Derivative-Free Optimization

Follow this topic Ask about this topic

Momentum

6 papers in the last four weeks, with none the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 16

All topics

Code to Control: Synthesizing Parameterized Reactive Controllers
Sep 30, 2026Zergham Ahmed, Joshua B. Tenenbaum, Chris Bates +1RL Control Language Model-Based Control
Harvard University · Massachusetts Institute of Technology · Florida Institute for Human and Machine Cognition
SPADE-DFL: Communication-Efficient Decentralized Federated Learning via Derivative-Free Linearized ADMM
Sep 24, 2026Mengli Wei, Mengkai Zhu, Jiawen Chen +2Communication-Efficient Distributed Training Black-Box Optimization
School of Mathematics, Southeast University, Nanjing 210096, China
Optimize, Learn, Refine: Whole-Body Grasping and Pick-and-Throw with a Spiral Soft Robot
Sep 22, 2026Marwah Basuhai, Tingcong Liu, Ibrahim Alsarraj +2Robotic Grasping Whole-Body Robotic Manipulation
Derivative-Free Structured Updates for Muon
Sep 15, 2026Pengcheng XieBlack-Box Optimization Zeroth-Order Optimization
Lawrence Berkeley National Laboratory & University of California Berkeley, CA 94720, USA
Trajectory Bundle Method in SE(3) for Black-Box Fixed-Wing Aircraft Trajectory Optimization
Sep 14, 2026Matthew D. Osburn, Cameron K. Peterson, John L. SalmonTrajectory Optimization Trajectory 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
Adaptively Incorporating Directional Hints into Zeroth-Order Optimization
Sep 8, 2026Alexander Ryabchenko, Jian Qian, Wenlong MouZeroth-Order Optimization Nonconvex Optimization
University of Toronto and Vector Institute · University of Hong Kong
Generative Refinement for Low-Budget Black-Box Optimization
Jul 1, 2026Edouard R. Dufour, Oliver Heinimann, Pascal FuaBlack-Box Optimization Derivative-Free Optimization
CVLab EPFL Lausanne, CH
\chisao{}: A GPU-Native Parallel Optimizer for Multimodal Black-Box Functions via Convergence-Anticonvergence Oscillation
Jun 24, 2026Ira WolfsonGPU Acceleration Black-Box Optimization
Department of Electronics and Electrical Engineering Braude College of Engineering, Karmiel, Israel
Wall-Clock Complexity for Zeroth-Order Optimization with Tunable Oracle Fidelity
May 29, 2026Alexandra Suvorikova, Igor Pavlov, Artem Vasin +4Stochastic Optimization Oracle 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
Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing
May 15, 2026Zeji Yi, Chaoyi Pan, Guanya Shi +1Optimization Convergence Analysis Black-Box Optimization
Carnegie Mellon University
Position: Zeroth-Order Optimization in Deep Learning Is Underexplored, Not Underpowered
May 15, 2026Sijia Liu, Yicheng Lang, Soumyadeep Pal +6Deep Learning Optimization Zeroth-Order Optimization
1OPTML Lab, Michigan State University, USA · 2Lawrence Livermore National Laboratory, USA
Gradient-Free Noise Optimization for Reward Alignment in Generative Models
May 12, 2026Jeongsol Kim, Hongeun Kim, Jian Wang +1Diffusion Model Alignment Stochastic Optimal Control
KAIST AI1 · Snap Inc.2
Training Non-Differentiable Networks via Optimal Transport
May 3, 2026An T. LeBlack-Box Optimization Neural Network Optimization
Center for AI Research, VinUniversity, Vietnam · Intelligent Autonomous Systems, TU Darmstadt, Germany
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 Optimization Black-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
Meta-Learning-Assisted Constraint Relaxation for Constrained Black-Box Optimization
Jan 31, 2026Sijie Ma, Zeyuan Ma, Yue-Jiao Gong +1Black-Box Optimization Learning to Optimize
Hong Kong Polytechnic University · South China Normal University · South China University of Technology
Consensus-based optimization for closed-box adversarial attacks and a connection to evolution strategies
Jun 30, 2025Tim Roith, Leon Bungert, Philipp WackerEvolutionary Optimization Black-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

Sep 30, 2026, cs.AIJ/K move · Enter open · S save

Code to Control: Synthesizing Parameterized Reactive Controllers

Zergham Ahmed, Joshua B. Tenenbaum, Chris Bates, Samuel J. Gershman

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

RL Control Language Model-Based Control LLM-Based Program Synthesis Derivative-Free Optimization

Open paper AskPDF arXiv

Recent LLM-based approaches to control either invoke a language model to select actions or synthesize world models that require planning at every decision, introducing latency that can limit real-time use. We introduce Code to Control, an approach that synthesizes Python controllers which execute directly as policies. Code to Control separates program structure from parameters. An LLM synthesizes the controller structure, while derivative-free search fits its parameters for continuous control using feedback from the environment. Once learned, the resulting controllers require neither LLM inference nor planning at decision time, enabling real-time gameplay and, under our timing protocol, faster action selection than a PPO policy. Across a suite of Atari games, Flappy Bird, and MuJoCo tasks, Code to Control outperforms planning-based program synthesis methods, remains competitive with deep reinforcement learning while using fewer environment interactions, transfers across substantial changes in environment dynamics, and scales to complex locomotion tasks.

Momentum

Related topics

Latest papers 16