English
Related papers

Related papers: Non-exponentially weighted aggregation: regret bou…

200 papers

In online learning the performance of an algorithm is typically compared to the performance of a fixed function from some class, with a quantity called regret. Forster proposed a last-step min-max algorithm which was somewhat simpler than…

Machine Learning · Computer Science 2013-01-28 Edward Moroshko , Koby Crammer

Mixability of a loss is known to characterise when constant regret bounds are achievable in games of prediction with expert advice through the use of Vovk's aggregating algorithm. We provide a new interpretation of mixability via convex…

Machine Learning · Computer Science 2014-03-12 Mark D. Reid , Rafael M. Frongillo , Robert C. Williamson

We propose an optimal iterative scheme for federated transfer learning, where a central planner has access to datasets ${\cal D}_1,\dots,{\cal D}_N$ for the same learning model $f_{\theta}$. Our objective is to minimize the cumulative…

Machine Learning · Computer Science 2024-10-04 Xuwei Yang , Anastasis Kratsios , Florian Krach , Matheus Grasselli , Aurelien Lucchi

We study online convex optimization on $\ell_p$-balls in $\mathbb{R}^d$ for $p > 2$. While always sub-linear, the optimal regret exhibits a shift between the high-dimensional setting ($d > T$), when the dimension $d$ is greater than the…

Machine Learning · Computer Science 2025-12-01 Emmeran Johnson , David Martínez-Rubio , Ciara Pike-Burke , Patrick Rebeschini

We consider a general framework of online learning with expert advice where regret is defined with respect to sequences of experts accepted by a weighted automaton. Our framework covers several problems previously studied, including…

Machine Learning · Computer Science 2017-10-24 Mehryar Mohri , Scott Yang

We study the adversarial kernel bandit problem, in which the loss at each round is induced by an arbitrary bounded element of a reproducing kernel Hilbert space (RKHS). We propose an exponential-weights algorithm built on a regularized…

Machine Learning · Computer Science 2026-05-27 Yu-Jie Zhang , Hao Qiu , Jonathan Scarlett , Kevin Jamieson

In this paper, we study a class of online optimization problems with long-term budget constraints where the objective functions are not necessarily concave (nor convex) but they instead satisfy the Diminishing Returns (DR) property.…

Optimization and Control · Mathematics 2019-07-02 Omid Sadeghi , Maryam Fazel

In a low-rank linear bandit problem, the reward of an action (represented by a matrix of size $d_1 \times d_2$) is the inner product between the action and an unknown low-rank matrix $\Theta^*$. We propose an algorithm based on a novel…

Machine Learning · Statistics 2020-10-20 Yangyi Lu , Amirhossein Meisami , Ambuj Tewari

We consider the Scale-Free Adversarial Multi Armed Bandits(MAB) problem. At the beginning of the game, the player only knows the number of arms $n$. It does not know the scale and magnitude of the losses chosen by the adversary or the…

Machine Learning · Computer Science 2021-10-12 Sudeep Raja Putta , Shipra Agrawal

In recommender system or crowdsourcing applications of online learning, a human's preferences or abilities are often a function of the algorithm's recent actions. Motivated by this, a significant line of work has formalized settings where…

Machine Learning · Statistics 2023-05-05 Dhruv Malik , Conor Igoe , Yuanzhi Li , Aarti Singh

Consider the classical problem of predicting the next bit in a sequence of bits. A standard performance measure is {\em regret} (loss in payoff) with respect to a set of experts. For example if we measure performance with respect to two…

Machine Learning · Computer Science 2013-04-30 Rina Panigrahy , Preyas Popat

We consider the problem of learning personalized decision policies from observational bandit feedback data across multiple heterogeneous data sources. In our approach, we introduce a novel regret analysis that establishes finite-sample…

Machine Learning · Computer Science 2024-10-14 Aldo Gael Carranza , Susan Athey

We investigate the \emph{linear contextual bandit problem} with independent and identically distributed (i.i.d.) contexts. In this problem, we aim to develop a \emph{Best-of-Both-Worlds} (BoBW) algorithm with regret upper bounds in both…

Machine Learning · Computer Science 2025-05-29 Masahiro Kato , Shinji Ito

We study reinforcement learning (RL) for a class of continuous-time linear-quadratic (LQ) control problems for diffusions, where states are scalar-valued and running control rewards are absent but volatilities of the state processes depend…

Machine Learning · Computer Science 2025-07-25 Yilie Huang , Yanwei Jia , Xun Yu Zhou

Most known regret bounds for reinforcement learning are either episodic or assume an environment without traps. We derive a regret bound without making either assumption, by allowing the algorithm to occasionally delegate an action to an…

Machine Learning · Computer Science 2019-07-22 Vanessa Kosoy

In this paper, we consider the problem of distributed online convex optimization, where a group of agents collaborate to track the global minimizers of a sum of time-varying objective functions in an online manner. Specifically, we propose…

Optimization and Control · Mathematics 2020-10-14 Yan Zhang , Robert J. Ravier , Vahid Tarokh , Michael M. Zavlanos

We consider the online convex optimization problem. In the setting of arbitrary sequences and finite set of parameters, we establish a new fast-rate quantile regret bound. Then we investigate the optimization into the L1-ball by…

Statistics Theory · Mathematics 2018-05-24 Pierre Gaillard , Olivier Wintenberger

Reinforcement learning from human feedback (RLHF) replaces hard-to-specify rewards with pairwise trajectory preferences, yet regret-oriented theory often assumes that preference labels are generated consistently from a single ground-truth…

Machine Learning · Computer Science 2026-04-03 Ming Shi , Yingbin Liang , Ness B. Shroff , Ananthram Swami

We study online decision making problems under resource constraints, where both reward and cost functions are drawn from distributions that may change adversarially over time. We focus on two canonical settings: $(i)$ online resource…

Machine Learning · Computer Science 2025-06-19 Francesco Emanuele Stradi , Matteo Castiglioni , Alberto Marchesi , Nicola Gatti , Christian Kroer

We derive an alternative proof for the regret of Thompson sampling (\ts) in the stochastic linear bandit setting. While we obtain a regret bound of order $\widetilde{O}(d^{3/2}\sqrt{T})$ as in previous results, the proof sheds new light on…

Machine Learning · Statistics 2019-11-06 Marc Abeille , Alessandro Lazaric