English
Related papers

Related papers: Deep Learning Moment Closure Approximations using …

200 papers

This paper establishes a continuous time approximation, a piece-wise continuous differential equation, for the discrete Heavy-Ball (HB) momentum method with explicit discretization error. Investigating continuous differential equations has…

Machine Learning · Computer Science 2025-10-23 Bochen Lyu , Xiaojing Zhang , Fangyi Zheng , He Wang , Zheng Wang , Zhanxing Zhu

We give a new framework for proving the existence of low-degree, polynomial approximators for Boolean functions with respect to broad classes of non-product distributions. Our proofs use techniques related to the classical moment problem…

Computational Complexity · Computer Science 2013-01-07 Adam Klivans , Raghu Meka

In this paper, we take a data-driven approach and apply machine learning to the moment closure problem for radiative transfer equation in slab geometry. Instead of learning the unclosed high order moment, we propose to directly learn the…

Numerical Analysis · Mathematics 2022-02-09 Juntao Huang , Yingda Cheng , Andrew J. Christlieb , Luke F. Roberts

We introduce a new method for training deep Boltzmann machines jointly. Prior methods of training DBMs require an initial learning pass that trains the model greedily, one layer at a time, or do not perform well on classification tasks. In…

Machine Learning · Statistics 2013-05-02 Ian J. Goodfellow , Aaron Courville , Yoshua Bengio

Many complex multiphysics systems in fluid dynamics involve using solvers with varied levels of approximations in different regions of the computational domain to resolve multiple spatiotemporal scales present in the flow. The accuracy of…

Computational Physics · Physics 2020-10-28 Suraj Pawar , Shady E. Ahmed , Omer San

Moment methods are classical approaches that approximate the mesoscopic radiative transfer equation by a system of macroscopic moment equations. An expansion in the angular variables transforms the original equation into a system of…

Mathematical Physics · Physics 2023-08-17 Martin Frank , Benjamin Seibold

This paper studies a novel approach for approximating the behavior of compartmental spreading processes. In contrast to prior work, the methods developed describe a dynamics which bound the exact moment dynamics, without explicitly…

Optimization and Control · Mathematics 2015-07-21 Nicholas J. Watkins , Cameron Nowzari , Victor M. Preciado , George J. Pappas

Conventional lattice Boltzmann models only satisfy moment isotropy up to fourth order. In order to accurately describe improtant physical effects beyond the isothermal Navier-Stokes fluid regime, higher order isotropy is required. In this…

Computational Physics · Physics 2007-09-11 Hudong Chen , Isaac Goldhrish , Steven Orszag

Restricted Boltzmann Machines (RBMs) are one of the fundamental building blocks of deep learning. Approximate maximum likelihood training of RBMs typically necessitates sampling from these models. In many training scenarios, computationally…

Machine Learning · Computer Science 2014-10-02 Guillaume Desjardins , Heng Luo , Aaron Courville , Yoshua Bengio

In this paper, we introduce a model-based deep-learning approach to solve finite-horizon continuous-time stochastic control problems with jumps. We iteratively train two neural networks: one to represent the optimal policy and the other to…

Machine Learning · Computer Science 2026-01-16 Patrick Cheridito , Jean-Loup Dupret , Donatien Hainaut

In stochastic systems, numerically sampling the relevant trajectories for the estimation of the large deviation statistics of time-extensive observables requires overcoming their exponential (in space and time) scarcity. The optimal way to…

Statistical Mechanics · Physics 2021-01-14 Tom H. E. Oakes , Adam Moss , Juan P. Garrahan

Deep learning builds deep architectures such as multi-layered artificial neural networks to effectively represent multiple features of input patterns. The adaptive structural learning method of Deep Belief Network (DBN) can realize a high…

Neural and Evolutionary Computing · Computer Science 2019-10-01 Shin Kamada , Takumi Ichimura

We trained deep neural networks (DNNs) as a function of the neutrino energy density, flux, and the fluid velocity to reproduce the Eddington tensor for neutrinos obtained in our first-principles core-collapse supernova (CCSN) simulations.…

High Energy Astrophysical Phenomena · Physics 2022-02-09 Akira Harada , Shota Nishikawa , Shoichi Yamada

Computing equilibrium states in condensed-matter many-body systems, such as solvated proteins, is a long-standing challenge. Lacking methods for generating statistically independent equilibrium samples in "one shot", vast computational…

Machine Learning · Statistics 2019-07-15 Frank Noé , Simon Olsson , Jonas Köhler , Hao Wu

The deep extension of the restricted Boltzmann machine (RBM), known as the deep Boltzmann machine (DBM), is an expressive family of machine learning models which can serve as compact representations of complex probability distributions.…

Machine Learning · Computer Science 2021-02-18 Haik Manukian , Massimiliano Di Ventra

In this work, we propose a new deep learning-based scheme for solving high dimensional nonlinear backward stochastic differential equations (BSDEs). The idea is to reformulate the problem as a global optimization, where the local loss…

Numerical Analysis · Mathematics 2024-04-18 Lorenc Kapllani , Long Teng

Restricted Boltzmann machines (RBMs) and their extensions, called 'deep-belief networks', are powerful neural networks that have found applications in the fields of machine learning and artificial intelligence. The standard way to training…

Machine Learning · Computer Science 2018-10-25 Haik Manukian , Fabio L. Traversa , Massimiliano Di Ventra

Moment approximation methods are gaining increasing attention for their use in the approximation of the stochastic kinetics of chemical reaction systems. In this paper we derive a general moment expansion method for any type of propensities…

Molecular Networks · Quantitative Biology 2015-06-15 Angelique Ale , Paul Kirk , Michael P. P. Stumpf

Spectral methods of moments provide a powerful tool for learning the parameters of latent variable models. Despite their theoretical appeal, the applicability of these methods to real data is still limited due to a lack of robustness to…

Machine Learning · Statistics 2018-10-18 Matteo Ruffini , Guillaume Rabusseau , Borja Balle

Deep Boltzmann machines are in principle powerful models for extracting the hierarchical structure of data. Unfortunately, attempts to train layers jointly (without greedy layer-wise pretraining) have been largely unsuccessful. We propose a…

Machine Learning · Statistics 2012-12-19 Grégoire Montavon , Klaus-Robert Müller