English
Related papers

Related papers: Generalizable Equivariant Diffusion Models for Non…

200 papers

Discretization of continuous-time diffusion processes is a widely recognized method for sampling. However, the canonical Euler Maruyama discretization of the Langevin diffusion process, referred as Unadjusted Langevin Algorithm (ULA),…

Computation · Statistics 2021-07-28 Dao Nguyen , Xin Dang , Yixin Chen

An Euler discretization of the Langevin diffusion is known to converge to the global minimizers of certain convex and non-convex optimization problems. We show that this property holds for any suitably smooth diffusion and that different…

Machine Learning · Statistics 2019-12-30 Murat A. Erdogdu , Lester Mackey , Ohad Shamir

Drawing from the theory of stochastic differential equations, we introduce a novel sampling method for known distributions and a new algorithm for diffusion generative models with unknown distributions. Our approach is inspired by the…

Statistics Theory · Mathematics 2024-07-12 Xicheng Zhang

With the advent of group equivariant convolutions in deep networks literature, spherical CNNs with $\mathsf{SO}(3)$-equivariant layers have been developed to cope with data that are samples of signals on the sphere $S^2$. One can implicitly…

Computer Vision and Pattern Recognition · Computer Science 2023-05-29 Gianfranco Cortes , Yue Yu , Robin Chen , Melissa Armstrong , David Vaillancourt , Baba C. Vemuri

Artificial neural networks (ANNs) are typically highly nonlinear systems which are finely tuned via the optimization of their associated, non-convex loss functions. In many cases, the gradient of any such loss function has superlinear…

Machine Learning · Computer Science 2023-01-18 Attila Lovas , Iosif Lytras , Miklós Rásonyi , Sotirios Sabanis

The principle of equivariance to symmetry transformations enables a theoretically grounded approach to neural network architecture design. Equivariant networks have shown excellent performance and data efficiency on vision and medical…

Machine Learning · Computer Science 2019-05-15 Taco S. Cohen , Maurice Weiler , Berkay Kicanaoglu , Max Welling

An Algorithm is proposed for the simulation of pure SU(N) lattice gauge theories based on Genetic Algorithms(GAs). Main difference between GAs and Metropolis methods(MPs) is that GAs treat a population of points at once, while MPs treat…

High Energy Physics - Lattice · Physics 2007-05-23 Yamaguchi Azusa

We recently demonstrated that standard fixed-time lattice random-walk models cannot be modified to properly represent biased diffusion processes in more than two dimensions. The origin of this fundamental limitation appears to be the fact…

Data Analysis, Statistics and Probability · Physics 2009-11-10 Michel G. Gauthier , Gary W. Slater

We generalize the Hamiltonian Monte Carlo algorithm with a stack of neural network layers and evaluate its ability to sample from different topologies in a two dimensional lattice gauge theory. We demonstrate that our model is able to…

High Energy Physics - Lattice · Physics 2021-05-10 Sam Foreman , Xiao-Yong Jin , James C. Osborn

We develop an analytical framework for understanding how the generated distribution evolves during diffusion model training. Leveraging a Gaussian-equivalence principle, we solve the full-batch gradient-flow dynamics of linear and…

Machine Learning · Computer Science 2026-04-07 Binxu Wang , Cengiz Pehlevan

Scalar particles in the adjoint representation of a non-Abelian gauge theory play an important role in many scenarios beyond the standard model, especially of GUT type. For such theories manifestly gauge-invariant, massless, composite…

High Energy Physics - Lattice · Physics 2020-11-30 Vincenzo Afferrante , Axel Maas , Pascal Törek

We study the gauge theories on noncommutative space. We employ the idea of the covariant position to understand the linear and angular momenta, the center of mass position, and to express all gauge invariant observables including the Wilson…

High Energy Physics - Theory · Physics 2014-11-18 Dongsu Bak , Kimyeong Lee , Jeong-Hyuck Park

This study delves into the connection between machine learning and lattice field theory by linking generative diffusion models (DMs) with stochastic quantization, from a stochastic differential equation perspective. We show that DMs can be…

High Energy Physics - Lattice · Physics 2023-11-08 Lingxiao Wang , Gert Aarts , Kai Zhou

Sampling from score-based diffusion models incurs bias due to both time discretisation and the approximation of the score function. A common strategy for reducing this bias is to apply corrector steps based on the unadjusted Langevin…

Machine Learning · Statistics 2026-05-12 Kevin H. Lam , Tyler Farghly , Christopher Williams , Jun Yang , Yee Whye Teh , Arnaud Doucet

Non-abelian gauge theories play an important role in the standard model of particle physics, and unfold a partially unexplored world of exciting physical phenomena. In this letter, we suggest a realization of a non-abelian lattice gauge…

Quantum Physics · Physics 2013-03-25 Erez Zohar , J. Ignacio Cirac , Benni Reznik

We study a class of Wilsonian formulations of non-Abelian gauge theories in algebraic non-covariant gauges where the Wilsonian infrared cutoff $\Lambda$ is inserted as a mass term for the propagating fields. In this way the Ward-Takahashi…

High Energy Physics - Theory · Physics 2011-08-17 Michele Simionato

We discuss a particular lattice discretization of abelian gauge theories in arbitrary dimensions. The construction is based on gauging the center symmetry of a non-compact abelian gauge theory, which results in a Villain type action. We…

High Energy Physics - Lattice · Physics 2019-06-26 Tin Sulejmanpasic , Christof Gattringer

Machine-learned normalizing flows can be used in the context of lattice quantum field theory to generate statistically correlated ensembles of lattice gauge fields at different action parameters. This work demonstrates how these…

Conventional wisdom in the sampling literature, backed by a popular diffusion scaling limit, suggests that the mixing time of the Metropolis-Adjusted Langevin Algorithm (MALA) scales as $O(d^{1/3})$, where $d$ is the dimension. However, the…

Statistics Theory · Mathematics 2020-12-24 Sinho Chewi , Chen Lu , Kwangjun Ahn , Xiang Cheng , Thibaut Le Gouic , Philippe Rigollet

We introduce a new family of MCMC samplers that combine auxiliary variables, Gibbs sampling and Taylor expansions of the target density. Our approach permits the marginalisation over the auxiliary variables yielding marginal samplers, or…

Machine Learning · Statistics 2018-01-26 Michalis K. Titsias , Omiros Papaspiliopoulos