English
Related papers

Related papers: The Exact Sample Complexity Gain from Invariances …

200 papers

The use of kernels for nonlinear prediction is widespread in machine learning. They have been popularized in support vector machines and used in kernel ridge regression, amongst others. Kernel methods share three aspects. First, instead of…

Machine Learning · Statistics 2025-08-25 Patrick J. F. Groenen , Michael Greenacre

We investigate the properties of a class of piecewise-fractional maps arising from the introduction of an invariance under rescaling into convex quadratic maps. The subsequent maps are quasiconvex, and pseudoconvex on specific convex cones;…

Optimization and Control · Mathematics 2025-04-25 Alexandra Zverovich , Matthew Hutchings , Bertrand Gauthier

The study of representations invariant to common transformations of the data is important to learning. Most techniques have focused on local approximate invariance implemented within expensive optimization frameworks lacking explicit…

Machine Learning · Computer Science 2017-02-27 Dipan K. Pal , Marios Savvides

Machine learning models can capture and amplify biases present in data, leading to disparate test performance across social groups. To better understand, evaluate, and mitigate these biases, a deeper theoretical understanding of how model…

Machine Learning · Computer Science 2025-03-19 Arjun Subramonian , Samuel J. Bell , Levent Sagun , Elvis Dohmatob

Kernel embeddings of distributions and the Maximum Mean Discrepancy (MMD), the resulting distance between distributions, are useful tools for fully nonparametric two-sample testing and learning on distributions. However, it is rarely that…

Machine Learning · Statistics 2017-11-07 Ho Chung Leon Law , Christopher Yau , Dino Sejdinovic

We consider the problem of simultaneously learning to linearly combine a very large number of kernels and learn a good predictor based on the learnt kernel. When the number of kernels $d$ to be combined is very large, multiple kernel…

Machine Learning · Computer Science 2015-03-20 Arash Afkanpour , András György , Csaba Szepesvári , Michael Bowling

Modern machine learning models are prone to over-reliance on spurious correlations, which can often lead to poor performance on minority groups. In this paper, we identify surprising and nuanced behavior of finetuned models on worst-group…

Machine Learning · Computer Science 2024-10-29 Tyler LaBonte , John C. Hill , Xinchen Zhang , Vidya Muthukumar , Abhishek Kumar

We apply kernel mean embedding methods to sample-based stochastic optimization and control. Specifically, we use the reduced-set expansion method as a way to discard sampled scenarios. The effect of such constraint removal is improved…

Optimization and Control · Mathematics 2020-04-24 Jia-Jie Zhu , Moritz Diehl , Bernhard Schölkopf

The principle of translation equivariance (if an input image is translated an output image should be translated by the same amount), led to the development of convolutional neural networks that revolutionized machine vision. Other…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Zachary Schlamowitz , Andrew Bennecke , Daniel J. Tward

We focus on the distribution regression problem: regressing to vector-valued outputs from probability measures. Many important machine learning and statistical tasks fit into this framework, including multi-instance learning and point…

Statistics Theory · Mathematics 2016-10-24 Zoltan Szabo , Bharath Sriperumbudur , Barnabas Poczos , Arthur Gretton

Random forest regression is a powerful non-parametric method that adapts to local data characteristics through data-driven partitioning, making it effective across diverse application domains. However, the piecewise constant nature of…

Machine Learning · Computer Science 2026-05-19 Ziyi Liu , Phuc Luong , Mario Boley , Daniel F. Schmidt

Recent theoretical studies illustrated that kernel ridgeless regression can guarantee good generalization ability without an explicit regularization. In this paper, we investigate the statistical properties of ridgeless regression with…

Machine Learning · Computer Science 2023-08-30 Jian Li , Yong Liu , Yingying Zhang

When solving data analysis problems it is important to integrate prior knowledge and/or structural invariances. This paper contributes by a novel framework for incorporating algebraic invariance structure into kernels. In particular, we…

Machine Learning · Statistics 2014-12-01 Franz J. Király , Andreas Ziehe , Klaus-Robert Müller

Data augmentation is a commonly applied technique with two seemingly related advantages. With this method one can increase the size of the training set generating new samples and also increase the invariance of the network against the…

Computer Vision and Pattern Recognition · Computer Science 2022-05-31 Jalal Al-afandi , Bálint Magyar , András Horváth

Recent work suggests that some auto-encoder variants do a good job of capturing the local manifold structure of the unknown data generating density. This paper contributes to the mathematical understanding of this phenomenon and helps…

Machine Learning · Computer Science 2012-07-03 Yoshua Bengio , Guillaume Alain , Salah Rifai

Generative models, like large language models, are becoming increasingly relevant in our daily lives, yet a theoretical framework to assess their generalization behavior and uncertainty does not exist. Particularly, the problem of…

Machine Learning · Computer Science 2024-07-11 Sebastian G. Gruber , Florian Buettner

We study approximation and learning capacities of convolutional neural networks (CNNs) with one-side zero-padding and multiple channels. Our first result proves a new approximation bound for CNNs with certain constraint on the weights. Our…

Machine Learning · Computer Science 2025-07-29 Yunfei Yang , Han Feng , Ding-Xuan Zhou

We adapt a manifold sampling algorithm for the nonsmooth, nonconvex formulations of learning that arise when imposing robustness to outliers present in the training data. We demonstrate the approach on objectives based on trimmed loss.…

Optimization and Control · Mathematics 2018-07-10 Matt Menickelly , Stefan M. Wild

We show that deep ensembles become equivariant for all inputs and at all training times by simply using data augmentation. Crucially, equivariance holds off-manifold and for any architecture in the infinite width limit. The equivariance is…

Machine Learning · Computer Science 2024-06-18 Jan E. Gerken , Pan Kessel

It is demonstrated that non-constant kernel solution, that can fit the spatial variations of the kernel can be obtained with minimum computing time. The CPU cost required with this new extension of the image subtraction method is almost the…

Astrophysics · Physics 2007-05-23 C. Alard