Zeroth-Order Optimization

Follow this topic Ask about this topic

Zeroth-order optimization studies how to improve an objective using only its evaluations, making it useful when gradients are unavailable, expensive, or incompatible with black-box systems. Common approaches estimate directions with finite differences or random perturbations, then reduce cost and noise through variance reduction, adaptive sampling, low-dimensional subspaces, or structured updates. The methods are used in settings such as language-model fine-tuning, robotics, test-time adaptation, and optimization under privacy or communication limits, alongside theoretical work on convergence and query complexity. A central tension is that avoiding backpropagation can save memory and enable broader access, but noisy estimates and many required evaluations can make optimization slower or less reliable than first-order methods.

Latest papers

86 papers15 papers in the last four weeks, up 200% on the four weeks before. 0.1% of all new papers.

Efficient Federated RLHF via Zeroth-Order Policy Optimization
Apr 20, 2026Deyi Wang, Qining Zhang, Lei YingFederated RL Communication-Efficient Distributed Training
University of Michigan, Ann Arbor
Zeroth-Order Optimization at the Edge of Stability
Apr 16, 2026Minhak Song, Liang Zhang, Bingcong Li +3Edge of Stability Zeroth-Order Optimization
KAIST · KRAFTON · ETH Zurich +2
Evolution of Optimization Methods: Algorithms, Scenarios, and Evaluations
Apr 14, 2026Tong Zhang, Jiangning Zhang, Zhucun Xue +9Deep Learning Optimization Adaptive Gradient Methods
Zhejiang University, APRIL Lab · Fudan University · Shanghai Jiaotong University +1
Optimizing Service Operations via LLM-Powered Multi-Agent Simulation
Apr 6, 2026Yanyuan Wang, Xiaowei ZhangStochastic Optimization Decision-Making under Uncertainty
Department of Industrial Engineering and Decision Analytics, The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong SAR
One-Shot Localisation of the Global Minimum of a Noisy One-Dimensional Function: An Iterative Neural Minimizer Compared with Set Transformers and Classical Estimators
Apr 4, 2026Qusay Muzaffar, David Levin, Michael WermanBlack-Box Optimization Zeroth-Order Optimization
Department of Computer Science, The Hebrew University of Jerusalem, Israel · Department of Applied Mathematics, Tel Aviv University, Israel
Finite-time analysis of Multi-timescale Stochastic Optimization Algorithms
Mar 31, 2026Kaustubh Kartikey, Shalabh BhatnagarStochastic Optimization Stochastic Optimization Convergence
Stochastic Dimension Zeroth-Order Estimator: Stable and Memory-Efficient Training of PINNs
Mar 25, 2026Zhangyong Liang, Huanhuan GaoZeroth-Order Optimization Neural Network Optimization
National Center for Applied Mathematics, Tianjin University, Tianjin 300072, China. · School of Mechanical and Aerospace Engineering, Jilin University, Changchun 130025, China
CurvZO: Adaptive Curvature-Guided Sparse Zeroth-Order Optimization for Efficient LLM Fine-Tuning
Mar 23, 2026Shuo Wang, Ziyu Chen, Ming TangZeroth-Order Optimization Memory-Efficient Fine-Tuning
Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China. · Department of Mathematics, Southern University of Science and Technology, Shenzhen, China.
Model Evolution Under Zeroth-Order Optimization: A Neural Tangent Kernel Perspective
Mar 22, 2026Chen Zhang, Yuxin Cheng, Chenchen Ding +5Zeroth-Order Optimization Neural Network Training Dynamics
The University of Hong Kong · The Hong Kong University of Science and Technology
HO-SFL: Hybrid-Order Split Federated Learning with Backprop-Free Clients and Dimension-Free Aggregation
Mar 16, 2026Qiyuan Chen, Xian Wu, Yi Wang +1Communication-Efficient Distributed Training Zeroth-Order Optimization
Department of Electrical and Computer Engineering, The University of Hong Kong, Hong Kong SAR, China.
ZOTTA: Test-Time Adaptation with Gradient-Free Zeroth-Order Optimization
Mar 15, 2026Ronghao Zhang, Shuaicheng Niu, Qi Deng +3Test-Time Adaptation Zeroth-Order Optimization
South China University of Technology, Guangzhou, 510000, China. · Nanyang Technological University, 639798, Singapore. · Xi’an Jiaotong University, Xi’an, 710049, China. +1
ZO-SAM: Zero-Order Sharpness-Aware Minimization for Efficient Sparse Training
Mar 13, 2026Jie Ji, Gen Li, Kaiyuan Deng +2Sharpness-Aware Minimization Sparse Neural Networks
Clemson University · University of Arizona
FOZO: Forward-Only Zeroth-Order Prompt Optimization for Test-Time Adaptation
Mar 5, 2026Xingyu Wang, Tao WangTest-Time Adaptation Continual Test-Time Adaptation
College of Computer Science, Sichuan University
Zeroth-Order Stackelberg Control in Combinatorial Congestion Games
Feb 26, 2026Saeed Masiha, Sepehr Elahi, Negar Kiyavash +1Frank-Wolfe Algorithms Stackelberg Games
EPFL School of Management of Technology · EPFL Department of Computer and Communications Sciences
AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization
Feb 23, 2026Mert Cemri, Shubham Agrawal, Akshat Gupta +9Large Language Model-Guided Optimization LLMs for Evolutionary Optimization
University of California, Berkeley · Bespoke Labs
Generalized Random Direction Newton Algorithms for Stochastic Optimization
Feb 23, 2026Soumen Pachal, Prashanth L. A., Shalabh Bhatnagar +1Stochastic Optimization Stochastic Optimization Convergence
Indian Institute of Technology Madras · Indian Institute of Science, Bangalore · TCS Research, Chennai, India
SeedFlood: A Step Toward Scalable Decentralized Fine-Tuning of LLMs
Feb 20, 2026Jihun Kim, Dongyeop Lee, Namhoon LeeCommunication-Efficient Distributed Training Zeroth-Order Optimization
POSTECH, pohang, Republic of Korea.
Powering Up Zeroth-Order Training via Subspace Gradient Orthogonalization
Feb 19, 2026Yicheng Lang, Changsheng Wang, Yihua Zhang +4Zeroth-Order Optimization Memory-Efficient Fine-Tuning
Michigan State University · University of Minnesota · University of California, Santa Barbara +2
Solving the Offline and Online Min-Max Problem of Non-smooth Submodular-Concave Functions: A Zeroth-Order Approach
Jan 29, 2026Amir Ali Farzin, Yuen-Man Pun, Philipp Braun +2Min-Max Optimization Submodular Optimization
School of Engineering, Australian National University, Canberra, Australia · Department of Mechanical Engineering, University of Texas at Dallas, Richardson, Texas, USA · Department of Electrical and Electronic Engineering, The University of Melbourne, Parkville, Australia
Power Homotopy for Zeroth-Order Non-Convex Optimizations
Nov 17, 2025Chen XuZeroth-Order Optimization Nonconvex Optimization
Department of Engineering, Shenzhen MSU-BIT University, China.
An Introduction to Zero-Order Optimization Techniques for Robotics
Jun 27, 2025Armand Jordana, Jianghan Zhang, Joseph Amigo +1Zeroth-Order Optimization Robotic Optimization
Machines in Motion Laboratory, New York University, USA
Minimisation of Quasar-Convex Functions Using Random Zeroth-Order Oracles
May 4, 2025Amir Ali Farzin, Yuen-Man Pun, Philipp Braun +1Zeroth-Order Optimization Constrained Optimization
School of Engineering Australian National University · Department of Electrical and Electronic Engineering University of Melbourne · Department of Electrical and Electronic Engineering22 University of Melbourne
Mirror Descent Linearized Augmented Lagrangian Methods for Nonconvex Constrained Stochastic Zeroth-Order Optimization
Apr 13, 2025Qiankun Shi, Han Yuan, Xiao Wang +1Zeroth-Order Optimization Augmented Lagrangian Method
Sun Yat-sen University, Guangzhou, 510006, China · Pengcheng Laboratory, Shenzhen, 518066, China · Sun Yat-sen University, Guangzhou, 518066, China +1
Sample-Efficient Optimization over Generative Priors via Coarse Learnability
Mar 10, 2025Pranjal Awasthi, Sreenivas Gollapudi, Ravi Kumar +1Zeroth-Order Optimization
Google Research, Mountain View, USA · Department of Computer Science, Duke University, Durham, USA
Risk-averse learning with delayed feedback
Sep 25, 2024Siyi Wang, Zifan Wang, Karl Henrik Johansson +1Dynamic Regret Minimization Zeroth-Order Optimization
Division of Decision and Control Systems, School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, 10044 Stockholm, Sweden · Chair of Information-oriented Control (ITR), Technical University of Munich, Germany
Gradient Testing and Estimation by Comparisons
May 19, 2024Xiwen Tao, Chenyi Zhang, Helin Wang +2Black-Box Optimization Zeroth-Order Optimization
School of Electronics Engineering and Computer Science, Peking University · Computer Science Department, Stanford University · Center on Frontiers of Computing Studies, Peking University +1

Apr 20, 2026J/K move · Enter open · S save

Efficient Federated RLHF via Zeroth-Order Policy Optimization

Deyi Wang, Qining Zhang, Lei Ying

University of Michigan, Ann Arbor

Federated RL Communication-Efficient Distributed Training Zeroth-Order Optimization Policy Learning RL from Human Feedback

Open paper AskPDF arXiv

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 Stochastic Zeroth-order Policy Optimization (Par-S

^2

ZPO). The algorithm is built on zeroth-order optimization with binary perturbation, resulting in low communication, computation, and memory complexity by design. Our theoretical analysis establishes an upper bound on the convergence rate of Par-S

^2

ZPO, revealing that it is as efficient as its centralized counterpart in terms of sample complexity but converges faster in terms of policy update iterations. Our experimental results show that it outperforms a FedAvg-based RLHF on four MuJoCo RL tasks.