Latent Heuristic Search: Continuous Optimization for Automated Algorithm Design

• URL: http://arxiv.org/abs/2605.17137v1
• Date: Sat, 16 May 2026 20:03:01 GMT
• Title: Latent Heuristic Search: Continuous Optimization for Automated Algorithm Design
• Abstract summary: This work proposes a continuous discovery framework that navigates a non-competitive landscape.<n>We use an embedding gradient map algorithm into continuous embeddings of latent differentiable surrogates.<n>The resulting optimized executables are projected through a learned mapper into soft prompts.
• Score: 6.870020562464171
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The integration of Large Language Models (LLMs) into evolutionary frameworks has established a new paradigm for automated heuristic discovery. Despite their promise, these methods typically search in the discrete space of program syntax, relying on stochastic sampling to navigate a highly non-convex optimization landscape. This work proposes a continuous heuristic discovery framework that shifts optimization to a learned latent manifold. We employ an encoder to map discrete programs into continuous embeddings and train a differentiable surrogate model to predict performance, enabling gradient-based search. To regularize the optimization trajectory, an invertible normalizing flow maps these embeddings to a structured Gaussian prior, where we perform gradient ascent. The resulting optimized latent vectors are projected through a learned mapper into soft prompts, which condition a frozen LLM to synthesize novel executable heuristics. We evaluate the proposed method on the Traveling Salesman Problem (TSP), the Capacitated Vehicle Routing Problem (CVRP), the Knapsack Problem (KSP), and Online Bin Packing (OBP). Empirical results demonstrate that continuous latent-space optimization achieves performance competitive with state-of-the-art discrete evolutionary baselines while offering a complementary methodological alternative for automated algorithm design. The implementation code is available at \url{https://github.com/cheikh025/LHS}.

Related papers

• Gradient-Free Noise Optimization for Reward Alignment in Generative Models [52.42087778653147]
  ZeNO is a gradient-free framework that formulates noise optimization as a path-integral control problem.<n>It enables effective inference-time scaling and demonstrates strong performance across diverse generators and reward functions.
  arXiv  Detail & Related papers  (2026-05-12T00:05:36Z)
• POLCA: Stochastic Generative Optimization with LLM [26.342554900977003]
  We introduce Prioritized Optimization with Local Contextualion (POLCA)<n>POLCA is a scalable framework designed to handle parameterity in optimization.<n>We demonstrate POLCA achieves robust, sample and time-efficient performance.
  arXiv  Detail & Related papers  (2026-03-16T03:07:44Z)
• DyACE: Dynamic Algorithm Co-evolution for Online Automated Heuristic Design with Large Language Model [12.490525543266807]
  We introduce DyACE (Dynamic Co-evolution) as a Non-stationary Bi-level Control problem.<n>A core element of DyACE is the Look-Ahead Rollout Search, which queries the landscape geometry to extract Search Tray Features.<n>Results demonstrate that DyACE significantly outperforms state-of-the-art static baselines.
  arXiv  Detail & Related papers  (2026-03-07T06:46:53Z)
• Learning Gradient Flow: Using Equation Discovery to Accelerate Engineering Optimization [0.0]
  We use trajectory data to learn the continuous-time dynamics associated with gradient descent, Newton's method, and ADAM optimization.<n>The discovered gradient is then solved as a surrogate for the original optimization problem.<n>We demonstrate the efficacy of this approach on several standard problems from engineering mechanics and scientific machine learning.
  arXiv  Detail & Related papers  (2026-02-13T22:44:33Z)
• Local Entropy Search over Descent Sequences for Bayesian Optimization [48.7994415668802]
  A practical alternative is to iteratively refine the neighborhood of an initial design using local optimization methods such as gradient descent.<n>We propose local entropy search (LES), a Bayesian optimization paradigm that explicitly targets the solutions reachable by the descent sequences.
  arXiv  Detail & Related papers  (2025-11-24T15:52:17Z)
• Sparsity-Constraint Optimization via Splicing Iteration [1.3622424109977902]
  We develop an algorithm named Sparsity-Constraint Optimization via sPlicing itEration (SCOPE) SCOPE converges effectively without tuning parameters. We apply SCOPE to solve quadratic optimization, learn sparse classifiers, and recover sparse Markov networks for binary variables. Our open-source Python package skscope based on C++ implementation is publicly available on GitHub.
  arXiv  Detail & Related papers  (2024-06-17T18:34:51Z)
• Beyond Single-Model Views for Deep Learning: Optimization versus Generalizability of Stochastic Optimization Algorithms [13.134564730161983]
  This paper adopts a novel approach to deep learning optimization, focusing on gradient descent (SGD) and its variants. We show that SGD and its variants demonstrate performance on par with flat-minimas like SAM, albeit with half the gradient evaluations. Our study uncovers several key findings regarding the relationship between training loss and hold-out accuracy, as well as the comparable performance of SGD and noise-enabled variants.
  arXiv  Detail & Related papers  (2024-03-01T14:55:22Z)
• Federated Conditional Stochastic Optimization [110.513884892319]
  Conditional optimization has found in a wide range of machine learning tasks, such as in-variant learning tasks, AUPRC, andAML. This paper proposes algorithms for distributed federated learning.
  arXiv  Detail & Related papers  (2023-10-04T01:47:37Z)
• Finite-Sample Bounds for Adaptive Inverse Reinforcement Learning using Passive Langevin Dynamics [13.440621354486906]
  This paper provides a finite-sample analysis of a passive gradient Langevin dynamics (PSGLD) algorithm.<n> Adaptive IRL aims to estimate the cost function of a forward learner performing a gradient algorithm.
  arXiv  Detail & Related papers  (2023-04-18T16:39:51Z)
• Performance Embeddings: A Similarity-based Approach to Automatic Performance Optimization [71.69092462147292]
  Performance embeddings enable knowledge transfer of performance tuning between applications. We demonstrate this transfer tuning approach on case studies in deep neural networks, dense and sparse linear algebra compositions, and numerical weather prediction stencils.
  arXiv  Detail & Related papers  (2023-03-14T15:51:35Z)
• 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)
• Global Optimization of Gaussian processes [52.77024349608834]
  We propose a reduced-space formulation with trained Gaussian processes trained on few data points. The approach also leads to significantly smaller and computationally cheaper sub solver for lower bounding. In total, we reduce time convergence by orders of orders of the proposed method.
  arXiv  Detail & Related papers  (2020-05-21T20:59:11Z)

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.