The paper studies high‑dimensional linear contextual bandits with knapsack constraints (CBwK), aiming to exploit sparsity for tighter regret bounds. It introduces an online hard‑thresholding estimator integrated into a primal‑dual framework, achieving sub‑linear regret that grows only logarithmically with the feature dimension. Under either a diverse‑covariate or margin condition, the regret improves to τ‑dependent rates, and when both hold simultaneously, a dual resolving scheme yields an even tighter bound. The approach also recovers optimal rates for high‑dimensional contextual bandits without knapsacks, and experiments demonstrate its practical effectiveness.
By Wanteng Ma, Dong Xia, Jiashuo Jiang
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 $w_t^\top G_t w_t$.
By Mo\"ise Blanchard, Dmitrii Ostrovskii, Aadirupa Saha
arXiv:2607. 08979v1 Announce Type: new Abstract: We study the active learning problem of fixed-confidence top-$k$ identification from noisy pairwise comparisons.
By Motti Goldberger, Nils Rudi
arXiv:2605.12340v5 Announce Type: replace-cross
Abstract: Learning-to-Defer (L2D) methods route each query either to a predictive model or to external experts. Real-world deployments require handling...
By Dang Hoang Duy, Yannis Montreuil, Maxime Meyer, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi
arXiv:2602. 09456v2 Announce Type: replace Abstract: We propose an algorithmic framework, Offline Estimation to Decisions (OE2D), that efficiently reduces contextual bandit learning with general reward function approximation to offline regression.
By Hao Qin, Chicheng Zhang
arXiv:2606. 11968v1 Announce Type: new Abstract: This paper studies efficient online algorithms for multinomial logistic bandits (MLogB), where the feedback distribution over $K+1$ outcomes follows a multinomial logistic model of $d$-dimensional action vectors.
By Linzhe He, Yu-Jie Zhang, Sifan Yang, Lijun Zhang
arXiv:2606. 00984v1 Announce Type: cross Abstract: We study linear contextual bandits under rare parameter updates: the learner may incorporate reward feedback into its parameter estimate only at a small number of update times, while still observing contexts online and selecting actions sequentially.
By Sanghoon Yu, Min-hwan Oh
arXiv:2602. 23116v3 Announce Type: replace Abstract: We consider the problem of regularized best-response max-regret minimization in online RLHF under general preferences and bandit feedback.
By Junghyun Lee, Minju Hong, Kwang-Sung Jun, Chulhee Yun, Se-Young Yun
arXiv:2604. 00531v2 Announce Type: replace Abstract: Multi-task representation learning exploits the shared structure among related tasks by learning a common latent representation, thereby improving sample efficiency.
By Jiabin Lin, Shana Moothedath
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.
arXiv:2606. 31449v1 Announce Type: new Abstract: We investigate the contextual slate bandit problem with generalized linear rewards under limited adaptivity.
By Tanmay Goyal, Sukruta Prakash Midigeshi, Gaurav Sinha
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