English
Related papers

Related papers: Zeroth Order Non-convex optimization with Dueling-…

200 papers

We consider function optimization as a sequential decision making problem under budget constraint. This constraint limits the number of objective function evaluations allowed during the optimization. We consider an algorithm inspired by a…

Machine Learning · Computer Science 2026-05-06 Philippe Preux , Rémi Munos , Michal Valko

Collecting human preference feedback is often expensive, leading recent works to develop principled algorithms to select them more efficiently. However, these works assume that the underlying reward function is linear, an assumption that…

Machine Learning · Computer Science 2025-07-18 Arun Verma , Xiaoqiang Lin , Zhongxiang Dai , Daniela Rus , Bryan Kian Hsiang Low

Distributed multi-agent optimization finds many applications in distributed learning, control, estimation, etc. Most existing algorithms assume knowledge of first-order information of the objective and have been analyzed for convex…

Optimization and Control · Mathematics 2020-06-17 Yujie Tang , Junshan Zhang , Na Li

Bayesian optimisation requires fitting a Gaussian process model, which in turn requires specifying prior on the unknown black-box function -- most of the theoretical literature assumes this prior is known. However, it is common to have more…

Machine Learning · Computer Science 2025-02-25 Juliusz Ziomek , Masaki Adachi , Michael A. Osborne

New ranking algorithms are continually being developed and refined, necessitating the development of efficient methods for evaluating these rankers. Online ranker evaluation focuses on the challenge of efficiently determining, from implicit…

Information Retrieval · Computer Science 2016-08-23 Brian Brost , Yevgeny Seldin , Ingemar J. Cox , Christina Lioma

We propose a novel zeroth-order optimization algorithm based on an efficient sampling strategy. Under mild global regularity conditions on the objective function, we establish non-asymptotic convergence rates for the proposed method.…

Optimization and Control · Mathematics 2025-09-24 Xicheng Zhang

Bandit based methods for tree search have recently gained popularity when applied to huge trees, e.g. in the game of go (Gelly et al., 2006). The UCT algorithm (Kocsis and Szepesvari, 2006), a tree search method based on Upper Confidence…

Machine Learning · Computer Science 2016-08-14 Pierre-Arnaud Coquelin , Rémi Munos

This paper considers the problem of distributed bandit online convex optimization with time-varying coupled inequality constraints. This problem can be defined as a repeated game between a group of learners and an adversary. The learners…

Optimization and Control · Mathematics 2019-12-10 Xinlei Yi , Xiuxian Li , Tao Yang , Lihua Xie , Karl H. Johansson , Tianyou Chai

We consider the problem of online convex optimization against an arbitrary adversary with bandit feedback, known as bandit convex optimization. We give the first $\tilde{O}(\sqrt{T})$-regret algorithm for this setting based on a novel…

Machine Learning · Computer Science 2016-03-16 Elad Hazan , Yuanzhi Li

I present the first algorithm for stochastic finite-armed bandits that simultaneously enjoys order-optimal problem-dependent regret and worst-case regret. Besides the theoretical results, the new algorithm is simple, efficient and…

Machine Learning · Computer Science 2016-02-25 Tor Lattimore

Zeroth-order methods are extensively used in machine learning applications where gradients are infeasible or expensive to compute, such as black-box attacks, reinforcement learning, and language model fine-tuning. Existing optimization…

Machine Learning · Computer Science 2025-11-12 Liang Zhang , Bingcong Li , Kiran Koshy Thekumparampil , Sewoong Oh , Michael Muehlebach , Niao He

We propose and analyze a randomized zeroth-order approach based on approximating the exact gradient byfinite differences computed in a set of orthogonal random directions that changes with each iteration. A number ofpreviously proposed…

Optimization and Control · Mathematics 2021-11-16 David Kozak , Cesare Molinari , Lorenzo Rosasco , Luis Tenorio , Silvia Villa

Differentially private zeroth-order optimization methods have recently gained popularity in private fine tuning of machine learning models due to their reduced memory requirements. Current approaches for privatizing zeroth-order methods…

Optimization and Control · Mathematics 2025-07-10 Devansh Gupta , Meisam Razaviyayn , Vatsal Sharan

In order to improve the performance of Bayesian optimisation, we develop a modified Gaussian process upper confidence bound (GP-UCB) acquisition function. This is done by sampling the exploration-exploitation trade-off parameter from a…

Machine Learning · Computer Science 2020-06-09 Julian Berk , Sunil Gupta , Santu Rana , Svetha Venkatesh

In this paper, we present a new algorithm for generic combinatorial optimization, which we term quantum dueling. Traditionally, potential solutions to the given optimization problems were encoded in a ``register'' of qubits. Various…

Quantum Physics · Physics 2024-01-03 Letian Tang , Haorui Wang , Zhengyang Li , Haozhan Tang , Chi Zhang , Shujin Li

We study online learning in constrained Markov decision processes (CMDPs) in which rewards and constraints may be either stochastic or adversarial. In such settings, Stradi et al.(2024) proposed the first best-of-both-worlds algorithm able…

Machine Learning · Computer Science 2025-02-10 Francesco Emanuele Stradi , Anna Lunghi , Matteo Castiglioni , Alberto Marchesi , Nicola Gatti

One approach for reducing run time and improving efficiency of machine learning is to reduce the convergence rate of the optimization algorithm used. Shuffling is an algorithm technique that is widely used in machine learning, but it only…

Machine Learning · Computer Science 2023-06-29 Yuetong Xu , Baharan Mirzasoleiman

Consensus-based optimization (CBO) has established itself as an efficient gradient-free optimization scheme, with attractive mathematical properties, such as mean-field convergence results for non-convex loss functions. In this work, we…

Optimization and Control · Mathematics 2025-07-01 Tim Roith , Leon Bungert , Philipp Wacker

Zeroth-order (ZO) optimization is widely used to handle challenging tasks, such as query-based black-box adversarial attacks and reinforcement learning. Various attempts have been made to integrate prior information into the gradient…

Machine Learning · Statistics 2021-11-09 Shuyu Cheng , Guoqiang Wu , Jun Zhu

We propose a zero-order optimization method for sequential min-max problems based on two populations of interacting particles. The systems are coupled so that one population aims to solve the inner maximization problem, while the other aims…

Optimization and Control · Mathematics 2024-07-25 Giacomo Borghi , Hui Huang , Jinniao Qiu