跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1958新增论文
+1549其中 AI 相关
+212已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-17 19:15 · 全站最近入库:2026-11-17 20:18各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 22:43 — 2026-11-17 22:43(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-17 19:15最近发现新增版本:2026-11-17 20:18库内论文最新更新时间:2026-11-17 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

25,785 已收录论文21,490 AI 相关7,725 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 2 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-17 19:14(北京时间)
版本更新 · v3arXiv:2605.22010

Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks

Margalit Glasgow, Joan Bruna

原文摘要

We consider one-hidden layer neural networks trained in the feature-learning regime using gradient descent, and relate the output of the finite-width network $f_{\hatρ_t^m}$ to its infinite-width counterpart $f_{ρ_t^{MF}}$, which evolves in the mean-field dynamics. While constant-time horizon bounds for $\|f_{ρ_t^{MF}} - f_{\hatρ_t^m}\|$ may be obtained via standard Grönwall estimates, the long-time behavior of the fluctuation is a more delicate matter. Uniform-in-time bounds often rely on (local) strong convexity in the landscape or Logarithmic Sobolev inequalities present in noisy gradient dynamics. In this work, we establish non-asymptotic weak propagation-of-chaos that holds uniformly in time, obtained by exploiting instead the convergence rate of the mean-field deterministic Wasserstein-gradient-flow dynamics. Specifically, denoting by $L_t$ the mean-field excess MSE loss at time $t$ and $m$ the number of neurons, under standard regularity assumptions and the condition $\int_0^\infty L_t^{1/2} dt =O(\log d)$, we obtain the uniform in time bound $\|f_{ρ_t^{MF}}- f_{\hatρ_t^m}\|^2 \lesssim \text{poly}(d) m^{-\min(1,c/6)}$ whenever $L_t \lesssim t^{-c}$. Our result holds in a noiseless setting and does not make any assumptions on the geometry of the landscape near the optimum, and extends seamlessly to other forms of discretization, including finite number of samples and time discretization. A key takeaway of our result is that whenever the convergence rate of the mean-field, population-loss dynamics is faster than $t^{-2}$, we can attain a loss of $ε$ with only $\text{poly}(d/ε)$ neurons, training samples, and GD steps.

stat.ML · cs.LG

新论文 · v1arXiv:2611.12867

SparseStack 的最优单侧注入性

Optimal Injectivity of the SparseStack

Lorenzo Beretta, Simone Bombari, Margalit Glasgow, Raphael Arkady Meyer, Kijun Shin, David P. Woodruff

AI 速读 基于摘要

作者证明 SparseStack 草图在行稀疏度约 √log r 时即可实现线性维度的单侧子空间注入,并给出匹配下界,说明该尺度是本质的。

cs.DS

查看原文摘要

An Oblivious Subspace Injection (OSI) is a random sketching matrix that reliably preserves the minimum singular value of any fixed subspace with high constant probability, requiring only a one-sided spectral lower bound without controlling upper singular values. While classical Oblivious Subspace Embeddings (OSEs) fundamentally require row sparsity $Ω(\log r)$ at linear sketch dimension $k = O(r)$, we show that one-sided injectivity permits strictly sparser sketches, establishing matching (up to $\log\log r$ factors) upper and lower bounds of $\tildeΘ(\sqrt{\log r})$. First, we prove that the SparseStack sketch achieves constant injectivity at linear dimension $k = Θ(r)$ with row sparsity only $ζ= O(\sqrt{\log r})$, well below the $Θ(\log r)$ barrier where standard operator-norm concentration fails. Second, we establish a matching lower bound: any isotropic random sketching matrix satisfying a mild row-overlap condition requires row sparsity $ζ= Ω(\sqrt{\log r / \log \log r})$ to achieve linear-dimension injectivity, confirming that the $\sqrt{\log r}$ scale is fundamental. To bypass the lack of an operator-norm upper bound when $ζ= O(\sqrt{\log r})$, we decouple the sketch into two independent halves and introduce three techniques: (i) a uniform lower bound for flat vectors via randomized rounding, controlling discretization error using solely the Frobenius norm; (ii) a Gaussian truncation and minimax duality argument showing that all non-flat vectors escaping injectivity in the first half concentrate on a single universal coordinate subset $I \subseteq [n]$ of size $O(r/ζ)$, bypassing union bounds over supports; and (iii) a two-tier coordinate isolation analysis in the second half that suppresses collisions to $e^{-Ω(ζ^2)} \ll 1/r$, reliably preserving these heavy coordinates.