English
Related papers

Related papers: Refining Adaptive Zeroth-Order Optimization at Eas…

200 papers

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

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

In this study, we consider an optimization problem with uncertainty dependent on decision variables, which has recently attracted attention due to its importance in machine learning and pricing applications. In this problem, the gradient of…

Optimization and Control · Mathematics 2024-12-31 Yuya Hikima , Akiko Takeda

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

While fine-tuning large language models (LLMs) for specific tasks often yields impressive results, it comes at the cost of memory inefficiency due to back-propagation in gradient-based training. Memory-efficient Zeroth-order (MeZO)…

Machine Learning · Computer Science 2026-02-17 Yong Liu , Zirui Zhu , Chaoyu Gong , Minhao Cheng , Cho-Jui Hsieh , Yang You

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

Fine-tuning vision language models (VLMs) has achieved remarkable performance across various downstream tasks; yet, it requires access to model gradients through backpropagation (BP), making them unsuitable for memory-constrained,…

Machine Learning · Computer Science 2025-10-27 Yifan Yang , Zhen Zhang , Rupak Vignesh Swaminathan , Jing Liu , Nathan Susanj , Zheng Zhang

Training deep neural networks is challenging. To accelerate training and enhance performance, we propose PadamP, a novel optimization algorithm. PadamP is derived by applying the adaptive estimation of the p-th power of the second-order…

Optimization and Control · Mathematics 2025-03-14 Yongqi Li , Xiaowei Zhang

Non-analytical objectives and constraints often arise in control systems, particularly in problems with complex dynamics, which are challenging yet lack efficient solution methods. In this work, we consider general constrained optimization…

Optimization and Control · Mathematics 2025-07-16 Yuke Zhou , Ruiyang Jin , Siyang Gao , Jianxiao Wang , Jie Song

In the learning to learn (L2L) framework, we cast the design of optimization algorithms as a machine learning problem and use deep neural networks to learn the update rules. In this paper, we extend the L2L framework to zeroth-order (ZO)…

Machine Learning · Computer Science 2020-02-10 Yangjun Ruan , Yuanhao Xiong , Sashank Reddi , Sanjiv Kumar , Cho-Jui Hsieh

We introduce LOREN, a curvature-aware zeroth-order (ZO) optimization method for fine-tuning large language models (LLMs). Existing ZO methods, which estimate gradients via finite differences using random perturbations, often suffer from…

Machine Learning · Computer Science 2025-11-12 Hyunseok Seung , Jaewoo Lee , Hyunsuk Ko

Zeroth-order (ZO, also known as derivative-free) methods, which estimate the gradient only by two function evaluations, have attracted much attention recently because of its broad applications in machine learning community. The two function…

Machine Learning · Computer Science 2021-04-12 Zhou Zhai , Bin Gu , Heng Huang

In many real-world problems, first-order (FO) derivative evaluations are too expensive or even inaccessible. For solving these problems, zeroth-order (ZO) methods that only need function evaluations are often more efficient than FO methods…

Optimization and Control · Mathematics 2021-12-22 Zichong Li , Pin-Yu Chen , Sijia Liu , Songtao Lu , Yangyang Xu

Test-Time Adaptation (TTA) is essential for enabling deep learning models to handle real-world data distribution shifts. However, current approaches face significant limitations: backpropagation-based methods are not suitable for low-end…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Xingyu Wang , Tao Wang

Fine-tuning large language models (LLMs) with classic first-order optimizers entails prohibitive GPU memory due to the backpropagation process. Recent works have turned to zeroth-order optimizers for fine-tuning, which save substantial…

Machine Learning · Computer Science 2025-02-19 Yanjun Zhao , Sizhe Dang , Haishan Ye , Guang Dai , Yi Qian , Ivor W. Tsang

Federated optimization, an emerging paradigm which finds wide real-world applications such as federated learning, enables multiple clients (e.g., edge devices) to collaboratively optimize a global function. The clients do not share their…

Machine Learning · Computer Science 2023-08-09 Yao Shu , Xiaoqiang Lin , Zhongxiang Dai , Bryan Kian Hsiang Low

Zero-order (ZO) optimization is a powerful tool for dealing with realistic constraints. On the other hand, the gradient-tracking (GT) technique proved to be an efficient method for distributed optimization aiming to achieve consensus.…

Machine Learning · Computer Science 2024-10-10 Elissa Mhanna , Mohamad Assaad

This work considers stochastic optimization problems in which the objective function values can only be computed by a blackbox corrupted by some random noise following an unknown distribution. The proposed method is based on sequential…

Optimization and Control · Mathematics 2023-08-15 Charles Audet , Jean Bigeon , Romain Couderc , Michael Kokkolaras

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…

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
‹ Prev 1 3 4 5 6 7 10 Next ›