English
Related papers

Related papers: A New One-Point Residual-Feedback Oracle For Black…

200 papers

We consider the zeroth-order optimization problem in the huge-scale setting, where the dimension of the problem is so large that performing even basic vector operations on the decision variables is infeasible. In this paper, we propose a…

Optimization and Control · Mathematics 2021-08-17 HanQin Cai , Yuchen Lou , Daniel McKenzie , Wotao Yin

In this paper, we study the problem of constrained robust (min-max) optimization ina black-box setting, where the desired optimizer cannot access the gradients of the objective function but may query its values. We present a principled…

Machine Learning · Computer Science 2020-06-18 Sijia Liu , Songtao Lu , Xiangyi Chen , Yao Feng , Kaidi Xu , Abdullah Al-Dujaili , Minyi Hong , Una-May O'Reilly

We address black-box convex optimization problems, where the objective and constraint functions are not explicitly known but can be sampled within the feasible set. The challenge is thus to generate a sequence of feasible points converging…

Optimization and Control · Mathematics 2022-11-08 Baiwei Guo , Yuning Jiang , Maryam Kamgarpour , Giancarlo Ferrari-Trecate

Large language models (LLMs) have demonstrated impressive capabilities across numerous NLP tasks. Nevertheless, conventional first-order fine-tuning techniques impose heavy memory demands, creating practical obstacles to real-world…

Machine Learning · Computer Science 2025-05-27 Zhendong Mi , Qitao Tan , Xiaodong Yu , Zining Zhu , Geng Yuan , Shaoyi Huang

Bayesian optimization and Lipschitz optimization have developed alternative techniques for optimizing black-box functions. They each exploit a different form of prior about the function. In this work, we explore strategies to combine these…

Machine Learning · Computer Science 2020-07-29 Mohamed Osama Ahmed , Sharan Vaswani , Mark Schmidt

Current state-of-the-art multi-objective optimization solvers, by computing gradients of all $m$ objective functions per iteration, produce after $k$ iterations a measure of proximity to critical conditions that is upper-bounded by…

Optimization and Control · Mathematics 2021-05-26 I. F. D. Oliveira , R. H. C. Takahashi

We study a class of zeroth-order distributed optimization problems, where each agent can control a partial vector and observe a local cost that depends on the joint vector of all agents, and the agents can communicate with each other with…

Optimization and Control · Mathematics 2024-01-09 Xinran Zheng , Tara Javidi , Behrouz Touri

We study mathematical programs with equilibrium constraints, in which a leader knows their own cost function, but lacks a model of the followers' response. Instead, the leader can only query this response at specific points. While this…

Optimization and Control · Mathematics 2026-05-19 Miriam Fischer , Dario Paccagnan

Fine-tuning large language models (LLMs) using zeroth-order optimization (ZO) offers a memory-efficient alternative to gradient-based methods but suffers from slower convergence and unstable optimization due to noisy gradient estimates.…

Machine Learning · Computer Science 2025-06-24 Jikai Long , Zijian Hu , Xiaodong Yu , Jianwen Xie , Zhaozhuo Xu

Continual learning requires new-task adaptation without damaging previously acquired capabilities. Recent forward-pass and zeroth-order (ZO) results show that low-query adaptation may retain better than first-order (FO) descent, but the…

Machine Learning · Computer Science 2026-05-12 Yao Shu , Jian Mu , Zhongxiang Dai

Bayesian optimization (BO) is a widely-used sequential method for zeroth-order optimization of complex and expensive-to-compute black-box functions. The existing BO methods assume that the function evaluation (feedback) is available to the…

Machine Learning · Computer Science 2022-06-22 Arun Verma , Zhongxiang Dai , Bryan Kian Hsiang Low

We propose a new framework for analyzing zeroth-order optimization (ZOO) from the perspective of \emph{oblivious randomized sketching}.In this framework, commonly used gradient estimators in ZOO-such as finite difference (FD) and random…

Optimization and Control · Mathematics 2025-10-14 Haishan Ye , Xiangyu Chang , Xi Chen

Fine-tuning Large Language Models (LLMs) has proven effective for a variety of downstream tasks. However, as LLMs grow in size, the memory demands for backpropagation become increasingly prohibitive. Zeroth-order (ZO) optimization methods…

Machine Learning · Computer Science 2025-07-25 Ziming Yu , Pan Zhou , Sike Wang , Jia Li , Mi Tian , Hua Huang

Recently introduced distributed zeroth-order optimization (ZOO) algorithms have shown their utility in distributed reinforcement learning (RL). Unfortunately, in the gradient estimation process, almost all of them require random samples…

Systems and Control · Electrical Eng. & Systems 2024-05-06 Gangshan Jing , He Bai , Jemin George , Aranya Chakrabortty , Piyush K. Sharma

The increasing computational and memory demands in deep learning present significant challenges, especially in resource-constrained environments. We introduce a zero-order quantized optimization (ZOQO) method designed for training models…

Machine Learning · Computer Science 2025-01-14 Noga Bar , Raja Giryes

The dual challenges of prohibitive communication overhead and the impracticality of gradient computation due to data privacy or black-box constraints in distributed systems motivate this work on communication-constrained gradient-free…

Optimization and Control · Mathematics 2025-09-19 Youqing Hua , Shuai Liu , Yiguang Hong , Wei Ren

The adaptive momentum method (AdaMM), which uses past gradients to update descent directions and learning rates simultaneously, has become one of the most popular first-order optimization methods for solving machine learning problems.…

Machine Learning · Computer Science 2019-10-17 Xiangyi Chen , Sijia Liu , Kaidi Xu , Xingguo Li , Xue Lin , Mingyi Hong , David Cox

Zeroth-order (ZO) optimization has become a popular technique for solving machine learning (ML) problems when first-order (FO) information is difficult or impossible to obtain. However, the scalability of ZO optimization remains an open…

We consider online convex optimization with a zero-order oracle feedback. In particular, the decision maker does not know the explicit representation of the time-varying cost functions, or their gradients. At each time step, she observes…

Optimization and Control · Mathematics 2020-05-05 Tatiana Tatarenko , Maryam Kamgarpour

We propose a first order algorithm, a modified version of FISTA, to solve an optimization problem with an objective function that is a sum of a possibly nonconvex function, with Lipschitz continuous gradient, and a convex function which can…

Optimization and Control · Mathematics 2025-08-20 Chee-Khian Sim