English
Related papers

Related papers: (Bandit) Convex Optimization with Biased Noisy Gra…

200 papers

We consider offline policy optimization (OPO) in contextual bandits, where one is given a fixed dataset of logged interactions. While pessimistic regularizers are typically used to mitigate distribution shift, prior implementations thereof…

Machine Learning · Computer Science 2023-10-27 Lequn Wang , Akshay Krishnamurthy , Aleksandrs Slivkins

We study the problem of learning the objective functions or constraints of a multiobjective decision making model, based on a set of sequentially arrived decisions. In particular, these decisions might not be exact and possibly carry…

Machine Learning · Computer Science 2022-12-27 Chaosheng Dong , Yijia Wang , Bo Zeng

Designing efficient general-purpose contextual bandit algorithms that work with large -- or even continuous -- action spaces would facilitate application to important scenarios such as information retrieval, recommendation systems, and…

Machine Learning · Computer Science 2022-07-14 Yinglun Zhu , Paul Mineiro

We consider the setting of online convex optimization with adversarial time-varying constraints in which actions must be feasible w.r.t. a fixed constraint set, and are also required on average to approximately satisfy additional…

Machine Learning · Computer Science 2024-02-15 Dan Garber , Ben Kretzu

Multi-agent systems are being increasingly deployed in challenging environments for performing complex tasks such as multi-target tracking, search-and-rescue, and intrusion detection. Notwithstanding the computational limitations of…

Optimization and Control · Mathematics 2017-11-30 Amrit Singh Bedi , Paban Sarma , Ketan Rajawat

We propose an extensible deep learning method that uses reinforcement learning to train neural networks for offline ranking in information retrieval (IR). We call our method BanditRank as it treats ranking as a contextual bandit problem. In…

Information Retrieval · Computer Science 2019-10-24 Phanideep Gampa , Sumio Fujita

Recent years have seen increased interest in performance guarantees of gradient descent algorithms for non-convex optimization. A number of works have uncovered that gradient noise plays a critical role in the ability of gradient descent…

Optimization and Control · Mathematics 2019-08-21 Stefan Vlaski , Ali H. Sayed

As application demands for online convex optimization accelerate, the need for designing new methods that simultaneously cover a large class of convex functions and impose the lowest possible regret is highly rising. Known online…

Machine Learning · Computer Science 2019-06-04 Saeed Masoudian , Ali Arabzadeh , Mahdi Jafari Siavoshani , Milad Jalal , Alireza Amouzad

We introduce a novel algorithmic approach to content recommendation based on adaptive clustering of exploration-exploitation ("bandit") strategies. We provide a sharp regret analysis of this algorithm in a standard stochastic noise setting,…

Machine Learning · Computer Science 2014-06-09 Claudio Gentile , Shuai Li , Giovanni Zappella

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

We consider the problem of bandit optimization, inspired by stochastic optimization and online learning problems with bandit feedback. In this problem, the objective is to minimize a global loss function of all the actions, not necessarily…

Machine Learning · Computer Science 2017-09-07 Quentin Berthet , Vianney Perchet

Learning in multi-player games can model a large variety of practical scenarios, where each player seeks to optimize its own local objective function, which at the same time relies on the actions taken by others. Motivated by the frequent…

Optimization and Control · Mathematics 2023-09-08 Yuanhanqing Huang , Jianghai Hu

A major approach to saddle point optimization $\min_x\max_y f(x, y)$ is a gradient based approach as is popularized by generative adversarial networks (GANs). In contrast, we analyze an alternative approach relying only on an oracle that…

Optimization and Control · Mathematics 2021-04-02 Youhei Akimoto

Frequently, when dealing with many machine learning models, optimization problems appear to be challenging due to a limited understanding of the constructions and characterizations of the objective functions in these problems. Therefore,…

Optimization and Control · Mathematics 2024-11-27 A. V. Gasnikov , M. S. Alkousa , A. V. Lobanov , Y. V. Dorn , F. S. Stonyakin , I. A. Kuruzov , S. R. Singh

We provide a new understanding of the stochastic gradient bandit algorithm by showing that it converges to a globally optimal policy almost surely using \emph{any} constant learning rate. This result demonstrates that the stochastic…

Machine Learning · Computer Science 2025-02-12 Jincheng Mei , Bo Dai , Alekh Agarwal , Sharan Vaswani , Anant Raj , Csaba Szepesvari , Dale Schuurmans

In citep{Hazan-2008-extract}, the authors showed that the regret of online linear optimization can be bounded by the total variation of the cost vectors. In this paper, we extend this result to general online convex optimization. We first…

Machine Learning · Computer Science 2012-06-15 Tianbao Yang , Mehrdad Mahdavi , Rong Jin , Shenghuo Zhu

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

First-order methods for minimization and saddle point (min-max) problems are widely used for solving large-scale problems, in particular arising in machine learning. The majority of works obtain favorable complexity guarantees of such…

Robust optimization (RO) has emerged as one of the leading paradigms to efficiently model parameter uncertainty. The recent connections between RO and problems in statistics and machine learning domains demand for solving RO problems in…

Optimization and Control · Mathematics 2017-11-21 Nam Ho-Nguyen , Fatma Kilinc-Karzan

Motivated by applications to online learning in sparse estimation and Bayesian optimization, we consider the problem of online unconstrained nonsubmodular minimization with delayed costs in both full information and bandit feedback…

Machine Learning · Computer Science 2022-06-02 Tianyi Lin , Aldo Pacchiano , Yaodong Yu , Michael I. Jordan