arXiv Machine Learning July 14, 2026 By Mo\"ise Blanchard, Dmitrii Ostrovskii, Aadirupa Saha

Bandit PCA with Minimax Optimal Regret

Read the original on arXiv Machine Learning →

arXiv:2607. 10936v1 Announce Type: new Abstract: We study the bandit-feedback version of online principal component analysis (Bandit PCA): in each round $t = 1,\dots,T$, the adversary selects a $d \times d$ symmetric gain matrix $G_t$ with spectrum in $[0,1]$ and rank at most $r$; the learner simultaneously selects a unit vector $w_t \in S^{d-1}$ and receives the reward $w_t^\top G_t w_t$.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

reinforcement-learning

arXiv Machine Learning

Jun 16

Near-Optimal Regret for Distributed Adversarial Bandits: A Black-Box Approach

arXiv:2602. 06404v2 Announce Type: replace Abstract: We study distributed adversarial bandits, where $N$ agents cooperate to minimize the global average loss while observing only their own local losses.

By Hao Qiu, Mengxiao Zhang, Nicol\`o Cesa-Bianchi

agents reinforcement-learning safety

arXiv AI

Aug 6

Efficient Online Lexicographic Generalized Low-Rank Matrix Bandits

arXiv:2608. 04324v1 Announce Type: cross Abstract: This paper studies generalized low-rank matrix bandits with multiple prioritized objectives.

By Bo Xue, Ji Cheng, Haodong Jing, Hongzong Li, Shuang Qiu

arXiv Machine Learning

2d ago

Quantum Multi-Armed Bandits and Linear Bandits: Lower Bounds and Algorithms

arXiv:2608. 14319v1 Announce Type: new Abstract: We study quantum multi-armed bandits (QMAB) and quantum linear bandits (QLB) in the model of Wan et al.

By Maoli Liu, Zhuohua Li, John C. S. Lui

rag reinforcement-learning safety

Hugging Face Trending Papers

Jul 21

The Price of Hidden Curvature: An $\widetildeΩ (d^{5/4} \sqrt{T})$ Lower Bound for Bandit Convex Optimization

We establish a $\widetildeΩ(d^{5/4}\sqrt T)$ lower bound on the minimax expected regret of stochastic bandit convex optimization of $1$-Lipschitz functions on the Euclidean ball. This presents the first nontrivial regret lower bound that grows faster than $d\sqrt{T}$ for this problem, establishing that stochastic bandit convex optimization is fundamentally harder than linear bandits.

reinforcement-learning

arXiv Machine Learning

Jul 22

The Price of Hidden Curvature: An $\widetilde{\Omega} (d^{5/4} \sqrt{T})$ Lower Bound for Bandit Convex Optimization

arXiv:2607. 18652v1 Announce Type: cross Abstract: We establish a $\widetilde\Omega(d^{5/4}\sqrt T)$ lower bound on the minimax expected regret of stochastic bandit convex optimization of $1$-Lipschitz functions on the Euclidean ball.

By Nived Rajaraman

reinforcement-learning

arXiv Machine Learning

Jul 9

Nonlinear Bandit

arXiv:2607. 07304v1 Announce Type: new Abstract: In this paper we first study the problem of generalized linear bandit (GLB) under heavy-tailed noise.

By Tianshuo Zheng, Ting Wu, Zhi-Hua Zhou, Keqin Liu

reinforcement-learning

Related stories

Near-Optimal Regret for Distributed Adversarial Bandits: A Black-Box Approach

Efficient Online Lexicographic Generalized Low-Rank Matrix Bandits

Quantum Multi-Armed Bandits and Linear Bandits: Lower Bounds and Algorithms

The Price of Hidden Curvature: An $\widetildeΩ (d^{5/4} \sqrt{T})$ Lower Bound for Bandit Convex Optimization

The Price of Hidden Curvature: An $\widetilde{\Omega} (d^{5/4} \sqrt{T})$ Lower Bound for Bandit Convex Optimization

Nonlinear Bandit