Continuous Program Search

• URL: http://arxiv.org/abs/2602.07659v1
• Date: Sat, 07 Feb 2026 18:41:14 GMT
• Title: Continuous Program Search
• Authors: Matthew Siper, Muhammad Umair Nasir, Ahmed Khalifa, Lisa Soros, Jay Azhang, Julian Togelius,
• Abstract summary: We frame this as an operator-design problem: learn a continuous program space where latent distance has behavioral meaning, then design mutation operators that exploit this structure without changing the evolutionary algorithm.<n>We make locality measurable by tracking action-level divergence under controlled latent perturbations, identifying an empirical trust region for behavior-local continuous variation.<n>Although isotropic mutation occasionally attains higher peak performance, geometry-compiled mutation yields faster, more reliable progress, demonstrating that semantically aligned mutation can substantially improve search efficiency without modifying the underlying evolutionary algorithm.
• Score: 4.198653054660764
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Genetic Programming yields interpretable programs, but small syntactic mutations can induce large, unpredictable behavioral shifts, degrading locality and sample efficiency. We frame this as an operator-design problem: learn a continuous program space where latent distance has behavioral meaning, then design mutation operators that exploit this structure without changing the evolutionary optimizer. We make locality measurable by tracking action-level divergence under controlled latent perturbations, identifying an empirical trust region for behavior-local continuous variation. Using a compact trading-strategy DSL with four semantic components (long/short entry and exit), we learn a matching block-factorized embedding and compare isotropic Gaussian mutation over the full latent space to geometry-compiled mutation that restricts updates to semantically paired entry--exit subspaces and proposes directions using a learned flow-based model trained on logged mutation outcomes. Under identical $(μ+λ)$ evolution strategies and fixed evaluation budgets across five assets, the learned mutation operator discovers strong strategies using an order of magnitude fewer evaluations and achieves the highest median out-of-sample Sharpe ratio. Although isotropic mutation occasionally attains higher peak performance, geometry-compiled mutation yields faster, more reliable progress, demonstrating that semantically aligned mutation can substantially improve search efficiency without modifying the underlying evolutionary algorithm.

Related papers

• Controlled Self-Evolution for Algorithmic Code Optimization [33.82967000330864]
  Self-evolution methods enhance code generation through iterative "generate-verify-refine" cycles.<n>Existing approaches fail to discover solutions with superior complexity within limited budgets.<n>We propose Controlled Self-Evolution (CSE), which consists of three key components.
  arXiv  Detail & Related papers  (2026-01-12T09:23:13Z)
• Weights to Code: Extracting Interpretable Algorithms from the Discrete Transformer [65.38883376379812]
  We propose the Discrete Transformer, an architecture engineered to bridge the gap between continuous representations and discrete symbolic logic.<n> Empirically, the Discrete Transformer not only achieves performance comparable to RNN-based baselines but crucially extends interpretability to continuous variable domains.
  arXiv  Detail & Related papers  (2026-01-09T12:49:41Z)
• EvoLattice: Persistent Internal-Population Evolution through Multi-Alternative Quality-Diversity Graph Representations for LLM-Guided Program Discovery [2.1756081703276]
  EvoLattice is a framework that represents an entire population of candidate programs or agent behaviors within a single directed acyclic graph.<n>Each node stores multiple persistent alternatives, and every valid path through the graph defines a distinct candidate.<n>EvoLattice produces statistics that reveal how local design choices affect global performance.
  arXiv  Detail & Related papers  (2025-12-15T19:43:06Z)
• Learning to Evolve with Convergence Guarantee via Neural Unrolling [37.99564850768798]
  We introduce Learning to Evolve (L2E), a unified bilevel meta-optimization framework.<n>L2E reformulates evolutionary search as a Neural Unrolling process grounded in Krasnosel'skii-Mann (KM) fixed-point theory.<n>Experiments demonstrate the scalability of L2E in high-dimensional spaces and its robust zero-shot generalization across synthetic and real-world control tasks.
  arXiv  Detail & Related papers  (2025-12-12T10:46:25Z)
• Improving Anomaly Detection in Industrial Time Series: The Role of Segmentation and Heterogeneous Ensemble [36.94429692322632]
  We show how the integration of segmentation techniques, combined with a heterogeneous ensemble, can enhance anomaly detection in an industrial production context.<n>We improve the AUC-ROC metric from 0.8599 (achieved with a PCA and LSTM ensemble) to 0.9760 (achieved with Random Forest and XGBoost)<n>In our future work, we intend to assess the benefit of introducing weighted features derived from the study of change points, combined with segmentation and the use of heterogeneous ensembles, to further optimize model performance in early anomaly detection.
  arXiv  Detail & Related papers  (2025-10-10T07:24:47Z)
• Neural Optimal Transport Meets Multivariate Conformal Prediction [58.43397908730771]
  We propose a framework for conditional vectorile regression (CVQR)<n>CVQR combines neural optimal transport with quantized optimization, and apply it to predictions.
  arXiv  Detail & Related papers  (2025-09-29T19:50:19Z)
• PseudoNeg-MAE: Self-Supervised Point Cloud Learning using Conditional Pseudo-Negative Embeddings [55.55445978692678]
  PseudoNeg-MAE enhances global feature representation of point cloud masked autoencoders by making them both discriminative and sensitive to transformations.<n>We propose a novel loss that explicitly penalizes invariant collapse, enabling the network to capture richer transformation cues while preserving discriminative representations.
  arXiv  Detail & Related papers  (2024-09-24T07:57:21Z)
• A Flexible Evolutionary Algorithm With Dynamic Mutation Rate Archive [2.07180164747172]
  We propose a new, flexible approach for dynamically maintaining successful mutation rates in evolutionary algorithms using $k$-bit flip mutations. Rates expire when their number of unsuccessful trials has exceeded a threshold, while rates currently not present in the archive can enter it in two ways. For the minimum selection probabilities, we suggest different options, including heavy-tailed distributions.
  arXiv  Detail & Related papers  (2024-04-05T10:51:40Z)
• GE-AdvGAN: Improving the transferability of adversarial samples by gradient editing-based adversarial generative model [69.71629949747884]
  Adversarial generative models, such as Generative Adversarial Networks (GANs), are widely applied for generating various types of data. In this work, we propose a novel algorithm named GE-AdvGAN to enhance the transferability of adversarial samples.
  arXiv  Detail & Related papers  (2024-01-11T16:43:16Z)
• Uncovering mesa-optimization algorithms in Transformers [61.06055590704677]
  Some autoregressive models can learn as an input sequence is processed, without undergoing any parameter changes, and without being explicitly trained to do so. We show that standard next-token prediction error minimization gives rise to a subsidiary learning algorithm that adjusts the model as new inputs are revealed. Our findings explain in-context learning as a product of autoregressive loss minimization and inform the design of new optimization-based Transformer layers.
  arXiv  Detail & Related papers  (2023-09-11T22:42:50Z)
• Deriving Differential Target Propagation from Iterating Approximate Inverses [91.3755431537592]
  We show that a particular form of target propagation, relying on learned inverses of each layer, which is differential, gives rise to an update rule which corresponds to an approximate Gauss-Newton gradient-based optimization. We consider several iterative calculations based on local auto-encoders at each layer in order to achieve more precise inversions for more accurate target propagation.
  arXiv  Detail & Related papers  (2020-07-29T22:34:45Z)

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.