← 研踪 PaperTrailarXiv:2508.05844 · v3
Online Budget Allocation with Censored Semi-Bandit Feedback
首次提交 2025-08-08 04:47
版本更新 2026-11-05 21:40
雷达观测 2026-11-06 13:11
摘要
We study a stochastic budget-allocation problem over $K$ tasks. At each round $t$, the learner chooses an allocation $X_t \in Δ_K$. Task $k$ succeeds with probability $F_k(X_{t,k})$, where $F_1,\dots,F_K$ are nondecreasing budget-to-success curves, and upon success yields a random reward with unknown mean $μ_k$. The learner observes which tasks succeed, and observes a task's reward only upon success (censored semi-bandit feedback). This model captures, for instance, splitting payments across crowdsourcing workers or distributing bids across simultaneous auctions, and subsumes stochastic multi-armed bandits and semi-bandits. We design an optimism-based algorithm that operates under censored semi-bandit feedback and assumes access to an exact maximization oracle. Our main result is an instance-dependent bound showing that in diminishing-returns regimes, the regret of this algorithm scales polylogarithmically with the horizon $T$ without any ad hoc tuning. For general nondecreasing curves, we prove that the same algorithm (with the same tuning) achieves a worst-case regret upper bound of $\tilde O(K\sqrt{T})$. Finally, we establish a matching worst-case regret lower bound of $Ω(K\sqrt{T})$ that holds even for full-feedback algorithms, highlighting the intrinsic hardness of our problem outside diminishing returns.
作者备注：44 pages, 1 figure. Accepted at NeurIPS 2026. This version revises assumptions and proofs and updates the related work
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v3 · 2026-11-05 21:40 · 最新观测版本
Online Budget Allocation with Censored Semi-Bandit Feedback
We study a stochastic budget-allocation problem over $K$ tasks. At each round $t$, the learner chooses an allocation $X_t \in Δ_K$. Task $k$ succeeds with probability $F_k(X_{t,k})$, where $F_1,\dots,F_K$ are nondecreasing budget-to-success curves, and upon success yields a random reward with unknown mean $μ_k$. The learner observes which tasks succeed, and observes a task's reward only upon success (censored semi-bandit feedback). This model captures, for instance, splitting payments across crowdsourcing workers or distributing bids across simultaneous auctions, and subsumes stochastic multi-armed bandits and semi-bandits. We design an optimism-based algorithm that operates under censored semi-bandit feedback and assumes access to an exact maximization oracle. Our main result is an instance-dependent bound showing that in diminishing-returns regimes, the regret of this algorithm scales polylogarithmically with the horizon $T$ without any ad hoc tuning. For general nondecreasing curves, we prove that the same algorithm (with the same tuning) achieves a worst-case regret upper bound of $\tilde O(K\sqrt{T})$. Finally, we establish a matching worst-case regret lower bound of $Ω(K\sqrt{T})$ that holds even for full-feedback algorithms, highlighting the intrinsic hardness of our problem outside diminishing returns.
查看此版本解读 →查看此版本原文 ↗