English
Related papers

Related papers: Deep Learning Beyond Lefschetz Thimbles

200 papers

Pre-training is crucial for learning deep neural networks. Most of existing pre-training methods train simple models (e.g., restricted Boltzmann machines) and then stack them layer by layer to form the deep structure. This layer-wise…

Machine Learning · Computer Science 2015-06-09 Zhiyuan Tang , Dong Wang , Yiqiao Pan , Zhiyong Zhang

Machine learning algorithms relying on deep neural networks recently allowed a great leap forward in artificial intelligence. Despite the popularity of their applications, the efficiency of these algorithms remains largely unexplained from…

Disordered Systems and Neural Networks · Physics 2020-03-24 Marylou Gabrié

In this work, we study the approximation of expected values of functional quantities on the solution of a stochastic differential equation (SDE), where we replace the Monte Carlo estimation with the evaluation of a deep neural network. Once…

Numerical Analysis · Mathematics 2021-02-18 Thomas Gerstner , Bastian Harrach , Daniel Roth , Martin Simon

The so-called trivializing flows were proposed to speed up Hybrid Monte Carlo simulations, where the Wilson flow was used as an approximation of a trivializing map, a transformation of the gauge fields which trivializes the theory. It was…

High Energy Physics - Lattice · Physics 2023-10-06 David Albandea , Luigi Del Debbio , Pilar Hernández , Richard Kenway , Joe Marsh Rossney , Alberto Ramos

Deep learning (DL) has shown unprecedented performance for many image analysis and image enhancement tasks. Yet, solving large-scale inverse problems like tomographic reconstruction remains challenging for DL. These problems involve…

Medical Physics · Physics 2019-12-18 Lin Fu , Bruno De Man

While machine learning (ML) has found multiple applications in photonics, traditional "black box" ML models typically require prohibitively large training data sets. Generation of such data, as well as the training processes themselves,…

The recent introduction of machine learning techniques, especially normalizing flows, for the sampling of lattice gauge theories has shed some hope on improving the sampling efficiency of the traditional HMC algorithm. Naive use of…

High Energy Physics - Lattice · Physics 2022-12-06 David Albandea , Luigi Del Debbio , Pilar Hernández , Richard Kenway , Joe Marsh Rossney , Alberto Ramos

The escalating parameter counts in modern deep learning models pose a fundamental challenge to efficient training and resolution of overfitting. We address this by introducing the \emph{Mapping Networks} which replace the high dimensional…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Lord Sen , Shyamapada Mukherjee

The field of Graph Signal Processing (GSP) has proposed tools to generalize harmonic analysis to complex domains represented through graphs. Among these tools are translations, which are required to define many others. Most works propose to…

Signal Processing · Electrical Eng. & Systems 2022-01-12 Raphael Baena , Lucas Drumetz , Vincent Gripon

We propose Riemannian Flow Matching (RFM), a simple yet powerful framework for training continuous normalizing flows on manifolds. Existing methods for generative modeling on manifolds either require expensive simulation, are inherently…

Machine Learning · Computer Science 2024-02-27 Ricky T. Q. Chen , Yaron Lipman

We review recent attempts at dealing with the sign problem in Monte Carlo calculations by deforming the region of integration in the path integral from real to complex fields. We discuss the theoretical foundations, the algorithmic issues…

High Energy Physics - Lattice · Physics 2018-04-18 Paulo F. Bedaque

Graph Neural Networks (GNNs) have become a central tool for learning on graph-structured data, yet their applicability to real-world systems remains limited by key challenges such as scalability, temporality, directionality, data…

Machine Learning · Computer Science 2025-10-28 Emanuele Rossi

Machine learning (ML) is revolutionizing the world, affecting almost every field of science and industry. Recent algorithms (in particular, deep networks) are increasingly data-hungry, requiring large datasets for training. Thus, the…

Machine Learning · Computer Science 2022-11-16 Chen Shani , Jonathan Zarecki , Dafna Shahaf

In this article we consider Bayesian inference associated to deep neural networks (DNNs) and in particular, trace-class neural network (TNN) priors which can be preferable to traditional DNNs as (a) they are identifiable and (b) they…

Computation · Statistics 2025-05-06 Neil K. Chada , Ajay Jasra , Kody J. H. Law , Sumeetpal S. Singh

Though the deep learning is pushing the machine learning to a new stage, basic theories of machine learning are still limited. The principle of learning, the role of the a prior knowledge, the role of neuron bias, and the basis for choosing…

Machine Learning · Statistics 2017-04-25 Hong Zhao

Multiresolution Matrix Factorization (MMF) is unusual amongst fast matrix factorization algorithms in that it does not make a low rank assumption. This makes MMF especially well suited to modeling certain types of graphs with complex…

Machine Learning · Computer Science 2024-08-20 Truong Son Hy , Thieu Khang , Risi Kondor

A neural network is a powerful tool that can uncover hidden laws beyond human intuition. However, it often appears as a black box due to its complicated nonlinear structures. By drawing upon the Gutzwiller mean-field theory, we can showcase…

Strongly Correlated Electrons · Physics 2023-12-25 Jin Cao , Shijie Hu , Zhiping Yin , Ke Xia

The numerical sign problem remains one of the central challenges in computational physics. The Worldvolume Hybrid Monte Carlo (WV-HMC) method has recently been proposed as a reliable and computationally efficient algorithm that crucially…

High Energy Physics - Lattice · Physics 2026-03-31 Masafumi Fukuma

We present an introduction to model-based machine learning for communication systems. We begin by reviewing existing strategies for combining model-based algorithms and machine learning from a high level perspective, and compare them to the…

Signal Processing · Electrical Eng. & Systems 2021-01-14 Nir Shlezinger , Nariman Farsad , Yonina C. Eldar , Andrea J. Goldsmith

Fueled by the expressive power of deep neural networks, normalizing flows have achieved spectacular success in generative modeling, or learning to draw new samples from a distribution given a finite dataset of training samples. Normalizing…

Machine Learning · Computer Science 2023-05-05 Yuehaw Khoo , Michael Lindsey , Hongli Zhao