English
Related papers

Related papers: Generalised Entropy MDPs and Minimax Regret

200 papers

In performative prediction, the deployment of a predictive model triggers a shift in the data distribution. As these shifts are typically unknown ahead of time, the learner needs to deploy a model to get feedback about the distribution it…

Machine Learning · Computer Science 2022-07-19 Meena Jagadeesan , Tijana Zrnic , Celestine Mendler-Dünner

We consider Bandits with Knapsacks (henceforth, BwK), a general model for multi-armed bandits under supply/budget constraints. In particular, a bandit algorithm needs to solve a well-known knapsack problem: find an optimal packing of items…

Data Structures and Algorithms · Computer Science 2023-03-08 Nicole Immorlica , Karthik Abinav Sankararaman , Robert Schapire , Aleksandrs Slivkins

In this paper, the problem of maximizing a black-box function $f:\mathcal{X} \to \mathbb{R}$ is studied in the Bayesian framework with a Gaussian Process (GP) prior. In particular, a new algorithm for this problem is proposed, and high…

Machine Learning · Statistics 2018-01-09 Shubhanshu Shekhar , Tara Javidi

We introduce a novel multi-armed bandit framework, where each arm is associated with a fixed unknown credal set over the space of outcomes (which can be richer than just the reward). The arm-to-credal-set correspondence comes from a known…

Machine Learning · Computer Science 2024-05-10 Vanessa Kosoy

There are two variants of the classical multi-armed bandit (MAB) problem that have received considerable attention from machine learning researchers in recent years: contextual bandits and simple regret minimization. Contextual bandits are…

Machine Learning · Statistics 2020-02-27 Aniket Anand Deshmukh , Srinagesh Sharma , James W. Cutler , Mark Moldwin , Clayton Scott

Originally motivated by default risk management applications, this paper investigates a novel problem, referred to as the profitable bandit problem here. At each step, an agent chooses a subset of the K possible actions. For each action…

Machine Learning · Statistics 2018-05-09 Mastane Achab , Stephan Clémençon , Aurélien Garivier

Individual decision-makers consume information revealed by the previous decision makers, and produce information that may help in future decisions. This phenomenon is common in a wide range of scenarios in the Internet economy, as well as…

Computer Science and Game Theory · Computer Science 2019-05-06 Yishay Mansour , Aleksandrs Slivkins , Vasilis Syrgkanis

Bayes estimators are well known to provide a means to incorporate prior knowledge that can be expressed in terms of a single prior distribution. However, when this knowledge is too vague to express with a single prior, an alternative…

Methodology · Statistics 2023-09-04 Hongxiang Qiu , Alex Luedtke

Thompson Sampling has been widely used for contextual bandit problems due to the flexibility of its modeling power. However, a general theory for this class of methods in the frequentist setting is still lacking. In this paper, we present a…

Machine Learning · Computer Science 2021-10-05 Tong Zhang

During the MaxEnt 2002 workshop in Moscow, Idaho, Tony Vignaux asked again a few simple questions about using Maximum Entropy or Bayesian approaches for the famous Dice problems which have been analyzed many times through this workshop and…

Data Analysis, Statistics and Probability · Physics 2009-11-07 Ali Mohammad-Djafari

Most bandit algorithms assume that the reward variances or their upper bounds are known, and that they are the same for all arms. This naturally leads to suboptimal performance and higher regret due to variance overestimation. On the other…

Machine Learning · Computer Science 2023-10-13 Aadirupa Saha , Branislav Kveton

A solution that is only reliable under favourable conditions is hardly a safe solution. Min Max Optimization is an approach that returns optima that are robust against worst case conditions. We propose algorithms that perform Min Max…

Machine Learning · Computer Science 2021-07-30 Dorina Weichert , Alexander Kister

We investigate a natural but surprisingly unstudied approach to the multi-armed bandit problem under safety risk constraints. Each arm is associated with an unknown law on safety risks and rewards, and the learner's goal is to maximise…

Machine Learning · Computer Science 2022-04-05 Tianrui Chen , Aditya Gangrade , Venkatesh Saligrama

We consider Bayesian optimization using Gaussian Process models, also referred to as kernel-based bandit optimization. We study the methodology of exploring the domain using random samples drawn from a distribution. We show that this random…

Machine Learning · Computer Science 2024-02-05 Sudeep Salgia , Sattar Vakili , Qing Zhao

We study the problem of stochastic contextual bandits in the agnostic setting, where the goal is to compete with the best policy in a given class without assuming realizability or imposing model restrictions on losses or rewards. In this…

Machine Learning · Statistics 2026-04-06 Samuel Girard , Aurelien Bibaut , Arthur Gretton , Nathan Kallus , Houssam Zenati

We consider the combinatorial volatile Gaussian process (GP) semi-bandit problem. Each round, an agent is provided a set of available base arms and must select a subset of them to maximize the long-term cumulative reward. We study the…

Machine Learning · Computer Science 2025-02-13 Jack Sandberg , Niklas Åkerblom , Morteza Haghir Chehreghani

Bandits with knapsacks (BwK) is an influential model of sequential decision-making under uncertainty that incorporates resource consumption constraints. In each round, the decision-maker observes an outcome consisting of a reward and a…

Machine Learning · Computer Science 2022-09-27 Raunak Kumar , Robert Kleinberg

Recently, there has been rising interest in Bayesian optimization -- the optimization of an unknown function with assumptions usually expressed by a Gaussian Process (GP) prior. We study an optimization strategy that directly uses an…

Machine Learning · Statistics 2018-08-14 Zi Wang , Bolei Zhou , Stefanie Jegelka

Policy optimization is a widely-used method in reinforcement learning. Due to its local-search nature, however, theoretical guarantees on global optimality often rely on extra assumptions on the Markov Decision Processes (MDPs) that bypass…

Machine Learning · Computer Science 2021-07-20 Haipeng Luo , Chen-Yu Wei , Chung-Wei Lee

In this paper, we consider a best action identification problem in the stochastic linear bandit setup with a fixed confident constraint. In the considered best action identification problem, instead of minimizing the accumulative regret as…

Machine Learning · Computer Science 2018-12-04 Jun Geng , Lifeng Lai