English
Related papers

Related papers: ZORMS-LfD: Learning from Demonstrations with Zerot…

200 papers

This paper introduces a class of model-free feedback methods for solving generic constrained optimization problems where the specific mathematical forms of the objective and constraint functions are not available. The proposed methods,…

Optimization and Control · Mathematics 2025-02-13 Xin Chen , Jorge I. Poveda , Na Li

Safe derivative-free optimization under unknown constraints is a fundamental challenge in modern learning and control. Existing zeroth-order (ZO) methods typically still assume access to a first-order oracle of the constraint functions or…

Optimization and Control · Mathematics 2026-01-29 Runyu Zhang , Gioele Zardini , Asuman Ozdaglar , Jeff Shamma , Na Li

Fine-tuning large pretrained language models (LLMs) is a cornerstone of modern NLP, yet its growing memory demands (driven by backpropagation and large optimizer States) limit deployment in resource-constrained settings. Zero-order (ZO)…

Machine Learning · Computer Science 2026-02-17 Valery Parfenov , Grigoriy Evseev , Andrey Veprikov , Nikolay Bushkov , Stanislav Moiseev , Aleksandr Beznosikov

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

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 optimizers have recently emerged as a practical approach for fine-tuning large language models (LLMs), significantly reducing GPU memory consumption compared to traditional first-order methods. Yet, existing zeroth-order…

Machine Learning · Computer Science 2025-10-02 Kairun Zhang , Haoyu Li , Yanjun Zhao , Yifan Sun , Huan Zhang

Learning from Demonstration (LfD) seeks to democratize robotics by enabling non-roboticist end-users to teach robots to perform novel tasks by providing demonstrations. However, as demonstrators are typically non-experts, modern LfD…

Robotics · Computer Science 2021-10-12 Letian Chen , Rohan Paleja , Matthew Gombolay

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

Learning from Demonstration (LfD) is a popular approach that allows humans to teach robots new skills by showing the correct way(s) of performing the desired skill. Human-provided demonstrations, however, are not always optimal and the…

Robotics · Computer Science 2024-07-01 Brendan Hertel , S. Reza Ahmadzadeh

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

In the evolving landscape of natural language processing (NLP), fine-tuning pre-trained Large Language Models (LLMs) with first-order (FO) optimizers like SGD and Adam has become standard. Yet, as LLMs grow {in size}, the substantial memory…

Zeroth-order (a.k.a, derivative-free) methods are a class of effective optimization methods for solving complex machine learning problems, where gradients of the objective functions are not available or computationally prohibitive.…

Optimization and Control · Mathematics 2023-12-12 Feihu Huang , Shangqian Gao , Jian Pei , Heng Huang

Classical optimization theory establishes that zeroth-order (ZO) algorithms suffer from a dimension-dependent slowdown, with convergence rates typically scaling with the model dimension compared to first-order methods. However, in contrast…

Machine Learning · Computer Science 2026-05-06 Zhe Li , Bicheng Ying , Zidong Liu , Haibo Yang

We provide the first generalization error analysis for black-box learning through derivative-free optimization. Under the assumption of a Lipschitz and smooth unknown loss, we consider the Zeroth-order Stochastic Search (ZoSS) algorithm,…

Machine Learning · Computer Science 2023-02-13 Konstantinos E. Nikolakakis , Farzin Haddadpour , Dionysios S. Kalogerias , Amin Karbasi

Zeroth-order optimization (ZO) has been a powerful framework for solving black-box problems, which estimates gradients using zeroth-order data to update variables iteratively. The practical applicability of ZO critically depends on the…

Optimization and Control · Mathematics 2026-03-03 Ruiyang Jin , Yuke Zhou , Yujie Tang , Jie Song , Siyang Gao

Derivative-free optimization has become an important technique used in machine learning for optimizing black-box models. To conduct updates without explicitly computing gradient, most current approaches iteratively sample a random search…

Machine Learning · Statistics 2018-08-03 Liu Liu , Minhao Cheng , Cho-Jui Hsieh , Dacheng Tao

Prompt learning has become a key method for adapting large language models to specific tasks with limited data. However, traditional gradient-based optimization methods for tuning prompts are computationally intensive, posing challenges for…

Statistics Theory · Mathematics 2025-12-30 Yao Fu , Yihang Jin , Chunxia Zhang , Junmin Liu , Guang Dai , Haishan Ye

Despite the numerous breakthroughs achieved with Reinforcement Learning (RL), solving environments with sparse rewards remains a challenging task that requires sophisticated exploration. Learning from Demonstrations (LfD) remedies this…

Machine Learning · Computer Science 2022-03-22 Georgiy Pshikhachev , Dmitry Ivanov , Vladimir Egorov , Aleksei Shpilman

Zeroth-order (ZO) optimization provides a gradient-free alternative to first-order (FO) methods by estimating gradients via finite differences of function evaluations, and has recently emerged as a memory-efficient paradigm for fine-tuning…

Machine Learning · Computer Science 2026-02-24 Yicheng Lang , Changsheng Wang , Yihua Zhang , Mingyi Hong , Zheng Zhang , Wotao Yin , Sijia Liu

In this study, we delve into an emerging optimization challenge involving a black-box objective function that can only be gauged via a ranking oracle-a situation frequently encountered in real-world scenarios, especially when the function…

Machine Learning · Computer Science 2024-04-16 Zhiwei Tang , Dmitry Rybin , Tsung-Hui Chang
‹ Prev 1 2 3 10 Next ›