Derivative-Free Optimization

Ask about this topic

Overview

Derivative-free optimization studies how to improve an objective when gradients are unavailable, unreliable, or too costly, as in simulations, robotics, and models that cannot be differentiated. Common approaches include evolutionary strategies such as CMA-ES, population and pattern search, zeroth-order updates from finite differences or random probes, and surrogate or generative methods that guide candidate selection. These methods are tested on constrained and multimodal benchmarks, neural-network adaptation, trajectory planning, and physical robot tasks. A central tension is that they can handle black-box and non-smooth settings, but evaluation costs and poor scaling with dimension can make them slower than gradient-based methods when accurate gradients are available.

Latest papers

CardsList

22 papers3 papers in the last four weeks, down 40% on the four weeks before. 0.0% of all new papers.

  1. NextEval: An Agent-Based Solver and Benchmark for Derivative-Free Optimization

    Oct 27, 2026Shuo Chen, Li Cui, Cunxin Huang +4Derivative-Free OptimizationLarge Language Model-Guided Optimization

    Independent Researcher · Beijing Normal University · The Hong Kong Polytechnic University +3

  2. Temporal-Difference Calibration of Black-Box Simulators

    Oct 26, 2026Min Zeng, Xin Wen, Xi Chen +2Model CalibrationTemporal-Difference Learning

    College of Computing, City University of Hong Kong · Stern School of Business, New York University · Daniels School of Business, Purdue University +1

  3. Gradient-Free Sampling from Generative Models via Stochastic Bounded Extremum Seeking

    Oct 3, 2026Alexander ScheinkerDiffusion SamplingMarkov Chain Monte Carlo

    Instrumentation and Controls Group Los Alamos National Laboratory Los Alamos, NM 87544, USA

  4. Learn Feasibility Once, Optimize All Objectives: Derivative-Free Diffusion Models for Chance-Constrained Programming

    Oct 2, 2026Ziwen Liu, Yan Liu, Congying Han +3Chance-Constrained OptimizationDiffusion Models

    School of Mathematical Sciences, Beijing University of Posts and Telecommunications · School of Statistics and Data Science, Nankai University · School of Mathematical Sciences, University of the Chinese Academy of Sciences +1

  5. Code to Control: Synthesizing Parameterized Reactive Controllers

    Sep 30, 2026Zergham Ahmed, Joshua B. Tenenbaum, Chris Bates +1RL ControlLanguage Model-Based Control

    Harvard University · Massachusetts Institute of Technology · Florida Institute for Human and Machine Cognition

  6. SPADE-DFL: Communication-Efficient Decentralized Federated Learning via Derivative-Free Linearized ADMM

    Sep 24, 2026Mengli Wei, Mengkai Zhu, Jiawen Chen +2Communication-Efficient Distributed TrainingBlack-Box Optimization

    School of Mathematics, Southeast University, Nanjing 210096, China

  7. Optimize, Learn, Refine: Whole-Body Grasping and Pick-and-Throw with a Spiral Soft Robot

    Sep 22, 2026Marwah Basuhai, Tingcong Liu, Ibrahim Alsarraj +2Robotic GraspingWhole-Body Robotic Manipulation

  8. Derivative-Free Structured Updates for Muon

    Sep 15, 2026Pengcheng XieBlack-Box OptimizationZeroth-Order Optimization

    Lawrence Berkeley National Laboratory & University of California Berkeley, CA 94720, USA

  9. Trajectory Bundle Method in SE(3) for Black-Box Fixed-Wing Aircraft Trajectory Optimization

    Sep 10, 2026Matthew D. Osburn, Cameron K. Peterson, John L. SalmonTrajectory OptimizationTrajectory Generation

    Department of Electrical and Computer Engineering, Brigham Young University, Provo, UT 84602, USA · Department of Mechanical Engineering, Brigham Young University, Provo, UT 84602, USA

  10. Adaptively Incorporating Directional Hints into Zeroth-Order Optimization

    Sep 8, 2026Alexander Ryabchenko, Jian Qian, Wenlong MouZeroth-Order OptimizationNonconvex Optimization

    University of Toronto and Vector Institute · University of Hong Kong

  11. Why and When Neural Networks Improve Local Approximation in Optimization

    Aug 25, 2026Chengkuo Bian, Pengcheng XieSurrogate-Assisted OptimizationNeural Surrogate Modeling

    University of California, Berkeley, CA 94720, USA. · Applied Mathematics and Computational Research Division, Lawrence Berkeley National Laboratory, University of California, 1 Cyclotron Road, Berkeley, CA 94720, USA.

  12. Generative Refinement for Low-Budget Black-Box Optimization

    Jul 1, 2026Edouard R. Dufour, Oliver Heinimann, Pascal FuaBlack-Box OptimizationDerivative-Free Optimization

    CVLab EPFL Lausanne, CH

  13. \chisao{}: A GPU-Native Parallel Optimizer for Multimodal Black-Box Functions via Convergence-Anticonvergence Oscillation

    Jun 24, 2026Ira WolfsonGPU AccelerationBlack-Box Optimization

    Department of Electronics and Electrical Engineering Braude College of Engineering, Karmiel, Israel

  14. Wall-Clock Complexity for Zeroth-Order Optimization with Tunable Oracle Fidelity

    May 29, 2026Alexandra Suvorikova, Igor Pavlov, Artem Vasin +4Stochastic OptimizationOracle Complexity

    Weierstrass Institute for Applied Analysis and Stochastics, Berlin, Germany · Moscow Independent Research Institute of Artificial Intelligence, Moscow, Russia · MSU Institute for Artificial Intelligence, Moscow, Russia +3

  15. Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing

    May 15, 2026Zeji Yi, Chaoyi Pan, Guanya Shi +1Optimization Convergence AnalysisBlack-Box Optimization

    Carnegie Mellon University

  16. Position: Zeroth-Order Optimization in Deep Learning Is Underexplored, Not Underpowered

    May 15, 2026Sijia Liu, Yicheng Lang, Soumyadeep Pal +6Deep Learning OptimizationZeroth-Order Optimization

    1OPTML Lab, Michigan State University, USA · 2Lawrence Livermore National Laboratory, USA

  17. Gradient-Free Noise Optimization for Reward Alignment in Generative Models

    May 12, 2026Jeongsol Kim, Hongeun Kim, Jian Wang +1Diffusion Model AlignmentStochastic Optimal Control

    KAIST AI · Snap Inc.

  18. Training Non-Differentiable Networks via Optimal Transport

    May 3, 2026An T. LeBlack-Box OptimizationNeural Network Optimization

    Center for AI Research, VinUniversity, Vietnam · Intelligent Autonomous Systems, TU Darmstadt, Germany

  19. BOOOM: Loss-Function-Agnostic Black-Box Optimization over Orthonormal Manifolds for Machine Learning and Statistical Inference

    Apr 23, 2026Beomchang Kim, Subhrajyoty Roy, Priyam DasStiefel Manifold OptimizationBlack-Box Optimization

    Department of Biostatistics, Virginia Commonwealth University, Richmond, VA, USA · Department of Statistics and Data Science, Washington University in St. Louis,[math.OC] St. Louis, MO, USA

  20. Subspace Optimization for Backpropagation-Free Continual Test-Time Adaptation

    Mar 30, 2026Damian Sójka, Sebastian Cygert, Marc MasanaSubspace OptimizationContinual Test-Time Adaptation

    Poznan University of Technology · Akces NCBR · NASK - National Research Institute +3

  21. Meta-Learning-Assisted Constraint Relaxation for Constrained Black-Box Optimization

    Jan 31, 2026Sijie Ma, Zeyuan Ma, Yue-Jiao Gong +1Black-Box OptimizationLearning to Optimize

    Hong Kong Polytechnic University · South China Normal University · South China University of Technology

  22. Consensus-based optimization for closed-box adversarial attacks and a connection to evolution strategies

    Jun 30, 2025Tim Roith, Leon Bungert, Philipp WackerEvolutionary OptimizationBlack-Box Adversarial Attacks

    TUM School of Computation, Information and Technology and Munich Center for Machine Learning (MCML), Boltzmannstr. 3, 85748 Garching bei München, Germany · Institute of Mathematics, Center for Artificial Intelligence and Data Science (CAIDAS), University of Würzburg, Emil-Fischer-Str. 40, 97074 Würzburg, Germany · School of Mathematics and Statistics, University of Canterbury