paper-with-me

홈 › Papers

Free energy Estimation on Any State Space

2026-05-29 · Jiajun He, Zijing Ou, Francisco Vargas, Yingzhen Li, José Miguel Hernández-Lobato, Carles Domingo-Enrich, Yuanqi Du arxiv

Free energy estimation is a fundamental yet challenging problem, from physics to statistics. Classical approaches rely on thermodynamic transformations, ranging from direct estimation, quasistatic integration, to finite-time averaging. Recent work [He and Du et al., 2025] learns neural transports to significantly accelerate the efficiency in the finite-time regime. In this paper, we generalize this framework to arbitrary state spaces. Building on this view, we develop a generalized neural transport learning approach for efficient estimation. Experiments validate the effectiveness and efficiency of the proposed method beyond continuous settings, extending to discrete and multimodal spaces as well as autoregressive settings. Beyond free energy estimation, we establish algebraic identities and reveal a group-theoretic structure linking infinitesimal time reversal and generalized Doob's $h$-transforms, showing that their compositions form a generalized dihedral group.

📄 PDF Abstract BibTeX arXiv:2605.31063

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Free Energy Principle for the Noise Smoothness Estimation of Linear Systems with Colored Noise

2022-04-04 · Ajith Anil Meera, Martijn Wisse

The free energy principle (FEP) from neuroscience provides a framework called active inference for the joint estimation and control of state space systems, subjected to colored noise. However, the active inference commun…

State Estimation

Assessing generative modeling approaches for free energy estimates in condensed matter

2025-12-30 · Maximilian Schebek, Jiajun He, Emil Hoffmann, Yuanqi Du 외 arxiv

The accurate estimation of free energy differences between two states is a long-standing challenge in molecular simulations. Traditional approaches generally rely on sampling multiple intermediate states to ensure suffic…

Estimating Solvation Free Energies with Boltzmann Generators

2025-12-20 · Maximilian Schebek, Nikolas M. Froböse, Bettina G. Keller, Jutta Rogal arxiv

Accurate calculations of solvation free energies remain a central challenge in molecular simulations, often requiring extensive sampling and numerous alchemical intermediates to ensure sufficient overlap between phase-sp…

Machine Learning of Thermodynamic Observables in the Presence of Mode Collapse

2021-11-22 · Kim A. Nicoli, Christopher Anders, Lena Funcke, Tobias Hartung 외

Estimating the free energy, as well as other thermodynamic observables, is a key task in lattice field theories. Recently, it has been pointed out that deep generative models can be used in this context [1]. Crucially, t…

BIG-bench Machine Learning

Computing Absolute Free Energy with Deep Generative Models

2020-05-01 · Xinqiang Ding, Bin Zhang

Fast and accurate evaluation of free energy has broad applications from drug design to material engineering. Computing the absolute free energy is of particular interest since it allows the assessment of the relative sta…

Drug Design