English
Related papers

Related papers: Statistical Learning Guarantees for Group-Invarian…

200 papers

Generative data augmentation, which scales datasets by obtaining fake labeled examples from a trained conditional generative model, boosts classification performance in various learning tasks including (semi-)supervised learning, few-shot…

Machine Learning · Computer Science 2023-05-30 Chenyu Zheng , Guoqiang Wu , Chongxuan Li

The introduction of convolutional layers greatly advanced the performance of neural networks on image tasks due to innately capturing a way of encoding and learning translation-invariant operations, matching one of the underlying symmetries…

Computer Vision and Pattern Recognition · Computer Science 2016-12-15 Nicholas Guttenberg , Nathaniel Virgo , Olaf Witkowski , Hidetoshi Aoki , Ryota Kanai

Natural gradient descent has a remarkable property that in the small learning rate limit, it displays an invariance with respect to network reparameterizations, leading to robust training behavior even for highly covariant network…

Machine Learning · Statistics 2023-12-11 Christian Goodbrake

Group equivariant neural networks have proven effective in modelling a wide range of tasks where the data lives in a classical geometric space and exhibits well-defined group symmetries. However, these networks are not suitable for learning…

Machine Learning · Computer Science 2025-05-26 Edward Pearce-Crump

Despite classical statistical theory predicting severe overfitting, modern massively overparameterized neural networks still generalize well. This unexpected property is attributed to the network's so-called implicit bias, which describes…

Machine Learning · Computer Science 2025-03-14 Justin Sahs , Ryan Pyle , Fabio Anselmi , Ankit Patel

This paper analyzes the convergence and generalization of training a one-hidden-layer neural network when the input features follow the Gaussian mixture model consisting of a finite number of Gaussian distributions. Assuming the labels are…

Machine Learning · Computer Science 2023-01-30 Hongkang Li , Shuai Zhang , Meng Wang

Convolutional neural networks often dominate fully-connected counterparts in generalization performance, especially on image classification tasks. This is often explained in terms of 'better inductive bias'. However, this has not been made…

Machine Learning · Computer Science 2021-05-05 Zhiyuan Li , Yi Zhang , Sanjeev Arora

In this paper we develop a co-induction operation which transforms an invariant random subgroup of a group into an invariant random subgroup of a larger group. We use this operation to construct new continuum size families of non-atomic,…

Logic · Mathematics 2019-03-18 Alexander S. Kechris , Vibeke Quorning

Recent work has shown deep learning can accelerate the prediction of physical dynamics relative to numerical solvers. However, limited physical accuracy and an inability to generalize under distributional shift limit its applicability to…

Machine Learning · Computer Science 2021-03-17 Rui Wang , Robin Walters , Rose Yu

Implicit generative models have the capability to learn arbitrary complex data distributions. On the downside, training requires telling apart real data from artificially-generated ones using adversarial discriminators, leading to unstable…

Machine Learning · Computer Science 2024-02-27 José Manuel de Frutos , Pablo M. Olmos , Manuel A. Vázquez , Joaquín Míguez

For a compact subgroup $G$ of the group of isometries acting on a Riemannian manifold $M$ we investigate subspaces of Besov and Triebel-Lizorkin type which are invariant with respect to the group action. Our main aim is to extend the…

Functional Analysis · Mathematics 2018-03-15 Nadine Große , Cornelia Schneider

We study the statistical-computational trade-offs for learning with exact invariances (or symmetries) using kernel regression. Traditional methods, such as data augmentation, group averaging, canonicalization, and frame-averaging, either…

Machine Learning · Computer Science 2026-02-05 Ashkan Soleymani , Behrooz Tahmasebi , Stefanie Jegelka , Patrick Jaillet

We present a method for estimating the maximal symmetry of a continuous regression function. Knowledge of such a symmetry can be used to significantly improve modelling by removing the modes of variation resulting from the symmetries.…

Methodology · Statistics 2023-12-21 Louis G. Christie , John A. D. Aston

Approximate Bayesian inference for neural networks is considered a robust alternative to standard training, often providing good performance on out-of-distribution data. However, Bayesian neural networks (BNNs) with high-fidelity…

Machine Learning · Computer Science 2021-12-07 Pavel Izmailov , Patrick Nicholson , Sanae Lotfi , Andrew Gordon Wilson

Model reparametrization, which follows the change-of-variable rule of calculus, is a popular way to improve the training of neural nets. But it can also be problematic since it can induce inconsistencies in, e.g., Hessian-based flatness…

Machine Learning · Computer Science 2023-10-24 Agustinus Kristiadi , Felix Dangel , Philipp Hennig

Group equivariant convolutional neural networks (G-CNNs) are generalizations of convolutional neural networks (CNNs) which excel in a wide range of technical applications by explicitly encoding symmetries, such as rotations and…

Machine Learning · Computer Science 2022-09-14 Hannah Lawrence , Kristian Georgiev , Andrew Dienes , Bobak T. Kiani

In fair machine learning, one source of performance disparities between groups is over-fitting to groups with relatively few training samples. We derive group-specific bounds on the generalization error of welfare-centric fair machine…

Machine Learning · Computer Science 2024-03-01 Cyrus Cousins , I. Elizabeth Kumar , Suresh Venkatasubramanian

We study the problem of learning equivariant neural networks via gradient descent. The incorporation of known symmetries ("equivariance") into neural nets has empirically improved the performance of learning pipelines, in domains ranging…

Machine Learning · Computer Science 2024-01-04 Bobak T. Kiani , Thien Le , Hannah Lawrence , Stefanie Jegelka , Melanie Weber

Learning invariant representations is a critical task in computer vision. In this paper, we propose the Theta-Restricted Boltzmann Machine ({\theta}-RBM in short), which builds upon the original RBM formulation and injects the notion of…

Computer Vision and Pattern Recognition · Computer Science 2016-06-30 Mario Valerio Giuffrida , Sotirios A. Tsaftaris

Recently, metric learning and similarity learning have attracted a large amount of interest. Many models and optimisation algorithms have been proposed. However, there is relatively little work on the generalization analysis of such…

Machine Learning · Computer Science 2013-03-19 Qiong Cao , Zheng-Chu Guo , Yiming Ying