English
Related papers

Related papers: Rate-Regularization and Generalization in VAEs

200 papers

We study strategic Gaussian semantic compression under rate and compute constraints, where an encoder and decoder optimize distinct quadratic objectives. A latent Gaussian state generates a task dependent semantic variable, and the decoder…

Information Theory · Computer Science 2026-02-05 Emrah Akyol

Variational autoencoders (VAEs) face a notorious problem wherein the variational posterior often aligns closely with the prior, a phenomenon known as posterior collapse, which hinders the quality of representation learning. To mitigate this…

Machine Learning · Statistics 2023-10-25 Yuma Ichikawa , Koji Hukushima

Data augmentation is used in machine learning to make the classifier invariant to label-preserving transformations. Usually this invariance is only encouraged implicitly by including a single augmented input during training. However,…

Machine Learning · Computer Science 2022-03-08 Aleksander Botev , Matthias Bauer , Soham De

Variational Autoencoder (VAE) is widely used as a generative model to approximate a model's posterior on latent variables by combining the amortized variational inference and deep neural networks. However, when paired with strong…

Machine Learning · Computer Science 2020-06-02 Qile Zhu , Jianlin Su , Wei Bi , Xiaojiang Liu , Xiyao Ma , Xiaolin Li , Dapeng Wu

In this paper, we consider variational autoencoders (VAE) for general state space models. We consider a backward factorization of the variational distributions to analyze the excess risk associated with VAE. Such backward factorizations…

Methodology · Statistics 2023-12-18 Élisabeth Gassiat , Sylvain Le Corff

Even though Variational Autoencoders (VAEs) are widely used for semi-supervised learning, the reason why they work remains unclear. In fact, the addition of the unsupervised objective is most often vaguely described as a regularization. The…

Machine Learning · Computer Science 2020-10-15 Ghazi Felhi , Joseph Leroux , Djamé Seddah

To analyze high-dimensional and complex data in the real world, deep generative models, such as variational autoencoder (VAE) embed data in a low-dimensional space (latent space) and learn a probabilistic model in the latent space. However,…

Machine Learning · Computer Science 2020-09-01 Keizo Kato , Jing Zhou , Tomotake Sasaki , Akira Nakagawa

We investigate information-theoretic limits and design of communication under receiver quantization. Unlike most existing studies, this work is more focused on the impact of resolution reduction from high to low. We consider a standard…

Information Theory · Computer Science 2025-12-29 Jing Zhou , Shuqin Pang , Wenyi Zhang

Sparse Autoencoders (SAEs) that can accurately reconstruct their input (minimizing distortion) by making efficient use of few features (minimizing the rate) often fail to learn monosemantic representations (highly interpretable), limiting…

Machine Learning · Computer Science 2026-05-15 Tommaso Mencattini , Francesco Montagna , Francesco Locatello

We consider the problem of learning Variational Autoencoders (VAEs), i.e., a type of deep generative model, from data with missing values. Such data is omnipresent in real-world applications of machine learning because complete data is…

Machine Learning · Computer Science 2023-10-26 Timur Sudak , Sebastian Tschiatschek

This paper is concerned with a rate-distortion theory for sequences of i.i.d. random variables with general distribution supported on general sets including manifolds and fractal sets. Manifold structures are prevalent in data science,…

Information Theory · Computer Science 2018-04-25 Erwin Riegler , Günther Koliander , Helmut Bölcskei

We study a variant of the variational autoencoder model (VAE) with a Gaussian mixture as a prior distribution, with the goal of performing unsupervised clustering through deep generative models. We observe that the known problem of…

A big mystery in deep learning continues to be the ability of methods to generalize when the number of model parameters is larger than the number of training examples. In this work, we take a step towards a better understanding of the…

Machine Learning · Computer Science 2021-11-25 Romain Cosentino , Randall Balestriero , Richard Baraniuk , Behnaam Aazhang

Classical rate-distortion theory requires knowledge of an elusive source distribution. Instead, we analyze rate-distortion properties of individual objects using the recently developed algorithmic rate-distortion theory. The latter is based…

Information Theory · Computer Science 2007-07-16 Steven de Rooij , Paul Vitanyi

We examine the coordinated and universal rate-efficient sampling of a subset of correlated discrete memoryless sources followed by lossy compression of the sampled sources. The goal is to reconstruct a predesignated subset of sources within…

Information Theory · Computer Science 2017-06-23 Vinay Praneeth Boda , Prakash Narayan

This survey articles focuses on emerging connections between the fields of machine learning and data compression. While fundamental limits of classical (lossy) data compression are established using rate-distortion theory, the connections…

Information Theory · Computer Science 2024-06-17 Jun Chen , Yong Fang , Ashish Khisti , Ayfer Ozgur , Nir Shlezinger , Chao Tian

Variational Autoencoders (VAEs) provide a theoretically-backed and popular framework for deep generative models. However, learning a VAE from data poses still unanswered theoretical questions and considerable practical challenges. In this…

Machine Learning · Computer Science 2020-06-01 Partha Ghosh , Mehdi S. M. Sajjadi , Antonio Vergari , Michael Black , Bernhard Schölkopf

I proposed rate tolerance and discussed its relation to rate distortion in my book "A Generalized Information Theory" published in 1993. Recently, I examined the structure function and the complexity distortion based on Kolmogorov's…

Information Theory · Computer Science 2012-04-18 Chenguang Lu

While the impact of variational inference (VI) on posterior inference in a fixed generative model is well-characterized, its role in regularizing a learned generative model when used in variational autoencoders (VAEs) is poorly understood.…

Machine Learning · Computer Science 2021-01-01 Abhishek Kumar , Ben Poole

This paper investigates the use of regularization priors in the context of treatment effect estimation using observational data where the number of control variables is large relative to the number of observations. First, the phenomenon of…

Methodology · Statistics 2016-12-30 P. Richard Hahn , Carlos M. Carvalho , Jingyu He , David Puelz