English
Related papers

Related papers: Temperature-Annealed Boltzmann Generators

200 papers

The Boltzmann distribution of a protein provides a roadmap to all of its functional states. Normalizing flows are a promising tool for modeling this distribution, but current methods are intractable for typical pharmacological targets; they…

Machine Learning · Computer Science 2024-01-10 Joseph C. Kim , David Bloore , Karan Kapoor , Jun Feng , Ming-Hong Hao , Mengdi Wang

For many applications, such as computing the expected value of different magnitudes, sampling from a known probability density function, the target density, is crucial but challenging through the inverse transform. In these cases, rejection…

Machine Learning · Computer Science 2020-03-24 Sebastian Pina-Otey , Thorsten Lux , Federico Sánchez , Vicens Gaitan

Scalable sampling of molecular states in thermodynamic equilibrium is a long-standing challenge in statistical physics. Boltzmann Generators tackle this problem by pairing a generative model, capable of exact likelihood computation, with…

Machine Learning · Computer Science 2025-12-11 Danyal Rehman , Tara Akhound-Sadegh , Artem Gazizov , Yoshua Bengio , Alexander Tong

Efficient sampling of the Boltzmann distribution of molecular systems is a long-standing challenge. Recently, instead of generating long molecular dynamics simulations, generative machine learning methods such as normalizing flows have been…

Machine Learning · Computer Science 2024-08-06 Henrik Schopmans , Pascal Friederich

Using normalizing flows and reweighting, Boltzmann Generators enable equilibrium sampling from a Boltzmann distribution, defined by an energy function and thermodynamic state. In this work, we introduce Thermodynamic Interpolation (TI),…

Chemical Physics · Physics 2024-11-18 Selma Moqvist , Weilong Chen , Mathias Schreiner , Feliks Nüske , Simon Olsson

Normalizing flows can generate complex target distributions and thus show promise in many applications in Bayesian statistics as an alternative or complement to MCMC for sampling posteriors. Since no data set from the target posterior…

Machine Learning · Statistics 2021-07-19 Marylou Gabrié , Grant M. Rotskoff , Eric Vanden-Eijnden

Approximating probability distributions can be a challenging task, particularly when they are supported over regions of high geometrical complexity or exhibit multiple modes. Annealing can be used to facilitate this task which is often…

Computation · Statistics 2022-02-03 Emma R. Cobian , Jonathan D. Hauenstein , Fang Liu , Daniele E. Schiavazzi

The accurate prediction of phase diagrams is of central importance for both the fundamental understanding of materials as well as for technological applications in material sciences. However, the computational prediction of the relative…

Statistical Mechanics · Physics 2024-11-26 Maximilian Schebek , Michele Invernizzi , Frank Noé , Jutta Rogal

We propose a scheme to calibrate the internal parameters of a quantum annealer to obtain well-approximated samples for training a restricted Boltzmann machine (RBM). Empirically, samples from quantum annealers obey the Boltzmann…

Quantum Physics · Physics 2025-02-18 Takeru Goto , Masayuki Ohzeki

Restricted Boltzmann Machine (RBM) is a bipartite graphical model that is used as the building block in energy-based deep generative models. Due to numerical stability and quantifiability of the likelihood, RBM is commonly used with…

Machine Learning · Statistics 2016-11-15 Chun-Liang Li , Siamak Ravanbakhsh , Barnabas Poczos

Boltzmann machine is a powerful tool for modeling probability distributions that govern the training data. A thermal equilibrium state is typically used for Boltzmann machine learning to obtain a suitable probability distribution. The…

Sampling physical systems with rough energy landscapes is hindered by rare events and metastable trapping. While Boltzmann generators already offer a solution, their reliance on the reverse Kullback--Leibler divergence frequently induces…

Machine Learning · Computer Science 2026-04-08 Guang Lin , Christian Moya , Di Qi , Xuda Ye

Boltzmann sampling is a central component of many computational frameworks, including numerous algorithms in machine learning. Although quantum annealers have been investigated as potential fast Boltzmann samplers, their dependence on…

Statistical Mechanics · Physics 2026-04-15 Ju-Yeon Gyhm , Gilhan Kim , Hyukjoon Kwon , Yongjoo Baek

We propose a generative, end-to-end solver for black-box combinatorial optimization that emphasizes both sample efficiency and solution quality on NP problems. Drawing inspiration from annealing-based algorithms, we treat the black-box…

Machine Learning · Computer Science 2025-08-07 Yuan-Hang Zhang , Massimiliano Di Ventra

Sampling from a Boltzmann distribution is NP-hard and so requires heuristic approaches. Quantum annealing is one promising candidate. The failure of annealing dynamics to equilibrate on practical time scales is a well understood limitation,…

Quantum Physics · Physics 2017-08-28 Jack Raymond , Sheir Yarkoni , Evgeny Andriyash

Our method proposes the efficient generation of samples from an unnormalized Boltzmann density by solving the underlying continuity equation in the low-rank tensor train (TT) format. It is based on the annealing path commonly used in MCMC…

Machine Learning · Computer Science 2024-12-11 Paul Hagemann , Janina Schütte , David Sommer , Martin Eigel , Gabriele Steidl

Boltzmann machine is a powerful machine learning model with many real-world applications, for example by constructing deep belief networks. Statistical inference on a Boltzmann machine can be carried out by sampling from its posterior…

Quantum Physics · Physics 2023-11-23 Mārtiņš Kālis , Andris Locāns , Rolands Šikovs , Hassan Naseri , Andris Ambainis

Sampling from unnormalized target distributions, e.g.\ Boltzmann distributions $\mu_{\text{target}}(x) \propto \exp(-E(x)/T)$, is fundamental to many scientific applications yet computationally challenging due to complex, high-dimensional…

Machine Learning · Statistics 2026-04-22 Niclas Dern , Lennart Redl , Sebastian Pfister , Marcel Kollovieh , David Lüdke , Stephan Günnemann

The design of effective cooling strategies is a crucial component in simulated annealing algorithms based on the Metropolis method. Traditionally, this is achieved through inverse logarithmic decays of the temperature to ensure convergence…

Optimization and Control · Mathematics 2025-12-16 Frédéric Blondeel , Lorenzo Pareschi , Giovanni Samaey

An increase in the efficiency of sampling from Boltzmann distributions would have a significant impact on deep learning and other machine-learning applications. Recently, quantum annealers have been proposed as a potential candidate to…

Quantum Physics · Physics 2016-08-17 Marcello Benedetti , John Realpe-Gómez , Rupak Biswas , Alejandro Perdomo-Ortiz