English
Related papers

Related papers: Improving Gradient Estimation in Evolutionary Stra…

200 papers

We propose a novel family of decision-aware surrogate losses, called Perturbation Gradient (PG) losses, for the predict-then-optimize framework. The key idea is to connect the expected downstream decision loss with the directional…

Machine Learning · Computer Science 2024-11-01 Michael Huang , Vishal Gupta

Gradient-based optimization is the foundation of deep learning and reinforcement learning. Even when the mechanism being optimized is unknown or not differentiable, optimization using high-variance or biased gradient estimates is still…

Machine Learning · Computer Science 2018-02-27 Will Grathwohl , Dami Choi , Yuhuai Wu , Geoffrey Roeder , David Duvenaud

Neural network optimization remains one of the most consequential yet poorly understood challenges in modern AI research, where improvements in training algorithms can lead to enhanced feature learning in foundation models,…

Machine Learning · Computer Science 2025-12-23 Ansh Nagwekar

We present a new method of blackbox optimization via gradient approximation with the use of structured random orthogonal matrices, providing more accurate estimators than baselines and with provable theoretical guarantees. We show that this…

Machine Learning · Computer Science 2018-06-13 Krzysztof Choromanski , Mark Rowland , Vikas Sindhwani , Richard E. Turner , Adrian Weller

In many mechanistic medical, biological, physical and engineered spatiotemporal dynamic models the numerical solution of partial differential equations (PDEs) can make simulations impractically slow. Biological models require the…

Soft Condensed Matter · Physics 2021-02-11 J. Quetzalcóatl Toledo-Marín , Geoffrey Fox , James P. Sluka , James A. Glazier

Evolutionary Reinforcement Learning (ERL), training the Reinforcement Learning (RL) policies with Evolutionary Algorithms (EAs), have demonstrated enhanced exploration capabilities and greater robustness than using traditional policy…

Machine Learning · Computer Science 2025-05-30 Bingdong Li , Mei Jiang , Hong Qian , Ke Tang , Aimin Zhou , Peng Yang

Evolutionary Reinforcement Learning (ERL) that applying Evolutionary Algorithms (EAs) to optimize the weight parameters of Deep Neural Network (DNN) based policies has been widely regarded as an alternative to traditional reinforcement…

Neural and Evolutionary Computing · Computer Science 2023-02-01 Lan Tang , Xiaxi Li , Jinyuan Zhang , Guiying Li , Peng Yang , Ke Tang

This paper presents a novel methodology that uses surrogate models in the form of neural networks to reduce the computation time of simulation-based optimization of a reference trajectory. Simulation-based optimization is necessary when…

Optimization and Control · Mathematics 2023-03-31 Evelyn Ruff , Rebecca Russell , Matthew Stoeckle , Piero Miotto , Jonathan P. How

Efficient Natural Evolution Strategies (eNES) is a novel alternative to conventional evolutionary algorithms, using the natural gradient to adapt the mutation distribution. Unlike previous methods based on natural gradients, eNES uses a…

Artificial Intelligence · Computer Science 2012-09-27 Yi Sun , Daan Wierstra , Tom Schaul , Juergen Schmidhuber

Evolution Strategies (ES) have recently been demonstrated to be a viable alternative to reinforcement learning (RL) algorithms on a set of challenging deep RL problems, including Atari games and MuJoCo humanoid locomotion benchmarks. While…

Neural and Evolutionary Computing · Computer Science 2018-02-27 Patryk Chrabaszcz , Ilya Loshchilov , Frank Hutter

In this paper, we consider a general stochastic optimization problem which is often at the core of supervised learning, such as deep learning and linear classification. We consider a standard stochastic gradient descent (SGD) method with a…

Machine Learning · Statistics 2018-12-27 Lam M. Nguyen , Nam H. Nguyen , Dzung T. Phan , Jayant R. Kalagnanam , Katya Scheinberg

This work concerns the evolutionary approaches to distributed stochastic black-box optimization, in which each worker can individually solve an approximation of the problem with nature-inspired algorithms. We propose a distributed evolution…

Neural and Evolutionary Computing · Computer Science 2022-04-12 Xiaoyu He , Zibin Zheng , Chuan Chen , Yuren Zhou , Chuan Luo , Qingwei Lin

Deep Reinforcement Learning (RL) has emerged as a powerful method for addressing complex control problems, particularly those involving underactuated robotic systems. However, in some cases, policies may require refinement to achieve…

Robotics · Computer Science 2025-07-15 Marco Calì , Alberto Sinigaglia , Niccolò Turcato , Ruggero Carli , Gian Antonio Susto

Surrogate models provide a low computational cost alternative to evaluating expensive functions. The construction of accurate surrogate models with large numbers of independent variables is currently prohibitive because it requires a large…

Machine Learning · Computer Science 2017-08-10 Mohamed Amine Bouhlel , Joaquim R. R. A. Martins

Fine-tuning large language models (LLMs) for downstream tasks is an essential stage of modern AI deployment. Reinforcement learning (RL) has emerged as the dominant fine-tuning paradigm, underpinning many state-of-the-art LLMs. In contrast,…

Machine Learning · Computer Science 2026-02-10 Xin Qiu , Yulu Gan , Conor F. Hayes , Qiyao Liang , Yinggan Xu , Roberto Dailey , Elliot Meyerson , Babak Hodjat , Risto Miikkulainen

Improving competent robot policies with on-policy RL is often hampered by noisy, low-signal gradients. We revisit Evolution Strategies (ES) as a policy-gradient proxy and localize exploration with bounded, antithetic triangular…

Machine Learning · Computer Science 2025-11-17 Ethan Hirschowitz , Fabio Ramos

For stochastic process models, parameter inference is often severely bottlenecked by computationally expensive likelihood functions. Simulation-based inference (SBI) bypasses this restriction by constructing amortized surrogate likelihoods,…

Machine Learning · Statistics 2026-05-26 Alexander Shen , Mikael Kuusela

We are interested in the development of surrogate models for uncertainty quantification and propagation in problems governed by stochastic PDEs using a deep convolutional encoder-decoder network in a similar fashion to approaches considered…

Computational Physics · Physics 2018-05-09 Yinhao Zhu , Nicholas Zabaras

In this paper, we propose a surrogate-assisted evolutionary algorithm (EA) for hyperparameter optimization of machine learning (ML) models. The proposed STEADE model initially estimates the objective function landscape using RadialBasis…

Neural and Evolutionary Computing · Computer Science 2020-12-14 Subhodip Biswas , Adam D Cobb , Andreea Sistrunk , Naren Ramakrishnan , Brian Jalaian

Evolution Strategy (ES) is a powerful black-box optimization technique based on the idea of natural evolution. In each of its iterations, a key step entails ranking candidate solutions based on some fitness score. For an ES method in…

Machine Learning · Computer Science 2023-02-22 Eshwar S R , Shishir Kolathaya , Gugan Thoppe