Performance of machine-learning-assisted Monte Carlo in sampling from simple statistical physics models

• URL: http://arxiv.org/abs/2505.22598v4
• Date: Tue, 07 Oct 2025 20:41:31 GMT
• Title: Performance of machine-learning-assisted Monte Carlo in sampling from simple statistical physics models
• Abstract summary: We study the widely-used Sequential Tempering procedure applied to a shallow MADE architecture for the Curie-Weiss model.<n>This work establishes a clear theoretical basis for the integration of machine learning techniques into Monte Carlo sampling and optimization.
• Score: 0.38233569758620045
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent years have seen a rise in the application of machine learning techniques to aid the simulation of hard-to-sample systems that cannot be studied using traditional methods. Despite the introduction of many different architectures and procedures, a wide theoretical understanding is still lacking, with the risk of suboptimal implementations. As a first step to address this gap, we provide here a complete analytic study of the widely-used Sequential Tempering procedure applied to a shallow MADE architecture for the Curie-Weiss model. The contribution of this work is twofold: firstly, we give a description of the optimal weights and of the training under Gradient Descent optimization. Secondly, we compare what happens in Sequential Tempering with and without the addition of local Metropolis Monte Carlo steps. We are thus able to give theoretical predictions on the best procedure to apply in this case. This work establishes a clear theoretical basis for the integration of machine learning techniques into Monte Carlo sampling and optimization.

Related papers

• INSPIRE: An Internalize-Then-Improve Approach for Example-Driven Mathematical Reasoning [61.60016491769943]
  In human mathematics education, example-based reasoning such as constructing counterexamples to test theorem boundaries reflects deep conceptual understanding.<n>We propose INSPIRE, an Internalize-Then-Improve approach combining Reference-Guided Student Internalization (RGSI) with a stage-wise preference training strategy.<n>Experiments across multiple model scales and families demonstrate consistent improvements, even surpassing larger open-source models.
  arXiv  Detail & Related papers  (2026-08-27T03:24:03Z)
• New Hybrid Fine-Tuning Paradigm for LLMs: Algorithm Design and Convergence Analysis Framework [52.69678300445233]
  Fine-tuning Large Language Models (LLMs) typically involves either full fine-tuning, which updates all model parameters, or.<n>Efficient Fine-Tuning (PEFT) adjusts a small subset of parameters.<n>We propose a novel hybrid fine-tuning approach that jointly updates both LLMs and PEFT modules using a combination of zeroth-order and first-order optimization methods.
  arXiv  Detail & Related papers  (2026-04-10T22:39:38Z)
• Efficient Stochastic Optimisation via Sequential Monte Carlo [0.5599792629509229]
  We develop sequential Monte Carlo samplers for optimisation of functions with intractable gradients.<n>Our approach replaces expensive inner sampling methods with efficient SMC approximations, which can result in significant computational gains.<n>We demonstrate the effectiveness of our approach on the reward-tuning of energy-based models within various settings.
  arXiv  Detail & Related papers  (2026-01-29T17:13:25Z)
• How to Set the Learning Rate for Large-Scale Pre-training? [73.03133634525635]
  We formalize this investigation into two distinct research paradigms: Fitting and Transfer.<n>Within the Fitting Paradigm, we introduce a Scaling Law for search factor, effectively reducing the search complexity from O(n3) to O(n*C_D*C_) via predictive modeling.<n>We extend the principles of $$Transfer to the Mixture of Experts (MoE) architecture, broadening its applicability to encompass model depth, weight decay, and token horizons.
  arXiv  Detail & Related papers  (2026-01-08T15:55:13Z)
• Fast Riemannian-manifold Hamiltonian Monte Carlo for hierarchical Gaussian-process models [0.0]
  We show that, compared with the slow inference achieved with existing program libraries, the performance can be drastically improved.<n>We demonstrate that RMHMC effectively samples from the posterior, allowing the calculation of model evidence.<n>We highlight the need to develop a customisable library set that allows users to incorporate dynamically programmed objects.
  arXiv  Detail & Related papers  (2025-11-09T14:44:13Z)
• Demonstrating Real Advantage of Machine-Learning-Enhanced Monte Carlo for Combinatorial Optimization [0.38233569758620045]
  We use a Global Annealing Monte Carlo algorithm that integrates standard local moves with global moves proposed via machine learning.<n>We show that local moves play a crucial role in achieving optimal performance.<n>These results provide the first clear and robust evidence that a machine learning-assisted optimization method can exceed the capabilities of classical state-of-the-art techniques.
  arXiv  Detail & Related papers  (2025-10-22T12:50:27Z)
• Large Language Models as Computable Approximations to Solomonoff Induction [11.811838796672369]
  We establish the first formal connection between large language models (LLMs) and Algorithmic Information Theory (AIT)<n>We leverage AIT to provide a unified theoretical explanation for in-context learning, few-shot learning, and scaling laws.<n>Our framework bridges the gap between theoretical foundations and practical LLM behaviors, providing both explanatory power and actionable insights for future model development.
  arXiv  Detail & Related papers  (2025-05-21T17:35:08Z)
• Will Pre-Training Ever End? A First Step Toward Next-Generation Foundation MLLMs via Self-Improving Systematic Cognition [86.21199607040147]
  Self-Improving cognition (SIcog) is a self-learning framework for constructing next-generation foundation language models.<n>We introduce Chain-of-Description, a step-by-step visual understanding method, and integrate structured chain-of-thought (CoT) reasoning to support in-depth multimodal reasoning.<n>Extensive experiments demonstrate that SIcog produces next-generation foundation MLLMs with substantially improved multimodal cognition.
  arXiv  Detail & Related papers  (2025-03-16T00:25:13Z)
• Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Review [59.856222854472605]
  This tutorial provides an in-depth guide on inference-time guidance and alignment methods for optimizing downstream reward functions in diffusion models.<n> practical applications in fields such as biology often require sample generation that maximizes specific metrics.<n>We discuss (1) fine-tuning methods combined with inference-time techniques, (2) inference-time algorithms based on search algorithms such as Monte Carlo tree search, and (3) connections between inference-time algorithms in language models and diffusion models.
  arXiv  Detail & Related papers  (2025-01-16T17:37:35Z)
• A Survey on Inference Optimization Techniques for Mixture of Experts Models [50.40325411764262]
  Large-scale Mixture of Experts (MoE) models offer enhanced model capacity and computational efficiency through conditional computation.<n> deploying and running inference on these models presents significant challenges in computational resources, latency, and energy efficiency.<n>This survey analyzes optimization techniques for MoE models across the entire system stack.
  arXiv  Detail & Related papers  (2024-12-18T14:11:15Z)
• SPO: Sequential Monte Carlo Policy Optimisation [41.52684912140086]
  We introduce SPO: Sequential Monte Carlo Policy optimisation. We show that SPO provides robust policy improvement and efficient scaling properties. We demonstrate statistically significant improvements in performance relative to model-free and model-based baselines.
  arXiv  Detail & Related papers  (2024-02-12T10:32:47Z)
• Variational Monte Carlo on a Budget -- Fine-tuning pre-trained Neural Wavefunctions [5.145741425164946]
  Deep-learning-based Variational Monte Carlo (DL-VMC) has recently outperformed conventional approaches in terms of accuracy, but only at large computational cost. We propose a DL-VMC model which has been pre-trained using self-supervised wavefunction optimization on a large and chemically diverse set of molecules. Applying this model to new molecules without any optimization, yields wavefunctions and absolute energies that outperform established methods such as CCSD(T)-2Z.
  arXiv  Detail & Related papers  (2023-07-15T09:56:22Z)
• Towards Constituting Mathematical Structures for Learning to Optimize [101.80359461134087]
  A technique that utilizes machine learning to learn an optimization algorithm automatically from data has gained arising attention in recent years. A generic L2O approach parameterizes the iterative update rule and learns the update direction as a black-box network. While the generic approach is widely applicable, the learned model can overfit and may not generalize well to out-of-distribution test sets. We propose a novel L2O model with a mathematics-inspired structure that is broadly applicable and generalized well to out-of-distribution problems.
  arXiv  Detail & Related papers  (2023-05-29T19:37:28Z)
• Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL [106.82295532402335]
  Existing reinforcement learning algorithms suffer from computational intractability, strong statistical assumptions, and suboptimal sample complexity. We provide the first computationally efficient algorithm that attains rate-optimal sample complexity with respect to the desired accuracy level. Our algorithm, MusIK, combines systematic exploration with representation learning based on multi-step inverse kinematics.
  arXiv  Detail & Related papers  (2023-04-12T14:51:47Z)
• Scalable PAC-Bayesian Meta-Learning via the PAC-Optimal Hyper-Posterior: From Theory to Practice [54.03076395748459]
  A central question in the meta-learning literature is how to regularize to ensure generalization to unseen tasks. We present a generalization bound for meta-learning, which was first derived by Rothfuss et al. We provide a theoretical analysis and empirical case study under which conditions and to what extent these guarantees for meta-learning improve upon PAC-Bayesian per-task learning bounds.
  arXiv  Detail & Related papers  (2022-11-14T08:51:04Z)
• Learning Lattice Quantum Field Theories with Equivariant Continuous Flows [10.124564216461858]
  We propose a novel machine learning method for sampling from the high-dimensional probability distributions of Lattice Field Theories. We test our model on the $phi4$ theory, showing that it systematically outperforms previously proposed flow-based methods in sampling efficiency.
  arXiv  Detail & Related papers  (2022-07-01T09:20:05Z)
• Macroscopic Traffic Flow Modeling with Physics Regularized Gaussian Process: Generalized Formulations [5.827236278192557]
  This study presents a new modeling framework, named physics regularized Gaussian process (PRGP) This novel approach can encode physics models, i.e., classical traffic flow models, into the Gaussian process architecture and so as to regularize the Machine Learning training process. To prove the effectiveness of the proposed model, this paper conducts empirical studies on a real-world dataset that is collected from a stretch of I-15 freeway, Utah.
  arXiv  Detail & Related papers  (2020-07-14T17:27:23Z)
• Guided Learning of Nonconvex Models through Successive Functional Gradient Optimization [22.603803397940133]
  This paper presents a framework for gradient optimization for non functional models such as neural networks. We provide a theoretical analysis method derived from this framework.
  arXiv  Detail & Related papers  (2020-06-30T14:31:24Z)
• A Dynamical Systems Approach for Convergence of the Bayesian EM Algorithm [59.99439951055238]
  We show how (discrete-time) Lyapunov stability theory can serve as a powerful tool to aid, or even lead, in the analysis (and potential design) of optimization algorithms that are not necessarily gradient-based. The particular ML problem that this paper focuses on is that of parameter estimation in an incomplete-data Bayesian framework via the popular optimization algorithm known as maximum a posteriori expectation-maximization (MAP-EM) We show that fast convergence (linear or quadratic) is achieved, which could have been difficult to unveil without our adopted S&C approach.
  arXiv  Detail & Related papers  (2020-06-23T01:34:18Z)
• Deep Neural Network Learning with Second-Order Optimizers -- a Practical Study with a Stochastic Quasi-Gauss-Newton Method [0.0]
  We introduce and study a second-order quasi-Gauss-Newton (SQGN) optimization method that combines ideas from quasi-Newton methods, Gauss-Newton methods, and variance reduction to address this problem. We discuss the implementation of SQGN with benchmark, and we compare its convergence and computational performance to selected first-order methods.
  arXiv  Detail & Related papers  (2020-04-06T23:41:41Z)

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.