GP-GOMEA with GPU-Based Fitness Evaluations: Design and Performance Analysis

• URL: http://arxiv.org/abs/2605.30954v1
• Date: Fri, 29 May 2026 07:48:46 GMT
• Title: GP-GOMEA with GPU-Based Fitness Evaluations: Design and Performance Analysis
• Abstract summary: GP-GOMEA is a state-of-the-art evolutionary algorithm for symbolic regression.<n>In this work, we take the first major step toward a fully GPU-accelerated GP-GOMEA by introducing a GPU-based fitness evaluation scheme.<n>This substantially increases evaluation throughput, enabling orders of magnitude more evaluations within the same time budget.<n>For the first time, this expanded capability allows a problem-agnostic evolutionary algorithm to reliably regress one of the largest Feynman equations within four hours.
• Score: 1.0439136407307046
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: GP-GOMEA is a state-of-the-art evolutionary algorithm for symbolic regression, known for discovering small and interpretable models. However, its computational cost remains substantial, limiting its applicability to larger datasets and more complex target expressions. In contrast, the rise of modern subsymbolic approaches, particularly deep learning, has been driven largely by the massive parallelism offered by GPUs. In this work, we take the first major step toward a fully GPU-accelerated GP-GOMEA by introducing a GPU-based fitness evaluation scheme. We design a GPU-friendly representation of GP-GOMEA's template-based individuals and a corresponding evaluation strategy that exploits the inherent parallelism of population-based search. This substantially increases evaluation throughput, enabling orders of magnitude more evaluations within the same time budget. Across four standard symbolic regression benchmarks, this increased evaluation capacity yields performance improvements, particularly for larger datasets and larger population sizes. Moreover, the ability to efficiently evaluate much larger datasets and more complex templates enables analyses that were previously infeasible, allowing us to systematically analyze what makes expressions increasingly difficult for GP-GOMEA, providing new insights into how expression structure affects search difficulty. Finally, for the first time, this expanded capability allows a problem-agnostic evolutionary algorithm to reliably regress one of the largest Feynman equations within four hours.

Related papers

• Simultaneous Model-Based Evolution of Constants and Expression Structure in GP-GOMEA for Symbolic Regression [1.2234742322758418]
  GP-GOMEA is one of the leading algorithms for finding accurate, yet compact expressions.<n>We propose a novel approach where constants in expressions are optimized at the same time as the expression structure.
  arXiv  Detail & Related papers  (2026-06-01T13:29:30Z)
• SIKA-GP: Accelerating Gaussian Process Inference with Sparse Inducing Kernel Approximations for Bayesian Deep Learning [5.828153240183482]
  We propose SIKA-GP, which accelerates GP inference using sparse inducing kernel approximations based on a dyadic ordered template basis.<n>Our approach constructs compact and expressive kernel representations from sparsely activated bases.<n>SIKA-GP can be naturally embedded into Bayesian neural networks (BNNs) with sparse activations, yielding significant speedups in both training and inference without sacrificing predictive performance.
  arXiv  Detail & Related papers  (2026-05-26T03:49:13Z)
• GPU-Accelerated Algorithms for Graph Vector Search: Taxonomy, Empirical Study, and Research Directions [54.570944939061555]
  We present a comprehensive study of GPU-accelerated graph-based vector search algorithms.<n>We establish a detailed taxonomy of GPU optimization strategies and clarify the mapping between algorithmic tasks and hardware execution units.<n>Our findings offer clear guidelines for designing scalable and robust GPU-powered approximate nearest neighbor search systems.
  arXiv  Detail & Related papers  (2026-02-10T16:18:04Z)
• A Better Multi-Objective GP-GOMEA -- But do we Need it? [0.0]
  In Symbolic Regression (SR) achieving a proper balance between accuracy and interpretability remains a key challenge.<n>The Genetic Programming variant of the Gene-pool Optimal Mixing Evolutionary Algorithm (GP-GOMEA) is of particular interest as it achieves state-of-the-art performance using a template that limits the size of expressions.<n>A recently introduced expansion, modular GP-GOMEA, is capable of decomposing expressions using multiple subexpressions, further increasing chances of interpretability.<n>A multi-objective variant of GP-GOMEA exists, which can be used, for instance, to optimize for size and accuracy simultaneously
  arXiv  Detail & Related papers  (2025-07-04T18:54:27Z)
• Enabling Population-Level Parallelism in Tree-Based Genetic Programming for GPU Acceleration [9.421242935448722]
  Tree-based Genetic Programming (TGP) is a widely used evolutionary computation algorithm for tasks such as symbolic regression, classification, and robotic control.<n>EvoGP is a high-performance framework tailored for GPU acceleration of TGP via population-level parallel execution.
  arXiv  Detail & Related papers  (2025-01-21T07:42:54Z)
• Generalizing Backpropagation for Gradient-Based Interpretability [103.2998254573497]
  We show that the gradient of a model is a special case of a more general formulation using semirings. This observation allows us to generalize the backpropagation algorithm to efficiently compute other interpretable statistics.
  arXiv  Detail & Related papers  (2023-07-06T15:19:53Z)
• Hierarchical shrinkage Gaussian processes: applications to computer code emulation and dynamical system recovery [5.694170341269015]
  We propose a new hierarchical shrinkage GP (HierGP), which incorporates such structure via cumulative shrinkage priors within a GP framework. We show that the HierGP implicitly embeds the well-known principles of effect sparsity, heredity and hierarchy for analysis of experiments. We propose efficient posterior sampling algorithms for model training and prediction, and prove desirable consistency properties for the HierGP.
  arXiv  Detail & Related papers  (2023-02-01T21:00:45Z)
• A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking [124.21408098724551]
  Large-scale graph training is a notoriously challenging problem for graph neural networks (GNNs) We present a new ensembling training manner, named EnGCN, to address the existing issues. Our proposed method has achieved new state-of-the-art (SOTA) performance on large-scale datasets.
  arXiv  Detail & Related papers  (2022-10-14T03:43:05Z)
• Integrated Gradient attribution for Gaussian Processes with non-Gaussian likelihoods [0.0]
  Gaussian Process (GP) models are a powerful tool in probabilistic machine learning.<n>The need for making a model's decision making process transparent and explainable is now a major focus of research.<n>This paper proposes an approach for applying Integrated Gradient-based explainability to non-Gaussian GP models.
  arXiv  Detail & Related papers  (2022-05-25T14:11:00Z)
• Scaling Gaussian Process Optimization by Evaluating a Few Unique Candidates Multiple Times [119.41129787351092]
  We show that sequential black-box optimization based on GPs can be made efficient by sticking to a candidate solution for multiple evaluation steps. We modify two well-established GP-Opt algorithms, GP-UCB and GP-EI to adapt rules from batched GP-Opt.
  arXiv  Detail & Related papers  (2022-01-30T20:42:14Z)
• Incremental Ensemble Gaussian Processes [53.3291389385672]
  We propose an incremental ensemble (IE-) GP framework, where an EGP meta-learner employs an it ensemble of GP learners, each having a unique kernel belonging to a prescribed kernel dictionary. With each GP expert leveraging the random feature-based approximation to perform online prediction and model update with it scalability, the EGP meta-learner capitalizes on data-adaptive weights to synthesize the per-expert predictions. The novel IE-GP is generalized to accommodate time-varying functions by modeling structured dynamics at the EGP meta-learner and within each GP learner.
  arXiv  Detail & Related papers  (2021-10-13T15:11:25Z)
• Harnessing Heterogeneity: Learning from Decomposed Feedback in Bayesian Modeling [68.69431580852535]
  We introduce a novel GP regression to incorporate the subgroup feedback. Our modified regression has provably lower variance -- and thus a more accurate posterior -- compared to previous approaches. We execute our algorithm on two disparate social problems.
  arXiv  Detail & Related papers  (2021-07-07T03:57:22Z)

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.