English
Related papers

Related papers: An aggregating strategy for shifting experts in di…

200 papers

We tackle the problem of online optimization with a general, possibly unbounded, loss function. It is well known that when the loss is bounded, the exponentially weighted aggregation strategy (EWA) leads to a regret in $\sqrt{T}$ after $T$…

Machine Learning · Statistics 2022-01-17 Pierre Alquier

Motivated by learning of correlated equilibria in non-cooperative games, we perform a large deviations analysis of a regret minimizing stochastic approximation algorithm. The regret minimization algorithm we consider comprises multiple…

Optimization and Control · Mathematics 2024-06-04 Hongjiang Qian , Vikram Krishnamurthy

To deal with changing environments, a new performance measure -- adaptive regret, defined as the maximum static regret over any interval, was proposed in online learning. Under the setting of online convex optimization, several algorithms…

Machine Learning · Computer Science 2025-08-04 Lijun Zhang , Wenhao Yang , Guanghui Wang , Wei Jiang , Zhi-Hua Zhou

We study the problem of online sequential decision-making given auxiliary demonstrations from experts who made their decisions based on unobserved contextual information. These demonstrations can be viewed as solving related but slightly…

Machine Learning · Computer Science 2025-06-17 Vahid Balazadeh , Keertana Chidambaram , Viet Nguyen , Rahul G. Krishnan , Vasilis Syrgkanis

This paper investigates how to incorporate expert observations (without explicit information on expert actions) into a deep reinforcement learning setting to improve sample efficiency. First, we formulate an augmented policy loss combining…

Machine Learning · Computer Science 2025-02-28 Erhan Can Ozcan , Vittorio Giammarino , James Queeney , Ioannis Ch. Paschalidis

We introduce a novel online learning framework that unifies and generalizes pre-established models, such as delayed and corrupted feedback, to encompass adversarial environments where action feedback evolves over time. In this setting, the…

Machine Learning · Computer Science 2024-05-28 Yogev Bar-On , Yishay Mansour

We consider the adversarial multi-armed bandit problem under delayed feedback. We analyze variants of the Exp3 algorithm that tune their step-size using only information (about the losses and delays) available at the time of the decisions,…

Machine Learning · Computer Science 2020-10-14 András György , Pooria Joulani

We consider regression under the "extremely small $n$ large $p$" condition, where the number of samples $n$ is so small compared to the dimensionality $p$ that predictors cannot be estimated without prior knowledge. This setup occurs in…

Machine Learning · Computer Science 2017-02-08 Marta Soare , Muhammad Ammad-ud-din , Samuel Kaski

We consider the classic problem of online convex optimisation. Whereas the notion of static regret is relevant for stationary problems, the notion of switching regret is more appropriate for non-stationary problems. A switching regret is…

Machine Learning · Computer Science 2025-03-07 Stephen Pasteris , Chris Hicks , Vasilios Mavroudis , Mark Herbster

We present distributed algorithms that can be used by multiple agents to align their estimates with a particular value over a network with time-varying connectivity. Our framework is general in that this value can represent a consensus…

Optimization and Control · Mathematics 2010-04-20 Angelia Nedić , Asuman Ozdaglar , Pablo A. Parrilo

In many online decision processes, the optimizing agent is called to choose between large numbers of alternatives with many inherent similarities; in turn, these similarities imply closely correlated losses that may confound standard…

Machine Learning · Computer Science 2022-06-22 Matthieu Martin , Panayotis Mertikopoulos , Thibaud Rahier , Houssam Zenati

Recent research suggests that combining AI models with a human expert can exceed the performance of either alone. The combination of their capabilities is often realized by learning to defer algorithms that enable the AI to learn to decide…

Machine Learning · Computer Science 2023-04-18 Patrick Hemmer , Lukas Thede , Michael Vössing , Johannes Jakubik , Niklas Kühl

We study an online mixed discrete and continuous optimization problem where a decision maker interacts with an unknown environment for a number of $T$ rounds. At each round, the decision maker needs to first jointly choose a discrete and a…

Optimization and Control · Mathematics 2024-08-27 Lintao Ye , Ming Chi , Zhi-Wei Liu , Xiaoling Wang , Vijay Gupta

One of the goals of learning algorithms is to complement and reduce the burden on human decision makers. The expert deferral setting wherein an algorithm can either predict on its own or defer the decision to a downstream expert helps…

Machine Learning · Computer Science 2022-07-21 Mohammad-Amin Charusaie , Hussein Mozannar , David Sontag , Samira Samadi

For the prediction with experts' advice setting, we construct forecasting algorithms that suffer loss not much more than any expert in the pool. In contrast to the standard approach, we investigate the case of long-term forecasting of time…

Machine Learning · Computer Science 2019-02-28 Alexander Korotin , Vladimir V'yugin , Evgeny Burnaev

We study the problem of non-stationary dueling bandits and provide the first adaptive dynamic regret algorithm for this problem. The only two existing attempts in this line of work fall short across multiple dimensions, including…

Machine Learning · Computer Science 2022-10-27 Thomas Kleine Buening , Aadirupa Saha

Gradient descent is arguably one of the most popular online optimization methods with a wide array of applications. However, the standard implementation where agents simultaneously update their strategies yields several undesirable…

Computer Science and Game Theory · Computer Science 2019-07-11 James P. Bailey , Gauthier Gidel , Georgios Piliouras

A key challenge in online learning is that classical algorithms can be slow to adapt to changing environments. Recent studies have proposed "meta" algorithms that convert any online learning algorithm to one that is adaptive to changing…

Machine Learning · Statistics 2017-11-08 Kwang-Sung Jun , Francesco Orabona , Stephen Wright , Rebecca Willett

This paper describes a new parameter-free online learning algorithm for changing environments. In comparing against algorithms with the same time complexity as ours, we obtain a strongly adaptive regret bound that is a factor of at least…

Machine Learning · Statistics 2017-08-08 Kwang-Sung Jun , Francesco Orabona , Rebecca Willett , Stephen Wright

Learning-to-Defer (L2D) methods route each query either to a predictive model or to external experts. While existing work studies this problem in batch settings, real-world deployments require handling streaming data, changing expert…

Machine Learning · Statistics 2026-05-29 Dang Hoang Duy , Yannis Montreuil , Maxime Meyer , Axel Carlier , Lai Xing Ng , Wei Tsang Ooi