English
Related papers

Related papers: Demystifying the unreasonable effectiveness of onl…

200 papers

This work theoretically studies a ubiquitous reinforcement learning policy for controlling the canonical model of continuous-time stochastic linear-quadratic systems. We show that randomized certainty equivalent policy addresses the…

Machine Learning · Computer Science 2022-08-23 Mohamad Kazem Shirani Faradonbeh

We study the problem of online learning (OL) from revealed preferences: a learner wishes to learn a non-strategic agent's private utility function through observing the agent's utility-maximizing actions in a changing environment. We adopt…

Optimization and Control · Mathematics 2021-06-07 Violet Xinying Chen , Fatma Kılınç-Karzan

We present tools for the analysis of Follow-The-Regularized-Leader (FTRL), Dual Averaging, and Mirror Descent algorithms when the regularizer (equivalently, prox-function or learning rate schedule) is chosen adaptively based on the data.…

Machine Learning · Computer Science 2015-11-10 H. Brendan McMahan

Motivated by the strategic participation of electricity producers in electricity day-ahead market, we study the problem of online learning in repeated multi-unit uniform price auctions focusing on the adversarial opposing bid setting. The…

Computer Science and Game Theory · Computer Science 2025-01-20 Marius Potfer , Dorian Baudry , Hugo Richard , Vianney Perchet , Cheng Wan

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

We consider an online two-stage stochastic optimization with long-term constraints over a finite horizon of $T$ periods. At each period, we take the first-stage action, observe a model parameter realization and then take the second-stage…

Machine Learning · Computer Science 2024-05-21 Jiashuo Jiang

Reinforcement Learning with Human Feedback (RLHF) has become crucial for aligning Large Language Models (LLMs) with human intent. However, existing offline RLHF approaches suffer from overoptimization, where language models degrade by…

Machine Learning · Computer Science 2026-04-20 Sharan Sahu , Martin T. Wells

Projection-free online learning has drawn increasing interest due to its efficiency in solving high-dimensional problems with complicated constraints. However, most existing projection-free online methods focus on minimizing the static…

Machine Learning · Computer Science 2023-05-22 Yibo Wang , Wenhao Yang , Wei Jiang , Shiyin Lu , Bing Wang , Haihong Tang , Yuanyu Wan , Lijun Zhang

In Apprenticeship Learning (AL), we are given a Markov Decision Process (MDP) without access to the cost function. Instead, we observe trajectories sampled by an expert that acts according to some policy. The goal is to find a policy that…

Machine Learning · Computer Science 2021-12-30 Lior Shani , Tom Zahavy , Shie Mannor

We study the problem of reinforcement learning in infinite-horizon discounted linear Markov decision processes (MDPs), and propose the first computationally efficient algorithm achieving rate-optimal regret guarantees in this setting. Our…

Machine Learning · Computer Science 2026-03-16 Antoine Moulin , Gergely Neu , Luca Viano

We develop a framework for designing simple and efficient policies for a family of online allocation and pricing problems, that includes online packing, budget-constrained probing, dynamic pricing, and online contextual bandits with…

Optimization and Control · Mathematics 2020-08-03 Alberto Vera , Siddhartha Banerjee , Itai Gurvich

Online linear programming (OLP) has found broad applications in revenue management and resource allocation. State-of-the-art OLP algorithms achieve low regret by repeatedly solving linear programming (LP) subproblems that incorporate…

Machine Learning · Statistics 2025-11-04 Jingruo Sun , Wenzhi Gao , Ellen Vitercik , Yinyu Ye

While Bayesian-based exploration often demonstrates superior empirical performance compared to bonus-based methods in model-based reinforcement learning (RL), its theoretical understanding remains limited for model-free settings. Existing…

Machine Learning · Computer Science 2026-02-05 He Wang , Xingyu Xu , Yuejie Chi

Reinforcement Learning from Human Feedback (RLHF) leverages a Kullback-Leibler (KL) divergence loss to stabilize training and prevent overfitting. However, in methods such as GRPO, its implementation may be guided by principles from…

Machine Learning · Computer Science 2025-10-07 Kezhao Liu , Jason Klein Liu , Mingtao Chen , Yiming Liu

We study the problem of minimizing swap regret in structured normal-form games. Players have a very large (potentially infinite) number of pure actions, but each action has an embedding into $d$-dimensional space and payoffs are given by…

Machine Learning · Computer Science 2025-02-14 Maxwell Fishelson , Robert Kleinberg , Princewill Okoroafor , Renato Paes Leme , Jon Schneider , Yifeng Teng

Reinforcement Learning from Human Feedback (RLHF) has emerged as a key technique for post-training large language models. Despite its empirical success, the theoretical understanding of RLHF is still limited, as learning the KL-regularized…

Machine Learning · Computer Science 2025-10-29 Di Wu , Chengshuai Shi , Jing Yang , Cong Shen

We study an asynchronous online learning setting with a network of agents. At each time step, some of the agents are activated, requested to make a prediction, and pay the corresponding loss. The loss function is then revealed to these…

Machine Learning · Computer Science 2020-01-16 Nicolò Cesa-Bianchi , Tommaso R. Cesari , Claire Monteleoni

We introduce \textsc{$k$-lazyGD}, an online learning algorithm that bridges the gap between greedy Online Gradient Descent (OGD, for $k{=}1$) and lazy GD/dual-averaging (for $k{=}T$), creating a spectrum between reactive and stable updates.…

Machine Learning · Computer Science 2026-05-11 Naram Mhaisen , George Iosifidis

In this paper, we consider two paradigms that are developed to account for uncertainty in optimization models: robust optimization (RO) and joint estimation-optimization (JEO). We examine recent developments on efficient and scalable…

Optimization and Control · Mathematics 2018-04-16 Nam Ho-Nguyen , Fatma Kilinc-Karzan

We address the problem of the achievable regret rates with online logistic regression. We derive lower bounds with logarithmic regret under $L_1$, $L_2$, and $L_\infty$ constraints on the parameter values. The bounds are dominated by $d/2…

Machine Learning · Computer Science 2020-02-20 Gil I. Shamir