reveals a fundamental property of the loss landscape in deep matrix factorization: It is sufficient, but not necessary, for flatness that, across all layers, the product of the spectral norms of the left and right intermediate factors equals a constant determined by the depth and the spectral norm of the target matrix. Most notably, in both depth-2 matrix factorization and deep overparameterized scalar factorization, we show that this condition is both necessary and sufficient for flatness, which implies that flat minima are spectral-norm balanced and not necessarily balanced in depth-2 matrix factorization. To complement our theory, we provide empirical verification, relying on our exact expression, of an escape phenomenon during gradient-based training near a minimizer of a deep matrix factorization problem.
In this chapter, we explore how a team of autonomous agents can flexibly reconfigure the distribution of its members across many spatially embedded tasks using a task allocation strategy grounded in a generalization of the recently proposed Nonlinear Opinion Dynamics model. Motivated by an adaptive maritime survey application, we couple opinion dynamics directly to spatial movement and examine how the emergent macroscopic allocation is shaped by the interplay between environmental geometry, nature of social interactions, and task demands. We illustrate in simulation how social coupling in the model tunes group cohesion, producing macroscopic allocation patterns ranging from maximally dispersed states, to intermediate semi-dispersed states with a smaller number of distinct subgroups, to maximally cohesive consensus states, in distinct and interpretable parameter regimes. Furthermore, we demonstrate with illustrative examples how a team can reconfigure itself in real time under changing task demands. For allocation scenarios with distance-based task preference and matched number of agents and tasks, we relate numerically the final allocation in the group to the Hungarian optimum, illustrating close-to-optimal performance. We illustrate performance of this method under realistic communication constraints in the MOOS-IvP-Multi simulation environment with simulated autonomous underwater vehicles (AUVs). Together, these examples show how a common set of local interaction rules can support a large range of interpretable macroscopic allocation states and flexible transitions between them.
We (the author and the AI systems that did the heavy lifting) show that the quantum query complexity of minimizing a convex function over a convex subset of $\mathbb{R}^n$ with evaluation and membership queries is $\tildeΩ(n)$, nearly matching the best known upper bound. In particular, we show this even for quadratic minimization, which is equivalent to inverting an $n \times n$ real matrix using matrix-vector queries. We also show linear or nearly linear lower bounds on the quantum query complexity of computing the trace, the sign of the determinant, and the magnitude of the determinant of a real matrix in the matrix-vector query model. We use a novel quantum lower bound technique, the determinantal witness method, based on identifying a witness whose Fourier transform vanishes on low-rank matrices and that correlates well with the function being computed.
Lane-changing (LC) maneuvers are highly challenging vehicle interactions, with substantial implications for traffic safety and efficiency. Developing effective LC strategies for connected and automated vehicles in mixed traffic is complicated by the uncertainty associated with surrounding-vehicle behavior and the computational burden of embedding realistic prediction models within optimization schemes. To capture these complex interactions while retaining tractability, this study proposes a data-driven optimization framework that embeds neural network (NN) surrogates for safety and lateral comfort within a Bézier-curve-based trajectory planner. Specifically, the safety cost during the LC process is quantified via a surrogate composed of an input convex recurrent neural network (ICRNN) encoding the planned trajectory, a fully input convex neural network (FICNN) embedding the LC duration, and a partially input convex neural network (PICNN) decoder fusing them with historical traffic states; separately, another FICNN surrogate approximates the optimal lateral comfort cost as a function of the LC duration. Both surrogates are embedded via linear programming (LP) formulations, avoiding the binary variables required by conventional mixed-integer programming (MIP) approaches for NN-embedded optimization. We further theoretically establish their exactness at optimality and extend the framework to problems with additional analytical objective terms and multiple surrogates. Experiments on a hybrid dataset combining real-world and simulated trajectories demonstrate that the proposed method achieves surrogate accuracy competitive with unconstrained baselines while substantially improving optimization efficiency over conventional MIPs. Closed-loop simulations further show that the proposed planners markedly reduce the weighted planning cost and consistently outperform baseline methods.
Can a shared-weight recurrent Transformer---one that repeatedly applies the same Transformer to update evolving latent states---develop distinct internal roles without being partitioned into separate modules? We study this in Asymmetric Input Recurrence (AIR), a minimal two-state reasoning architecture in which the same Transformer model is reused for both updates (per literature, L and H) and the only built-in difference in the update rule is that the encoded input is injected during L-updates but not H-updates. Across Sudoku-Extreme and Maze, decoded rollouts reveal a consistent split: $z_H$ behaves like a fully committed proposal state, whereas $z_L$ retains local uncertainty and shifting intermediate structure. Freeze interventions provide evidence of dynamical dependence between the two states, with responses that vary across tasks, intervention directions, and seeds. Ablations show that to induce specialization, the shared model needs to be able to tell the two update types apart, either from input injection asymmetry or from a separate level token. Mechanistically, attention analysis shows that L-updates are consistently more local than H-updates in both Sudoku and Maze. Together, these results show that, in a two-state recurrent setting, a clear state-identity signal can induce stable, related functional roles inside a shared-parameter recurrent Transformer. Code is available at https://github.com/juchengshen/air.
The empirical success of matrix-aware optimizers, such as Muon (Jordan et al., 2024) and Shampoo (arXiv:1802.09568), highlights the potential of non-Euclidean geometry for deep learning, including large language model (LLM) training. Despite this progress, the theoretical understanding of stochastic optimization in general normed spaces remains limited, particularly in distributed settings. We analyze minibatch stochastic gradient descent (SGD) for smooth nonconvex optimization with respect to an arbitrary norm on a finite-dimensional space. Using the framework of $κ$-regular normed spaces (arXiv:0809.0813), we derive high-probability oracle complexity bounds under a light-tail condition stated directly in the dual norm induced by the update norm. The bounds make the dependence on geometry explicit through the regularity constant $κ$ of the dual space. In the Euclidean case, our bound recovers the standard minibatch SGD rate up to logarithmic factors. For some non-Euclidean geometries and noise models, it is sharper than bounds obtained by converting a Euclidean noise assumption, reducing a linear dimension dependence to a logarithmic one. Building on this framework, we introduce Rennala NSGD, a semi-asynchronous distributed algorithm, and establish wall-clock time complexity guarantees under fixed, heterogeneous worker computation times. In the Euclidean case ($κ=1$), our bound matches the parameter dependence of classical Rennala SGD up to logarithmic factors.
We present cuPDQPx, a GPU-accelerated, factorization-free first-order solver for large-scale convex quadratic programming (QP). Building on the restarted reflected Halpern primal-dual framework of cuPDLPx, we introduce an auxiliary-variable splitting that yields explicit updates without linearizing the quadratic objective or solving inner quadratic subproblems. A preconditioned proximal point interpretation yields both sublinear and linear fixed-point residual convergence guarantees. For practical efficiency, cuPDQPx integrates diagonal preconditioning, step-size selection, adaptive restart, and adaptive primal and quadratic weight updates. cuPDQPx is implemented in C and CUDA with optimized sparse matrix-vector products, kernel fusion, and CUDA Graphs. Numerical experiments on the Maros-Mészáros collection, a convex subset of QPLIB, and synthetic large-scale QPs demonstrate that cuPDQPx has strong numerical performance at both $10^{-4}$ and $10^{-8}$ tolerances.