English
Related papers

Related papers: Rate-Regularization and Generalization in VAEs

200 papers

Despite the increasing relevance of forecasting methods, causal implications of these algorithms remain largely unexplored. This is concerning considering that, even under simplifying assumptions such as causal sufficiency, the statistical…

The framework of variational autoencoders (VAEs) provides a principled method for jointly learning latent-variable models and corresponding inference models. However, the main drawback of this approach is the blurriness of the generated…

Machine Learning · Computer Science 2020-07-01 Ioannis Gatopoulos , Maarten Stol , Jakub M. Tomczak

We provide universality results that quantify how data augmentation affects the variance and limiting distribution of estimates through simple surrogates, and analyze several specific models in detail. The results confirm some observations…

Machine Learning · Computer Science 2025-12-03 Kevin Han Huang , Peter Orbanz , Morgane Austern

We examine the relationship between the mutual information between the output model and the empirical sample and the generalization of the algorithm in the context of stochastic convex optimization. Despite increasing interest in…

Machine Learning · Computer Science 2024-01-17 Roi Livni

In recent years, the compression of large language models (LLMs) has emerged as a key problem in facilitating LLM deployment on resource-limited devices, reducing compute costs, and mitigating the environmental footprint due to large-scale…

Machine Learning · Computer Science 2025-05-07 Sean I. Young

Modern neural networks are highly overparameterized, with capacity to substantially overfit to training data. Nevertheless, these networks often generalize well in practice. It has also been observed that trained networks can often be…

Machine Learning · Statistics 2019-02-26 Wenda Zhou , Victor Veitch , Morgane Austern , Ryan P. Adams , Peter Orbanz

The Variational Autoencoder (VAE) is a popular and powerful model applied to text modelling to generate diverse sentences. However, an issue known as posterior collapse (or KL loss vanishing) happens when the VAE is used in text modelling,…

Computation and Language · Computer Science 2020-11-04 Ruizhe Li , Xiao Li , Guanyi Chen , Chenghua Lin

Deep neural networks have long been criticized for being black-box. To unveil the inner workings of modern neural architectures, a recent work \cite{yu2024white} proposed an information-theoretic objective function called Sparse Rate…

Machine Learning · Computer Science 2024-11-27 Yunzhe Hu , Difan Zou , Dong Xu

We explain why directly changing the prior can be a surprisingly ineffective mechanism for incorporating inductive biases into VAEs, and introduce a simple and effective alternative approach: Intermediary Latent Space VAEs(InteL-VAEs).…

Machine Learning · Statistics 2022-02-16 Ning Miao , Emile Mathieu , N. Siddharth , Yee Whye Teh , Tom Rainforth

Efficient channel state information (CSI) compression at the user equipment plays a key role in enabling accurate channel reconstruction and precoder design in massive multiple-input multiple-output systems. A key challenge lies in…

Information Theory · Computer Science 2026-02-04 Xi Chen , Homa Esfahanizadeh , Foad Sohrabi

We give a novel, unified derivation of conditional PAC-Bayesian and mutual information (MI) generalization bounds. We derive conditional MI bounds as an instance, with special choice of prior, of conditional MAC-Bayesian (Mean Approximately…

Machine Learning · Computer Science 2021-06-18 Peter Grünwald , Thomas Steinke , Lydia Zakynthinou

Variational autoencoders (VAEs) are one class of generative probabilistic latent-variable models designed for inference based on known data. They balance reconstruction and regularizer terms. A variational approximation produces an evidence…

Machine Learning · Statistics 2023-12-13 Robert I. Cukier

Estimating the Generalization Error (GE) of Deep Neural Networks (DNNs) is an important task that often relies on availability of held-out data. The ability to better predict GE based on a single training set may yield overarching DNN…

Machine Learning · Computer Science 2022-07-20 Angus Galloway , Anna Golubeva , Mahmoud Salem , Mihai Nica , Yani Ioannou , Graham W. Taylor

Information-theoretic (IT) generalization bounds have been used to study the generalization of learning algorithms. These bounds are intrinsically data- and algorithm-dependent so that one can exploit the properties of data and algorithm to…

Machine Learning · Computer Science 2026-01-06 Ze Peng , Jian Zhang , Yisen Wang , Lei Qi , Yinghuan Shi , Yang Gao

We propose a novel training approach for improving the generalization in neural networks. We show that in contrast to regular constraints for orthogonality, our approach represents a {\em data-dependent} orthogonality constraint, and is…

Computer Vision and Pattern Recognition · Computer Science 2020-07-02 You Xie , Nils Thuerey

Adversarially trained models exhibit a large generalization gap: they can interpolate the training set even for large perturbation radii, but at the cost of large test error on clean samples. To investigate this gap, we decompose the test…

Machine Learning · Computer Science 2021-06-15 Yaodong Yu , Zitong Yang , Edgar Dobriban , Jacob Steinhardt , Yi Ma

Conventional prior for Variational Auto-Encoder (VAE) is a Gaussian distribution. Recent works demonstrated that choice of prior distribution affects learning capacity of VAE models. We propose a general technique…

Machine Learning · Computer Science 2018-12-10 Eugene Golikov , Maksim Kretov

A trade-off exists between reconstruction quality and the prior regularisation in the Evidence Lower Bound (ELBO) loss that Variational Autoencoder (VAE) models use for learning. There are few satisfactory approaches to deal with a balance…

Machine Learning · Computer Science 2019-09-10 Shuyu Lin , Stephen Roberts , Niki Trigoni , Ronald Clark

This report explains, implements and extends the works presented in "Tighter Variational Bounds are Not Necessarily Better" (T Rainforth et al., 2018). We provide theoretical and empirical evidence that increasing the number of importance…

Machine Learning · Statistics 2022-09-27 Amine M'Charrak , Vít Růžička , Sangyun Shin , Madhu Vankadari

We consider the semantic rate-distortion problem motivated by task-oriented video compression. The semantic information corresponding to the task, which is not observable to the encoder, shows impacts on the observations through a joint…

Information Theory · Computer Science 2022-08-15 Tao Guo , Yizhu Wang , Jie Han , Huihui Wu , Bo Bai , Wei Han