English
Related papers

Related papers: Regret Analysis for Randomized Gaussian Process Up…

200 papers

In this work, we address the open problem of finding low-complexity near-optimal multi-armed bandit algorithms for sequential decision making problems. Existing bandit algorithms are either sub-optimal and computationally simple (e.g.,…

Machine Learning · Computer Science 2018-04-18 Fang Liu , Sinong Wang , Swapna Buccapatnam , Ness Shroff

Stochastic programming is often challenged by epistemic uncertainty, where critical probability distributions are poorly characterized or unknown due to a lack of data. To address this, we pioneer a novel framework for stochastic…

Optimization and Control · Mathematics 2026-05-19 Shixin Liu , Ming Gao , Jian Hu

Gaussian processes have become a promising tool for various safety-critical settings, since the posterior variance can be used to directly estimate the model error and quantify risk. However, state-of-the-art techniques for safety-critical…

Machine Learning · Computer Science 2022-07-22 Alexandre Capone , Armin Lederer , Sandra Hirche

In this work, we study the generalization capability of algorithms from an information-theoretic perspective. It has been shown that the expected generalization error of an algorithm is bounded from above by a function of the relative…

Information Theory · Computer Science 2021-10-27 Borja Rodríguez-Gálvez , Germán Bassi , Mikael Skoglund

We consider stochastic multi-armed bandits where the expected reward is a unimodal function over partially ordered arms. This important class of problems has been recently investigated in (Cope 2009, Yu 2011). The set of arms is either…

Machine Learning · Computer Science 2014-05-21 Richard Combes , Alexandre Proutiere

We introduce a stochastic variational inference procedure for training scalable Gaussian process (GP) models whose per-iteration complexity is independent of both the number of training points, $n$, and the number basis functions used in…

Machine Learning · Statistics 2020-06-05 Trefor W. Evans , Prasanth B. Nair

We introduce Conformal Bandits, a novel framework integrating Conformal Prediction (CP) into bandit problems, a classic paradigm for sequential decision-making under uncertainty. Traditional regret-minimisation bandit strategies like…

Machine Learning · Computer Science 2025-12-11 Simone Cuonzo , Nina Deliu

The Adversarial Markov Decision Process (AMDP) is a learning framework that deals with unknown and varying tasks in decision-making applications like robotics and recommendation systems. A major limitation of the AMDP formalism, however, is…

Machine Learning · Statistics 2024-05-06 Sang Bin Moon , Abolfazl Hashemi

Value-at-risk (VaR) is an established measure to assess risks in critical real-world applications with random environmental factors. This paper presents a novel VaR upper confidence bound (V-UCB) algorithm for maximizing the VaR of a…

Machine Learning · Computer Science 2021-05-14 Quoc Phong Nguyen , Zhongxiang Dai , Bryan Kian Hsiang Low , Patrick Jaillet

The optimized certainty equivalent (OCE) is a family of risk measures that cover important examples such as entropic risk, conditional value-at-risk and mean-variance models. In this paper, we propose a new episodic risk-sensitive…

Machine Learning · Computer Science 2023-06-09 Wenhao Xu , Xuefeng Gao , Xuedong He

Gaussian Process (GP) regression is a flexible modeling technique used to predict outputs and to capture uncertainty in the predictions. However, the GP regression process becomes computationally intensive when the training spatial dataset…

Computation · Statistics 2024-09-19 Juliette Mukangango , Amanda Muyskens , Benjamin W. Priest

We provide improved gap-dependent regret bounds for reinforcement learning in finite episodic Markov decision processes. Compared to prior work, our bounds depend on alternative definitions of gaps. These definitions are based on the…

Machine Learning · Computer Science 2021-10-27 Christoph Dann , Teodor V. Marinov , Mehryar Mohri , Julian Zimmert

We tackle the problem of online reward maximisation over a large finite set of actions described by their contexts. We focus on the case when the number of actions is too big to sample all of them even once. However we assume that we have…

Machine Learning · Computer Science 2013-09-27 Michal Valko , Nathaniel Korda , Remi Munos , Ilias Flaounas , Nelo Cristianini

The Gaussian process (GP) regression model is a widely employed surrogate modeling technique for computer experiments, offering precise predictions and statistical inference for the computer simulators that generate experimental data.…

Methodology · Statistics 2024-04-02 Lulu Kang , Yuanxing Cheng , Yiwei Wang , Chun Liu

We study how to make decisions that minimize Bayesian regret in offline linear bandits. Prior work suggests that one must take actions with maximum lower confidence bound (LCB) on their reward. We argue that the reliance on LCB is…

Machine Learning · Computer Science 2024-07-04 Marek Petrik , Guy Tennenholtz , Mohammad Ghavamzadeh

Stochastic multi-armed bandits (MABs) provide a fundamental reinforcement learning model to study sequential decision making in uncertain environments. The upper confidence bounds (UCB) algorithm gave birth to the renaissance of bandit…

Machine Learning · Computer Science 2024-06-11 Ambrus Tamás , Szabolcs Szentpéteri , Balázs Csanád Csáji

Confidence bounds are an essential tool for rigorously quantifying the uncertainty of predictions. They are a core component in many sequential learning and decision-making algorithms, with tighter confidence bounds giving rise to…

Machine Learning · Statistics 2024-11-12 Hamish Flynn , David Reeb

Many settings involve sequential decision-making where a set of actions can be chosen at each time step, each action provides a stochastic reward, and the distribution for the reward of each action is initially unknown. However, frequent…

Optimization and Control · Mathematics 2019-10-21 Yonatan Mintz , Anil Aswani , Philip Kaminsky , Elena Flowers , Yoshimi Fukuoka

Bayesian optimization (BO) has well-documented merits for optimizing black-box functions with an expensive evaluation cost. Such functions emerge in applications as diverse as hyperparameter tuning, drug discovery, and robotics. BO hinges…

Machine Learning · Statistics 2026-05-28 Qin Lu , Konstantinos D. Polyzos , Bingcong Li , Georgios B. Giannakis

I analyse the frequentist regret of the famous Gittins index strategy for multi-armed bandits with Gaussian noise and a finite horizon. Remarkably it turns out that this approach leads to finite-time regret guarantees comparable to those…

Machine Learning · Computer Science 2016-05-31 Tor Lattimore