English
Related papers

Related papers: Matricial Free Energy as a Gaussianizing Regulariz…

200 papers

We present a new method to renormalize stochastic differential equations subjected to multiplicative noise. The method is based on the widely used concept of effective potential in high energy physics, and has already been successfully…

Statistical Mechanics · Physics 2020-12-29 Jean-Sebastien Gagnon , David Hochberg , Juan Perez-Mercader

Autoencoders are a popular model in many branches of machine learning and lossy data compression. However, their fundamental limits, the performance of gradient methods and the features learnt during optimization remain poorly understood,…

Machine Learning · Computer Science 2023-01-12 Alexander Shevchenko , Kevin Kögler , Hamed Hassani , Marco Mondelli

The variational autoencoder is a well defined deep generative model that utilizes an encoder-decoder framework where an encoding neural network outputs a non-deterministic code for reconstructing an input. The encoder achieves this by…

Machine Learning · Computer Science 2021-09-23 Amur Ghose , Abdullah Rashwan , Pascal Poupart

We propose a novel regularization loss that enforces standard Gaussianity, encouraging samples to align with a standard Gaussian distribution. This facilitates a range of downstream tasks involving optimization in the latent space of…

Computer Vision and Pattern Recognition · Computer Science 2025-09-19 Jisung Hwang , Jaihoon Kim , Minhyuk Sung

We consider the problem of estimating a low-rank matrix from a noisy observed matrix. Previous work has shown that the optimal method depends crucially on the choice of loss function. In this paper, we use a family of weighted loss…

Statistics Theory · Mathematics 2021-04-08 William Leeb

In this PhD thesis, we explore and apply methods inspired by the free energy principle to two important areas in machine learning and neuroscience. The free energy principle is a general mathematical theory of the necessary…

Artificial Intelligence · Computer Science 2021-08-31 Beren Millidge

Deep generative models such as GANs, normalizing flows, and diffusion models are powerful regularizers for inverse problems. They exhibit great potential for helping reduce ill-posedness and attain high-quality results. However, the latent…

Computer Vision and Pattern Recognition · Computer Science 2024-07-30 Dongzhuo Li

Gaussian graphical models are of great interest in statistical learning. Because the conditional independencies between different nodes correspond to zero entries in the inverse covariance matrix of the Gaussian distribution, one can learn…

Machine Learning · Computer Science 2010-11-02 Katya Scheinberg , Shiqian Ma , Donald Goldfarb

Among other uses, neural networks are a powerful tool for solving deterministic and Bayesian inverse problems in real-time, where variational autoencoders, a specialized type of neural network, enable the Bayesian estimation of model…

Machine Learning · Computer Science 2025-09-25 Andrea Tonini , Luca Dede'

Auto-Encoders are unsupervised models that aim to learn patterns from observed data by minimizing a reconstruction cost. The useful representations learned are often found to be sparse and distributed. On the other hand, compressed sensing…

Machine Learning · Statistics 2017-07-14 Devansh Arpit , Yingbo Zhou , Hung Q. Ngo , Nils Napp , Venu Govindaraju

We introduce two new particle-based algorithms for learning latent variable models via marginal maximum likelihood estimation, including one which is entirely tuning-free. Our methods are based on the perspective of marginal maximum…

Machine Learning · Statistics 2024-03-04 Louis Sharrock , Daniel Dodd , Christopher Nemeth

We propose Energy-based generator matching (EGM), a modality-agnostic approach to train generative models from energy functions in the absence of data. Extending the recently proposed generator matching, EGM enables training of arbitrary…

Machine Learning · Computer Science 2025-11-20 Dongyeop Woo , Minsu Kim , Minkyu Kim , Kiyoung Seong , Sungsoo Ahn

Trajectory optimization using a learned model of the environment is one of the core elements of model-based reinforcement learning. This procedure often suffers from exploiting inaccuracies of the learned model. We propose to regularize…

Machine Learning · Computer Science 2019-12-30 Rinu Boney , Norman Di Palo , Mathias Berglund , Alexander Ilin , Juho Kannala , Antti Rasmus , Harri Valpola

Random matrices tend to be well conditioned, and we employ this well known property to advance matrix computations. We prove that our algorithms employing Gaussian random matrices are efficient, but in our tests the algorithms have…

Numerical Analysis · Mathematics 2012-10-30 Victor Y. Pan , Guoliang Qian , Ai-Long Zheng

The Gaussianity assumption has been consistently criticized as a main limitation of the Variational Autoencoder (VAE) despite its efficiency in computational modeling. In this paper, we propose a new approach that expands the model capacity…

Machine Learning · Statistics 2023-10-30 Seunghwan An , Jong-June Jeon

The smallest singular value and condition number play important roles in numerical linear algebra and the analysis of algorithms. In numerical analysis with randomness, many previous works make Gaussian assumptions, which are not general…

Probability · Mathematics 2022-11-09 Haoyu Wang

Compression is at the heart of effective representation learning. However, lossy compression is typically achieved through simple parametric models like Gaussian noise to preserve analytic tractability, and the limitations this imposes on…

Machine Learning · Computer Science 2019-11-15 Rob Brekelmans , Daniel Moyer , Aram Galstyan , Greg Ver Steeg

We study the asymmetric matrix factorization problem under a natural nonconvex formulation with arbitrary overparametrization. The model-free setting is considered, with minimal assumption on the rank or singular values of the observed…

Machine Learning · Computer Science 2023-08-22 Liwei Jiang , Yudong Chen , Lijun Ding

Autoencoders are popular among neural-network-based matrix completion models due to their ability to retrieve potential latent factors from the partially observed matrices. Nevertheless, when training data is scarce their performance is…

Machine Learning · Computer Science 2018-07-06 Duc Minh Nguyen , Evaggelia Tsiligianni , Robert Calderbank , Nikos Deligiannis

Latent Gaussian models have a rich history in statistics and machine learning, with applications ranging from factor analysis to compressed sensing to time series analysis. The classical method for maximizing the likelihood of these models…

Machine Learning · Computer Science 2023-06-07 Alexander Lin , Bahareh Tolooshams , Yves Atchadé , Demba Ba