The paper studies contextual bilateral trade with full feedback, showing that action-independent observations eliminate the usual polynomial adaptation penalty seen in heavy-tailed bandits. It presents fully parameter-free algorithms that achieve oracle minimax regret rates without knowing the moment order or scale, and derives new regret bounds for both parametric and nonparametric settings. The key technical insight is a paired squared‑loss statistic whose noise cancels, enabling model selection and yielding regret rates that interpolate between classical nonparametric and linear extremes.
By Hangyi Zhao
arXiv:2606. 18527v1 Announce Type: cross Abstract: U-calibration studies online forecasting algorithms whose predictions can be consumed by any unknown downstream agent, guaranteeing sublinear regret simultaneously for all proper loss functions.
By Rafael Frongillo, Haipeng Luo, Nishant A. Mehta, Jon Schneider
arXiv:2609.38375v1 Announce Type: new
Abstract: Can a constant number of linear minimizations per round improve on the $T^{3/4}$ regret rate of online Frank-Wolfe on general convex sets? Weibel et al...
By Mohit Sinha
arXiv:2608. 15996v1 Announce Type: new Abstract: We study second-order path-length regret in adversarial $K$-armed bandits against oblivious loss sequences.
By Mengxiao Zhang
arXiv:2603. 25029v4 Announce Type: replace Abstract: We study online convex optimization (OCO) with two-point bandit feedback against a non-anticipating adaptive adversary.
By Haishan Ye
arXiv:2607. 28856v1 Announce Type: new Abstract: Swap-agnostic learning strengthens classical agnostic learning by allowing the comparator to select a different hypothesis on each level set of the learner's predictions.
By Princewill Okoroafor
arXiv:2608. 10869v1 Announce Type: new Abstract: Worst-case multiclass bounds do not become smaller when the best classifier is already nearly correct: what is missing is an optimistic rate, a guarantee whose fluctuation scales with the oracle risk itself.
By Xiaoyu Li, Andi Han, Jiaojiao Jiang, Junbin Gao
We study the problem of \emph{adversarially robust} PAC learning. In this framework, the learner observes independent samples from an unknown distribution over $\mathcal{X} \times \{0,1\}$, as in clas...
arXiv:2609.24260v1 Announce Type: cross
Abstract: We study the problem of \emph{adversarially robust} PAC learning. In this framework, the learner observes independent samples from an unknown distrib...
By Steve Hanneke, Amirreza Shaeiri
arXiv:2607. 19689v1 Announce Type: cross Abstract: We study the problem of recalibrating an online predictor [KE17, OKS24]: given an arbitrary "hint" sequence of forecasts, the learner must output new predictions that are calibrated while incurring small excess error relative to the original forecasts, under a proper loss.
By Lunjia Hu, Kevin Tian, Chutong Yang
arXiv:2607. 19854v1 Announce Type: new Abstract: We study horizon-free regret minimization for finite-horizon time-homogeneous tabular Markov decision processes with $S$ states, $A$ actions, horizon $H$, and per-trajectory total reward bounded by $1$.
By Runlong Zhou, Zihan Zhang, Maryam Fazel, Simon S. Du
arXiv:2309. 06349v2 Announce Type: replace-cross Abstract: Thompson sampling (TS) is one of the most popular and earliest algorithms to solve stochastic multi-armed bandit problems.
By Prateek Jaiswal, Debdeep Pati, Anirban Bhattacharya, Bani K. Mallick