EvoGrad: Metaheuristics in a Differentiable Wonderland

• URL: http://arxiv.org/abs/2506.06320v1
• Date: Wed, 28 May 2025 15:42:07 GMT
• Title: EvoGrad: Metaheuristics in a Differentiable Wonderland
• Authors: Beatrice F. R. Citterio, Andrea Tangherloni,
• Abstract summary: Differentiable programming has revolutionised optimisation by enabling efficient gradient-based training of complex models.<n>EvoGrad is a unified differentiable framework that integrates EC and SI with gradient-based optimisation.<n>Our results show the substantial benefits of fully differentiable evolutionary and swarm optimisation.
• Score: 1.065497990128313
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Differentiable programming has revolutionised optimisation by enabling efficient gradient-based training of complex models, such as Deep Neural Networks (NNs) with billions and trillions of parameters. However, traditional Evolutionary Computation (EC) and Swarm Intelligence (SI) algorithms, widely successful in discrete or complex search spaces, typically do not leverage local gradient information, limiting their optimisation efficiency. In this paper, we introduce EvoGrad, a unified differentiable framework that integrates EC and SI with gradient-based optimisation through backpropagation. EvoGrad converts conventional evolutionary and swarm operators (e.g., selection, mutation, crossover, and particle updates) into differentiable operators, facilitating end-to-end gradient optimisation. Extensive experiments on benchmark optimisation functions and training of small NN regressors reveal that our differentiable versions of EC and SI metaheuristics consistently outperform traditional, gradient-agnostic algorithms in most scenarios. Our results show the substantial benefits of fully differentiable evolutionary and swarm optimisation, setting a new standard for hybrid optimisation frameworks.

Related papers

• Frankenstein Optimizer: Harnessing the Potential by Revisiting Optimization Tricks [2.932254642052481]
  We propose Frankenstein, which combines various adaptive algorithms' mechanisms.<n>Experiments on computer vision, natural language processing, few-shot learning, and scientific simulations show that Frankenstein surpasses existing adaptive algorithms and gradient descent (SGD)<n>This research deepens our understanding of adaptive algorithms through centered kernel alignment analysis and loss landscape visualization during the learning process.
  arXiv  Detail & Related papers  (2025-03-04T00:25:54Z)
• Quantum Time-Series Learning with Evolutionary Algorithms [0.0]
  Variational quantum circuits have arisen as an important method in quantum computing.<n>We explore the use of evolutionary algorithms for such optimization, specifically for time-series forecasting.
  arXiv  Detail & Related papers  (2024-12-23T13:53:35Z)
• Integrating Chaotic Evolutionary and Local Search Techniques in Decision Space for Enhanced Evolutionary Multi-Objective Optimization [1.8130068086063336]
  This paper focuses on both Single-Objective Multi-Modal Optimization (SOMMOP) and Multi-Objective Optimization (MOO) In SOMMOP, we integrate chaotic evolution with niching techniques, as well as Persistence-Based Clustering combined with Gaussian mutation. For MOO, we extend these methods into a comprehensive framework that incorporates Uncertainty-Based Selection, Adaptive Tuning, and introduces a radius ( R ) concept in deterministic crowding.
  arXiv  Detail & Related papers  (2024-11-12T15:18:48Z)
• Sample-efficient Bayesian Optimisation Using Known Invariances [56.34916328814857]
  We show that vanilla and constrained BO algorithms are inefficient when optimising invariant objectives. We derive a bound on the maximum information gain of these invariant kernels. We use our method to design a current drive system for a nuclear fusion reactor, finding a high-performance solution.
  arXiv  Detail & Related papers  (2024-10-22T12:51:46Z)
• Ensemble Kalman Filtering Meets Gaussian Process SSM for Non-Mean-Field and Online Inference [47.460898983429374]
  We introduce an ensemble Kalman filter (EnKF) into the non-mean-field (NMF) variational inference framework to approximate the posterior distribution of the latent states. This novel marriage between EnKF and GPSSM not only eliminates the need for extensive parameterization in learning variational distributions, but also enables an interpretable, closed-form approximation of the evidence lower bound (ELBO) We demonstrate that the resulting EnKF-aided online algorithm embodies a principled objective function by ensuring data-fitting accuracy while incorporating model regularizations to mitigate overfitting.
  arXiv  Detail & Related papers  (2023-12-10T15:22:30Z)
• Lottery Tickets in Evolutionary Optimization: On Sparse Backpropagation-Free Trainability [0.0]
  We study gradient descent (GD)-based sparse training and evolution strategies (ES) We find that ES explore diverse and flat local optima and do not preserve linear mode connectivity across sparsity levels and independent runs.
  arXiv  Detail & Related papers  (2023-05-31T15:58:54Z)
• An Empirical Evaluation of Zeroth-Order Optimization Methods on AI-driven Molecule Optimization [78.36413169647408]
  We study the effectiveness of various ZO optimization methods for optimizing molecular objectives. We show the advantages of ZO sign-based gradient descent (ZO-signGD) We demonstrate the potential effectiveness of ZO optimization methods on widely used benchmark tasks from the Guacamol suite.
  arXiv  Detail & Related papers  (2022-10-27T01:58:10Z)
• Accelerating the Evolutionary Algorithms by Gaussian Process Regression with $\epsilon$-greedy acquisition function [2.7716102039510564]
  We propose a novel method to estimate the elite individual to accelerate the convergence of optimization. Our proposal has a broad prospect to estimate the elite individual and accelerate the convergence of optimization.
  arXiv  Detail & Related papers  (2022-10-13T07:56:47Z)
• SUPER-ADAM: Faster and Universal Framework of Adaptive Gradients [99.13839450032408]
  It is desired to design a universal framework for adaptive algorithms to solve general problems. In particular, our novel framework provides adaptive methods under non convergence support for setting.
  arXiv  Detail & Related papers  (2021-06-15T15:16:28Z)
• Evolutionary Variational Optimization of Generative Models [0.0]
  We combine two popular optimization approaches to derive learning algorithms for generative models: variational optimization and evolutionary algorithms. We show that evolutionary algorithms can effectively and efficiently optimize the variational bound. In the category of "zero-shot" learning, we observed the evolutionary variational algorithm to significantly improve the state-of-the-art in many benchmark settings.
  arXiv  Detail & Related papers  (2020-12-22T19:06:33Z)
• Bilevel Optimization: Convergence Analysis and Enhanced Design [63.64636047748605]
  Bilevel optimization is a tool for many machine learning problems. We propose a novel stoc-efficientgradient estimator named stoc-BiO.
  arXiv  Detail & Related papers  (2020-10-15T18:09:48Z)
• EOS: a Parallel, Self-Adaptive, Multi-Population Evolutionary Algorithm for Constrained Global Optimization [68.8204255655161]
  EOS is a global optimization algorithm for constrained and unconstrained problems of real-valued variables. It implements a number of improvements to the well-known Differential Evolution (DE) algorithm. Results prove that EOSis capable of achieving increased performance compared to state-of-the-art single-population self-adaptive DE algorithms.
  arXiv  Detail & Related papers  (2020-07-09T10:19:22Z)
• Dynamic Hierarchical Mimicking Towards Consistent Optimization Objectives [73.15276998621582]
  We propose a generic feature learning mechanism to advance CNN training with enhanced generalization ability. Partially inspired by DSN, we fork delicately designed side branches from the intermediate layers of a given neural network. Experiments on both category and instance recognition tasks demonstrate the substantial improvements of our proposed method.
  arXiv  Detail & Related papers  (2020-03-24T09:56:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.