English
Related papers

Related papers: Cauchy Annealing Schedule: An Annealing Schedule f…

200 papers

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…

The inverse Potts problem for estimating evolutionary single-site fields and pairwise couplings in homologous protein sequences from their single-site and pairwise amino acid frequencies observed in their multiple sequence alignment would…

Biomolecules · Quantitative Biology 2026-04-21 Sanzo Miyazawa

Efficient sampling from the Boltzmann distribution given its energy function is a key challenge for modeling complex physical systems such as molecules. Boltzmann Generators address this problem by leveraging continuous normalizing flows to…

Machine Learning · Computer Science 2025-10-17 Rishal Aggarwal , Jacky Chen , Nicholas M. Boffi , David Ryan Koes

We develop the Cauchy theory of the spatially homogeneous inelastic Boltzmann equation for hard spheres, for a general form of collision rate which includes in particular variable restitution coefficients depending on the kinetic energy and…

Analysis of PDEs · Mathematics 2016-08-16 Stéphane Mischler , Clément Mouhot , Mariano Rodriguez Ricard

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

Efficient sampling of unnormalized probability densities such as the Boltzmann distribution of molecular systems is a longstanding challenge. Next to conventional approaches like molecular dynamics or Markov chain Monte Carlo, variational…

Machine Learning · Computer Science 2025-06-18 Henrik Schopmans , Pascal Friederich

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

Particle based optimization algorithms have recently been developed as sampling methods that iteratively update a set of particles to approximate a target distribution. In particular Stein variational gradient descent has gained attention…

Machine Learning · Computer Science 2021-03-19 Francesco D'Angelo , Vincent Fortuin

Energy-based models provide a natural bridge between statistical physics and machine learning by representing data through structured energy landscapes. Boltzmann machines are a particularly compelling class of such models for capturing…

Quantum Physics · Physics 2026-05-19 Gilhan Kim , Daniel K. Park

We empirically evaluate a stochastic annealing strategy for Bayesian posterior optimization with variational inference. Variational inference is a deterministic approach to approximate posterior inference in Bayesian models in which a…

Machine Learning · Statistics 2015-05-26 San Gultekin , Aonan Zhang , John Paisley

Feature selection is a technique in statistical prediction modeling that identifies features in a record with a strong statistical connection to the target variable. Excluding features with a weak statistical connection to the target…

Quantum Physics · Physics 2025-11-07 Andrew Vlasic , Hunter Grant , Salvatore Certo

A Boltzmann machine whose effective "temperature" can be dynamically "cooled" provides a stochastic neural network realization of simulated annealing, which is an important metaheuristic for solving combinatorial or global optimization…

Emerging Technologies · Computer Science 2019-05-16 Tong Wu , Huan Zhao , Fanxin Liu , Jing Guo , Han Wang

Quantum annealing (QA) is a hardware-based heuristic optimization and sampling method applicable to discrete undirected graphical models. While similar to simulated annealing, QA relies on quantum, rather than thermal, effects to explore…

The paper focuses on the a posteriori tuning of a generative model in order to favor the generation of good instances in the sense of some external differentiable criterion. The proposed approach, called Boltzmann Tuning of Generative…

Artificial Intelligence · Computer Science 2021-04-13 Victor Berger , Michele Sebag

Population annealing is an efficient sequential Monte Carlo algorithm for simulating equilibrium states of systems with rough free energy landscapes. The theory of population annealing is presented, and systematic and statistical errors are…

Disordered Systems and Neural Networks · Physics 2015-12-21 Wenlong Wang , Jonathan Machta , Helmut G. Katzgraber

By contrasting the performance of two quantum annealers operating at different temperatures, we address recent questions related to the role of temperature in these devices and their function as `Boltzmann samplers'. Using a method to…

Quantum Physics · Physics 2018-01-03 Jeffrey Marshall , Eleanor G. Rieffel , Itay Hen

In evolutionary algorithms, the fitness of a population increases with time by mutating and recombining individuals and by a biased selection of more fit individuals. The right selection pressure is critical in ensuring sufficient…

Artificial Intelligence · Computer Science 2007-05-23 Marcus Hutter

The annealing schedule is optimized for a parameter in the Lechner-Hauke-Zoller (LHZ) scheme for quantum annealing designed for the all-to-all-interacting Ising model representing generic combinatorial optimization problems. We adapt the…

Quantum Physics · Physics 2021-03-02 Yuki Susa , Hidetoshi Nishimori

Population annealing is a sequential Monte Carlo scheme well-suited to simulating equilibrium states of systems with rough free energy landscapes. Here we use population annealing to study a binary mixture of hard spheres. Population…

Statistical Mechanics · Physics 2017-07-27 Jared Callaham , Jon Machta

Restricted Boltzmann machines are undirected neural networks which have been shown to be effective in many applications, including serving as initializations for training deep multi-layer neural networks. One of the main reasons for their…

Disordered Systems and Neural Networks · Physics 2016-02-11 Marylou Gabrié , Eric W. Tramel , Florent Krzakala