English
Related papers

Related papers: Zeroth-Order Optimization Meets Human Feedback: Pr…

200 papers

Zeroth-order (ZO) optimization has emerged as a promising alternative to gradient-based backpropagation methods, particularly for black-box optimization and large language model (LLM) fine-tuning. However, ZO methods often suffer from slow…

Machine Learning · Computer Science 2025-05-26 Sihwan Park , Jihun Yun , SungYub Kim , Souvik Kundu , Eunho Yang

We consider the problem of minimizing a high-dimensional objective function, which may include a regularization term, using (possibly noisy) evaluations of the function. Such optimization is also called derivative-free, zeroth-order, or…

Optimization and Control · Mathematics 2023-03-20 HanQin Cai , Daniel Mckenzie , Wotao Yin , Zhenliang Zhang

This paper deals with the black-box optimization problem. In this setup, we do not have access to the gradient of the objective function, therefore, we need to estimate it somehow. We propose a new type of approximation JAGUAR, that…

Optimization and Control · Mathematics 2024-12-03 Andrey Veprikov , Aleksandr Bogdanov , Vladislav Minashkin , Aleksandr Beznosikov

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

Fine-tuning Large Language Models (LLMs) is essential for adapting pre-trained models to downstream tasks. Yet traditional first-order optimizers such as Stochastic Gradient Descent (SGD) and Adam incur prohibitive memory and computational…

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

We study the problem of zero-order optimization of a strongly convex function. The goal is to find the minimizer of the function by a sequential exploration of its values, under measurement noise. We study the impact of higher order…

Machine Learning · Computer Science 2022-11-28 Arya Akhavan , Massimiliano Pontil , Alexandre B. Tsybakov

Reward inference (learning a reward model from human preferences) is a critical intermediate step in the Reinforcement Learning from Human Feedback (RLHF) pipeline for fine-tuning Large Language Models (LLMs). In practice, RLHF faces…

Machine Learning · Computer Science 2025-03-04 Qining Zhang , Lei Ying

Fine-tuning large language models (LLMs) has achieved remarkable success across various NLP tasks, but the substantial memory overhead during backpropagation remains a critical bottleneck, especially as model scales grow. Zeroth-order (ZO)…

Computation and Language · Computer Science 2026-01-09 Feihu Jin , Shipeng Cen , Ying Tan

Zeroth-order (ZO) optimization is one key technique for machine learning problems where gradient calculation is expensive or impossible. Several variance reduced ZO proximal algorithms have been proposed to speed up ZO optimization for…

Optimization and Control · Mathematics 2024-10-04 Bin Gu , Xiyuan Wei , Hualin Zhang , Yi Chang , Heng Huang

We consider the problem of optimizing a high-dimensional convex function using stochastic zeroth-order queries. Under sparsity assumptions on the gradients or function values, we present two algorithms: a successive component/feature…

Machine Learning · Statistics 2018-02-27 Yining Wang , Simon Du , Sivaraman Balakrishnan , Aarti Singh

Fine-tuning large language models (LLMs) using standard first-order (FO) optimization often drives training toward sharp, poorly generalizing minima. Conversely, zeroth-order (ZO) methods offer stronger exploratory behavior without relying…

Machine Learning · Computer Science 2026-01-12 Feihu Jin , Ying Tan

Zeroth-order optimization is a fundamental research topic that has been a focus of various learning tasks, such as black-box adversarial attacks, bandits, and reinforcement learning. However, in theory, most complexity results assert a…

Optimization and Control · Mathematics 2023-08-03 Pengyun Yue , Long Yang , Cong Fang , Zhouchen Lin

Zeroth-order optimization aims to minimize an objective function using only function evaluations, and is therefore fundamental in black-box optimization, hyperparameter tuning, bandit learning, and adversarial machine learning. While…

Optimization and Control · Mathematics 2026-04-28 Haishan Ye

Interest in stochastic zeroth-order (SZO) methods has recently been revived in black-box optimization scenarios such as adversarial black-box attacks to deep neural networks. SZO methods only require the ability to evaluate the objective…

Machine Learning · Statistics 2020-11-11 Mayumi Ohta , Nathaniel Berger , Artem Sokolov , Stefan Riezler

Large language models (LLMs) have brought about significant transformations in human society. Among the crucial computations in LLMs, the softmax unit holds great importance. Its helps the model generating a probability distribution on…

Machine Learning · Computer Science 2023-07-18 Yichuan Deng , Zhihang Li , Sridhar Mahadevan , Zhao Song

We propose Zeroth-Order Random Matrix Search for Learning from Demonstrations (ZORMS-LfD). ZORMS-LfD enables the costs, constraints, and dynamics of constrained optimal control problems, in both continuous and discrete time, to be learned…

Machine Learning · Computer Science 2025-07-24 Olivia Dry , Timothy L. Molloy , Wanxin Jin , Iman Shames

Zeroth-order optimization (ZO) is widely used for solving black-box optimization and control problems. In particular, single-point ZO (SZO) is well-suited to online or dynamic problem settings due to its requirement of only a single…

Optimization and Control · Mathematics 2026-02-06 Xin Chen , Zhaolin Ren

This paper considers reinforcement learning from human feedback in a federated learning setting with resource-constrained agents, such as edge devices. We propose an efficient federated RLHF algorithm, named Partitioned, Sign-based…

Machine Learning · Computer Science 2026-04-21 Deyi Wang , Qining Zhang , Lei Ying

Distributed optimization is the standard way of speeding up machine learning training, and most of the research in the area focuses on distributed first-order, gradient-based methods. Yet, there are settings where some…

Machine Learning · Computer Science 2025-11-03 Matin Ansaripour , Shayan Talaei , Giorgi Nadiradze , Dan Alistarh