English
Related papers

Related papers: Prior-Informed Zeroth-Order Optimization with Adap…

200 papers

While backpropagation--reverse-mode automatic differentiation--has been extraordinarily successful in deep learning, it requires two passes (forward and backward) through the neural network and the storage of intermediate activations.…

Machine Learning · Computer Science 2025-11-06 Daniel Wang , Evan Markou , Dylan Campbell

Zeroth-order optimization (ZO) algorithms have been recently used to solve black-box or simulation-based learning and control problems, where the gradient of the objective function cannot be easily computed but can be approximated using the…

Optimization and Control · Mathematics 2021-09-09 Yan Zhang , Yi Zhou , Kaiyi Ji , Michael M. Zavlanos

Given the limitations of backpropagation, perturbation-based gradient computation methods have recently gained focus for learning with only forward passes, also referred to as queries. Conventional forward learning consumes enormous queries…

Machine Learning · Computer Science 2025-03-11 Tao Ren , Zishi Zhang , Jinyang Jiang , Guanghao Li , Zeliang Zhang , Mingqian Feng , Yijie Peng

Bilevel optimization (BLO) is a popular approach with many applications including hyperparameter optimization, neural architecture search, adversarial robustness and model-agnostic meta-learning. However, the approach suffers from time and…

Machine Learning · Computer Science 2021-06-08 Valerii Likhosherstov , Xingyou Song , Krzysztof Choromanski , Jared Davis , Adrian Weller

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

Reinforcement Learning from Human Feedback (RLHF) has emerged as a powerful technique for aligning large language models (LLMs) with human preferences. However, effectively aligning LLMs with diverse human preferences remains a significant…

Computation and Language · Computer Science 2025-07-03 Chengao Li , Hanyu Zhang , Yunkun Xu , Hongyan Xue , Xiang Ao , Qing He

Bilevel optimization problems consist of minimizing a value function whose evaluation depends on the solution of an inner optimization problem. These problems are typically tackled using first-order methods that require computing the…

Optimization and Control · Mathematics 2026-01-30 Marco Rando , Samuel Vaiter

Fine-tuning Large Language Models (LLMs) has become a crucial technique for adapting pre-trained models to downstream tasks. However, the enormous size of LLMs poses significant challenges in terms of computational complexity and resource…

Computation and Language · Computer Science 2024-10-28 Yifei Zhang , Hao Zhu , Aiwei Liu , Han Yu , Piotr Koniusz , Irwin King

We propose an efficient layer-specific optimization (ELO) method designed to enhance continual pretraining (CP) for specific languages in multilingual large language models (MLLMs). This approach addresses the common challenges of high…

Computation and Language · Computer Science 2026-01-21 HanGyeol Yoo , ChangSu Choi , Minjun Kim , Seohyun Song , SeungWoo Song , Inho Won , Jongyoul Park , Cheoneum Park , KyungTae Lim

Federated learning enables collaborative model training across numerous edge devices without requiring participants to share data; however, memory and communication constraints on these edge devices may preclude their participation in…

Machine Learning · Computer Science 2025-09-04 Gwen Legate , Irina Rish , Eugene Belilovsky

There is growing interest in reinforcement learning (RL) methods that leverage the simulator's derivatives to improve learning efficiency. While early gradient-based approaches have demonstrated superior performance compared to…

Robotics · Computer Science 2025-09-05 Joseph Amigo , Rooholla Khorrambakht , Elliot Chane-Sane , Nicolas Mansard , Ludovic Righetti

Finetuning language models (LMs) is crucial for adapting the models to downstream data and tasks. However, full finetuning is usually costly. Existing work, such as parameter-efficient finetuning (PEFT), often focuses on \textit{how to…

Computation and Language · Computer Science 2025-06-03 Jian Gu , Aldeida Aleti , Chunyang Chen , Hongyu Zhang

Recent Large-Language Models (LLMs) pruning methods typically operate at the post-training phase without the expensive weight finetuning, however, their pruning criteria often rely on heuristically hand-crafted metrics, potentially leading…

Machine Learning · Computer Science 2025-07-04 Yuan Gao , Zujing Liu , Weizhong Zhang , Bo Du , Gui-Song Xia

In this paper, we prove new complexity bounds for zeroth-order methods in non-convex optimization with inexact observations of the objective function values. We use the Gaussian smoothing approach of Nesterov and Spokoiny [2015] and extend…

Optimization and Control · Mathematics 2021-01-14 Innokentiy Shibaev , Pavel Dvurechensky , Alexander Gasnikov

This paper considers a consensus optimization problem, where all the nodes in a network, with access to the zeroth-order information of its local objective function only, attempt to cooperatively achieve a common minimizer of the sum of…

Optimization and Control · Mathematics 2024-06-17 Chengan Wang , Zichong Ou , Jie Lu

Recent studies have introduced various approaches for prompt-tuning black-box vision-language models, referred to as black-box prompt-tuning (BBPT). While BBPT has demonstrated considerable potential, it is often found that many existing…

Computer Vision and Pattern Recognition · Computer Science 2025-04-10 Seonghwan Park , Jaehyeon Jeong , Yongjun Kim , Jaeho Lee , Namhoon Lee

This paper investigates how to accelerate the convergence of distributed optimization algorithms on nonconvex problems with zeroth-order information available only. We propose a zeroth-order (ZO) distributed primal-dual stochastic…

Optimization and Control · Mathematics 2021-10-15 Shengjun Zhang , Colleen P. Bailey

Zeroth-order optimization (ZO) typically relies on two-point feedback to estimate the unknown gradient of the objective function. Nevertheless, two-point feedback can not be used for online optimization of time-varying objective functions,…

Machine Learning · Computer Science 2020-12-04 Yan Zhang , Yi Zhou , Kaiyi Ji , Michael M. Zavlanos

Fine-tuned Large Language Models (LLMs) often demonstrate poor calibration, with their confidence scores misaligned with actual performance. While calibration has been extensively studied in models trained from scratch, the impact of LLMs'…

Computation and Language · Computer Science 2025-05-28 Ziming Wang , Zeyu Shi , Haoyi Zhou , Shiqi Gao , Qingyun Sun , Jianxin Li

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
‹ Prev 1 8 9 10 Next ›