English
Related papers

Related papers: Regularized Online RLHF with Generalized Bilinear …

200 papers

We develop a novel family of algorithms for the online learning setting with regret against any data sequence bounded by the empirical Rademacher complexity of that sequence. To develop a general theory of when this type of adaptive regret…

Machine Learning · Computer Science 2017-04-14 Dylan J. Foster , Alexander Rakhlin , Karthik Sridharan

Due to the drastic gap in complexity between sequential and batch statistical learning, recent work has studied a smoothed sequential learning setting, where Nature is constrained to select contexts with density bounded by 1/{\sigma} with…

Machine Learning · Statistics 2022-05-27 Adam Block , Max Simchowitz

We propose a framework which generalizes "decision making with structured observations" by allowing robust (i.e. multivalued) models. In this framework, each model associates each decision with a convex set of probability distributions over…

Machine Learning · Computer Science 2025-06-27 Alexander Appel , Vanessa Kosoy

Gradient-variation online learning aims to achieve regret guarantees that scale with variations in the gradients of online functions, which has been shown to be crucial for attaining fast convergence in games and robustness in stochastic…

Machine Learning · Computer Science 2024-11-05 Yan-Feng Xie , Peng Zhao , Zhi-Hua Zhou

We study online learning problems in which a decision maker has to take a sequence of decisions subject to $m$ long-term constraints. The goal of the decision maker is to maximize their total reward, while at the same time achieving small…

Machine Learning · Computer Science 2022-09-16 Matteo Castiglioni , Andrea Celli , Alberto Marchesi , Giulia Romano , Nicola Gatti

State-of-the-art efficient model-based Reinforcement Learning (RL) algorithms typically act by iteratively solving empirical models, i.e., by performing \emph{full-planning} on Markov Decision Processes (MDPs) built by the gathered…

Machine Learning · Computer Science 2019-11-01 Yonathan Efroni , Nadav Merlis , Mohammad Ghavamzadeh , Shie Mannor

We study the generalization performance of online learning algorithms trained on samples coming from a dependent source of data. We show that the generalization error of any stable online algorithm concentrates around its regret--an easily…

Machine Learning · Statistics 2012-06-08 Alekh Agarwal , John C. Duchi

This paper introduces a new problem-dependent regret measure for online convex optimization with smooth losses. The notion, which we call the $G^\star$ regret, depends on the cumulative squared gradient norm evaluated at the decision in…

Machine Learning · Statistics 2026-02-10 Wenzhi Gao , Chang He , Madeleine Udell

Follow-the-Regularized-Leader (FTRL) algorithms are a popular class of learning algorithms for online linear optimization (OLO) that guarantee sub-linear regret, but the choice of regularizer can significantly impact dimension-dependent…

Machine Learning · Computer Science 2024-10-24 Khashayar Gatmiry , Jon Schneider , Stefanie Jegelka

We develop parameter-free algorithms for unconstrained online learning with regret guarantees that scale with the gradient variation $V_T(u) = \sum_{t=2}^T \|\nabla f_t(u)-\nabla f_{t-1}(u)\|^2$. For $L$-smooth convex loss, we provide…

Machine Learning · Computer Science 2026-04-14 Yuheng Zhao , Andrew Jacobsen , Nicolò Cesa-Bianchi , Peng Zhao

Reinforcement Learning from Human Feedback (RLHF) has become a cornerstone technique for post-training large language models. While most existing approaches rely on the reverse KL-regularization, recent empirical studies have begun…

Machine Learning · Computer Science 2026-05-11 Di Wu , Chengshuai Shi , Jing Yang , Cong Shen

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

We uncover a fairly general principle in online learning: If regret can be (approximately) expressed as a function of certain "sufficient statistics" for the data sequence, then there exists a special Burkholder function that 1) can be used…

Machine Learning · Computer Science 2018-03-22 Dylan J. Foster , Alexander Rakhlin , Karthik Sridharan

Recent growing adoption of experimentation in practice has led to a surge of attention to multiarmed bandits as a technique to reduce the opportunity cost of online experiments. In this setting, a decision-maker sequentially chooses among a…

Machine Learning · Computer Science 2022-04-04 Nima Hamidi , Mohsen Bayati

We study online fair allocation of $T$ sequentially arriving items among $n$ agents with heterogeneous preferences, with the objective of maximizing generalized-mean welfare, defined as the $p$-mean of agents' time-averaged utilities, with…

Computer Science and Game Theory · Computer Science 2026-02-12 Zongjun Yang , Rachitesh Kumar , Christian Kroer

We propose a novel contextual bandit algorithm for generalized linear rewards with an $\tilde{O}(\sqrt{\kappa^{-1} \phi T})$ regret over $T$ rounds where $\phi$ is the minimum eigenvalue of the covariance of contexts and $\kappa$ is a lower…

Machine Learning · Statistics 2023-03-02 Wonyoung Kim , Kyungbok Lee , Myunghee Cho Paik

We study a general version of the adversarial online learning problem. We are given a decision set $\mathcal{X}$ in a reflexive Banach space $X$ and a sequence of reward vectors in the dual space of $X$. At each iteration, we choose an…

Machine Learning · Computer Science 2016-06-07 Maximilian Balandat , Walid Krichene , Claire Tomlin , Alexandre Bayen

We investigate the problem of unconstrained combinatorial multi-armed bandits with full-bandit feedback and stochastic rewards for submodular maximization. Previous works investigate the same problem assuming a submodular and monotone…

Machine Learning · Computer Science 2023-02-03 Fares Fourati , Vaneet Aggarwal , Christopher John Quinn , Mohamed-Slim Alouini

This paper investigates regret minimization, statistical inference, and their interplay in high-dimensional online decision-making based on the sparse linear context bandit model. We integrate the $\varepsilon$-greedy bandit algorithm for…

Machine Learning · Computer Science 2025-05-20 Congyuan Duan , Wanteng Ma , Jiashuo Jiang , Dong Xia

Consider the sequential optimization of an expensive to evaluate and possibly non-convex objective function $f$ from noisy feedback, that can be considered as a continuum-armed bandit problem. Upper bounds on the regret performance of…

Machine Learning · Statistics 2021-03-11 Sattar Vakili , Kia Khezeli , Victor Picheny