English
Related papers

Related papers: Nonlinear stochastic multiarmed bandit problems wi…

200 papers

An algorithm is proposed, analyzed, and tested experimentally for solving stochastic optimization problems in which the decision variables are constrained to satisfy equations defined by deterministic, smooth, and nonlinear functions. It is…

Optimization and Control · Mathematics 2021-07-09 Frank E. Curtis , Daniel P. Robinson , Baoyu Zhou

We study the safe reinforcement learning problem with nonlinear function approximation, where policy optimization is formulated as a constrained optimization problem with both the objective and the constraint being nonconvex functions. For…

Machine Learning · Computer Science 2019-10-29 Ming Yu , Zhuoran Yang , Mladen Kolar , Zhaoran Wang

We study unconstrained optimization problems with nonsmooth and convex objective function in the form of a mathematical expectation. The proposed method approximates the expected objective function with a sample average function using…

Optimization and Control · Mathematics 2022-11-03 Natasa Krejic , Natasa Krklec Jerinkic , Tijana Ostojic

In this paper we present a convergence rate analysis of inexact variants of several randomized iterative methods. Among the methods studied are: stochastic gradient descent, stochastic Newton, stochastic proximal point and stochastic…

Optimization and Control · Mathematics 2019-03-20 Nicolas Loizou , Peter Richtárik

In this paper, we propose a multilevel stochastic framework for the solution of nonconvex unconstrained optimization problems. The proposed approach uses random regularized first-order models that exploit an available hierarchical…

Optimization and Control · Mathematics 2025-11-27 Filippo Marini , Margherita Porcelli , Elisa Riccietti

We consider robust optimization problems, where the goal is to optimize in the worst case over a class of objective functions. We develop a reduction from robust improper optimization to Bayesian optimization: given an oracle that returns…

Machine Learning · Computer Science 2017-07-05 Robert Chen , Brendan Lucier , Yaron Singer , Vasilis Syrgkanis

In this paper we analyze several new methods for solving nonconvex optimization problems with the objective function formed as a sum of two terms: one is nonconvex and smooth, and another is convex but simple and its structure is known.…

Optimization and Control · Mathematics 2014-06-25 A. Patrascu , I. Necoara

In this paper, we consider smooth convex optimization problems with simple constraints and inexactness in the oracle information such as value, partial or directional derivatives of the objective function. We introduce a unifying framework,…

Optimization and Control · Mathematics 2020-12-17 Pavel Dvurechensky , Alexander Gasnikov , Alexander Tiurin , Vladimir Zholobov

This paper considers the problem of maximizing an expectation function over a finite set, or finite-arm bandit problem. We first propose a naive stochastic bandit algorithm for obtaining a probably approximately correct (PAC) solution to…

Optimization and Control · Mathematics 2022-06-16 Marie Billaud-Friess , Arthur Macherey , Anthony Nouy , Clémentine Prieur

Saddle-point or primal-dual methods have recently attracted renewed interest as a systematic technique to design distributed algorithms which solve convex optimization problems. When implemented online for streaming data or as dynamic…

Optimization and Control · Mathematics 2021-04-22 John W. Simpson-Porco , Bala Kameshwar Poolla , Nima Monshizadeh , Florian Dorfler

Satisficing is a relaxation of maximizing and allows for less risky decision making in the face of uncertainty. We propose two sets of satisficing objectives for the multi-armed bandit problem, where the objective is to achieve reward-based…

Machine Learning · Computer Science 2016-12-20 Paul Reverdy , Vaibhav Srivastava , Naomi Ehrich Leonard

We give in this paper a convergence result concerning parallel synchronous algorithm for nonlinear fixed point problems with respect to the euclidian norm in $\Rn$. We then apply this result to some problems related to convex analysis like…

Numerical Analysis · Mathematics 2007-05-23 Ahmed Addou , Abdenasser Benahmed

Many stochastic optimization algorithms work by estimating the gradient of the cost function on the fly by sampling datapoints uniformly at random from a training set. However, the estimator might have a large variance, which inadvertently…

Machine Learning · Computer Science 2017-08-10 Farnood Salehi , L. Elisa Celis , Patrick Thiran

In this paper, we consider a novel variant of the multi-armed bandit (MAB) problem, MAB with cost subsidy, which models many real-life applications where the learning agent has to pay to select an arm and is concerned about optimizing…

Machine Learning · Computer Science 2021-03-16 Deeksha Sinha , Karthik Abinav Sankararama , Abbas Kazerouni , Vashist Avadhanula

We consider a multiobjective multiarmed bandit problem with lexicographically ordered objectives. In this problem, the goal of the learner is to select arms that are lexicographic optimal as much as possible without knowing the arm reward…

Machine Learning · Computer Science 2019-07-30 Alihan Hüyük , Cem Tekin

In a typical stochastic multi-armed bandit problem, the objective is often to maximize the expected sum of rewards over some time horizon $T$. While the choice of a strategy that accomplishes that is optimal with no additional information,…

Machine Learning · Computer Science 2023-11-01 Reda Alami , Mohammed Mahfoud , Mastane Achab

We develop an inexact primal-dual first-order smoothing framework to solve a class of non-bilinear saddle point problems with primal strong convexity. Compared with existing methods, our framework yields a significant improvement over the…

Optimization and Control · Mathematics 2023-07-25 Le Thi Khanh Hien , Renbo Zhao , William B. Haskell

We study the stochastic multi-armed bandits problem in the presence of adversarial corruption. We present a new algorithm for this problem whose regret is nearly optimal, substantially improving upon previous work. Our algorithm is agnostic…

Machine Learning · Computer Science 2019-03-29 Anupam Gupta , Tomer Koren , Kunal Talwar

Bandit optimization usually refers to the class of online optimization problems with limited feedback, namely, a decision maker uses only the objective value at the current point to make a new decision and does not have access to the…

Machine Learning · Computer Science 2026-02-18 Yuriy Dorn , Aleksandr Katrutsa , Ilgam Latypov , Anastasiia Soboleva

We consider the problem of online boosting for regression tasks, when only limited information is available to the learner. We give an efficient regret minimization method that has two implications: an online boosting algorithm with noisy…

Machine Learning · Computer Science 2020-07-24 Nataly Brukhim , Elad Hazan