English
Related papers

Related papers: Why Zeroth-Order Adaptation May Forget Less: A Ran…

200 papers

Reinforcement learning often requires extensive training data. Simulation-to-real transfer offers a promising approach to address this challenge in robotics. While differentiable simulators offer improved sample efficiency through exact…

Robotics · Computer Science 2024-12-02 Severin Bochem , Eduardo Gonzalez-Sanchez , Yves Bicker , Gabriele Fadini

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

Recent studies suggest that Reinforcement Fine-Tuning (RFT) is inherently more resilient to catastrophic forgetting than Supervised Fine-Tuning (SFT). However, whether RFT (e.g., GRPO) can effectively overcome forgetting in challenging…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Meng Lou , Hanzhong Guo , Linwei Chen , Yizhou Yu

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

Zeroth-order methods have become important tools for solving problems where we have access only to function evaluations. However, the zeroth-order methods only using gradient approximations are $n$ times slower than classical first-order…

Optimization and Control · Mathematics 2022-02-10 Erik Berglund , Sarit Khirirat , Xiaoyu Wang

Large language models have demonstrated exceptional capabilities across diverse tasks, but their fine-tuning demands significant memory, posing challenges for resource-constrained environments. Zeroth-order (ZO) optimization provides a…

Machine Learning · Computer Science 2025-02-18 Zhen Zhang , Yifan Yang , Kai Zhen , Nathan Susanj , Athanasios Mouchtaris , Siegfried Kunzmann , Zheng Zhang

Zeroth-Order (ZO) optimization is pivotal for scenarios where backpropagation is unavailable, such as memory-constrained on-device learning and black-box optimization. However, existing methods face a stark trade-off: they are either…

Machine Learning · Computer Science 2026-05-29 Chen Liang , Xiatao Sun , Qian Wang , Daniel Rakita

Reinforcement learning (RL) has become a key driver of language model reasoning. Among RL algorithms, Group Relative Policy Optimization (GRPO) is the de facto standard, avoiding the need for a critic by using per-prompt baselines and…

Machine Learning · Computer Science 2026-02-02 Cheng Ge , Caitlyn Heqi Yin , Hao Liang , Jiawei Zhang

Zeroth-order optimization is the process of minimizing an objective $f(x)$, given oracle access to evaluations at adaptively chosen inputs $x$. In this paper, we present two simple yet powerful GradientLess Descent (GLD) algorithms that do…

Machine Learning · Computer Science 2020-05-20 Daniel Golovin , John Karro , Greg Kochanski , Chansoo Lee , Xingyou Song , Qiuyi Zhang

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

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

Catastrophic forgetting remains a central challenge in continual learning (CL) with pre-trained models. While existing approaches typically freeze the backbone and fine-tune a small number of parameters to mitigate forgetting, they still…

Machine Learning · Computer Science 2025-09-03 Jiao Chen , Jiayi He , Fangfang Chen , Zuohong Lv , Jianhua Tang

The zeroth-order optimization has been widely used in machine learning applications. However, the theoretical study of the zeroth-order optimization focus on the algorithms which approximate (first-order) gradients using (zeroth-order)…

Machine Learning · Computer Science 2023-08-02 Haishan Ye

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

We study zeroth-order optimization where solutions must minimize a cost $d(s)$ while maintaining high probability under a complex generative prior $L(s)$ (e.g., a parameterized model). This reduces to sampling from a target distribution…

Machine Learning · Computer Science 2026-05-06 Pranjal Awasthi , Sreenivas Gollapudi , Ravi Kumar , Kamesh Munagala

Fine-tuning language models (LMs) has demonstrated success in a wide array of downstream tasks. However, as LMs are scaled up, the memory requirements for backpropagation become prohibitively high. Zeroth-order (ZO) optimization methods can…

Machine Learning · Computer Science 2024-04-15 Tanmay Gautam , Youngsuk Park , Hao Zhou , Parameswaran Raman , Wooseok Ha

The paper discusses derivative-free optimization (DFO), which involves minimizing a function without access to gradients or directional derivatives, only function evaluations. Classical DFO methods, which mimic gradient-based methods, such…

Optimization and Control · Mathematics 2025-04-17 Bumsu Kim , HanQin Cai , Daniel McKenzie , Wotao Yin

Zeroth-order optimization (ZOO) is an important framework for stochastic optimization when gradients are unavailable or expensive to compute. A potential limitation of existing ZOO methods is the bias inherent in most gradient estimators…

Machine Learning · Computer Science 2025-10-24 Shaocong Ma , Heng Huang

Modern GPUs are equipped with large amounts of high-bandwidth memory, enabling them to support mini-batch sizes of up to tens of thousands of training samples. However, most existing optimizers struggle to perform effectively at such a…

Machine Learning · Computer Science 2026-02-10 Yishun Lu , Wesley Armour

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
‹ Prev 1 3 4 5 6 7 10 Next ›