English
Related papers

Related papers: Learning in High Dimension Always Amounts to Extra…

200 papers

Neural networks trained on large datasets by minimizing a loss have become the state-of-the-art approach for resolving data science problems, particularly in computer vision, image processing and natural language processing. In spite of…

Computer Vision and Pattern Recognition · Computer Science 2022-11-08 Adrien Courtois , Jean-Michel Morel , Pablo Arias

It is frequently observed that overparameterized neural networks generalize well. Regarding such phenomena, existing theoretical work mainly devotes to linear settings or fully-connected neural networks. This paper studies the learning…

Machine Learning · Statistics 2023-08-17 Tian-Yi Zhou , Xiaoming Huo

Overparametrized models can exhibit an excellent generalization performance, although they should be prone to overfitting according to classical statistical theory. The discovery of the "double descent", indicating that the generalization…

Machine Learning · Computer Science 2026-05-22 Tino Werner

It is often possible to perform reduced order modelling by specifying linear subspace which accurately captures the dynamics of the system. This approach becomes especially appealing when linear subspace explicitly depends on parameters of…

Machine Learning · Computer Science 2026-04-17 Vladimir Fanaskov , Vladislav Trifonov , Alexander Rudikov , Ekaterina Muravleva , Ivan Oseledets

The last decade has seen blossoming research in deep learning theory attempting to answer, "Why does deep learning generalize?" A powerful shift in perspective precipitated this progress: the study of overparametrized models in the…

Machine Learning · Statistics 2024-06-18 Patrik Reizinger , Szilvia Ujváry , Anna Mészáros , Anna Kerekes , Wieland Brendel , Ferenc Huszár

Current deep neural networks are highly overparameterized (up to billions of connection weights) and nonlinear. Yet they can fit data almost perfectly through variants of gradient descent algorithms and achieve unexpected levels of…

This paper establishes the generalization error of pooled min-$\ell_2$-norm interpolation in transfer learning where data from diverse distributions are available. Min-norm interpolators emerge naturally as implicit regularized limits of…

Statistics Theory · Mathematics 2024-06-21 Yanke Song , Sohom Bhattacharya , Pragya Sur

Machine learning models have been progressively used for predicting materials properties. These models can be built using pre-existing data and are useful for rapidly screening the physicochemical space of a material, which is…

Soft Condensed Matter · Physics 2024-09-17 Israrul H. Hashmi , Himanshu , Rahul Karmakar , Tarak K Patra

The premise of identifiable and causal representation learning is to improve the current representation learning paradigm in terms of generalizability or robustness. Despite recent progress in questions of identifiability, more theoretical…

Machine Learning · Computer Science 2024-03-06 Sorawit Saengkyongam , Elan Rosenfeld , Pradeep Ravikumar , Niklas Pfister , Jonas Peters

We study the problem of transfer learning, observing that previous efforts to understand its information-theoretic limits do not fully exploit the geometric structure of the source and target domains. In contrast, our study first…

Machine Learning · Computer Science 2022-02-24 Xuhui Zhang , Jose Blanchet , Soumyadip Ghosh , Mark S. Squillante

A persistent paradox in continual learning (CL) is that neural networks often retain linearly separable representations of past tasks even when their output predictions fail. We formalize this distinction as the gap between deep…

Machine Learning · Computer Science 2026-03-20 Giulia Lanzillotta , Damiano Meier , Thomas Hofmann

Recent success in training deep neural networks have prompted active investigation into the features learned on their intermediate layers. Such research is difficult because it requires making sense of non-linear computations performed by…

Machine Learning · Computer Science 2016-03-01 Yixuan Li , Jason Yosinski , Jeff Clune , Hod Lipson , John Hopcroft

A fundamental problem in manifold learning is to approximate a functional relationship in a data chosen randomly from a probability distribution supported on a low dimensional sub-manifold of a high dimensional ambient Euclidean space. The…

Machine Learning · Computer Science 2023-07-11 H. N. Mhaskar , Ryan O'Dowd

The Performance Estimation Problem (PEP) approach consists in computing worst-case performance bounds on optimization algorithms by solving an optimization problem: one maximizes an error criterion over all initial conditions allowed and…

Optimization and Control · Mathematics 2024-02-13 Anne Rubbens , Nizar Bousselmi , Sebastien Colla , Julien M. Hendrickx

Dropout as regularization has been used extensively to prevent overfitting for training neural networks. During training, units and their connections are randomly dropped, which could be considered as sampling many different submodels from…

Machine Learning · Computer Science 2022-04-28 Zhaoyuan Yang , Arpit Jain

Disobeying the classical wisdom of statistical learning theory, modern deep neural networks generalize well even though they typically contain millions of parameters. Recently, it has been shown that the trajectories of iterative…

Machine Learning · Computer Science 2021-11-29 Tolga Birdal , Aaron Lou , Leonidas Guibas , Umut Şimşekli

Extreme value theory provides rigorous theory and statistical tools for extrapolation in machine learning, particularly in settings where traditional methods struggle due to data scarcity in the tails. A broad range of tasks benefit from…

Machine Learning · Statistics 2026-05-05 Sebastian Engelke , Nicola Gnecco , Anne Sabourin

Modern neural networks are often operated in a strongly overparametrized regime: they comprise so many parameters that they can interpolate the training set, even if actual labels are replaced by purely random ones. Despite this, they…

Machine Learning · Statistics 2022-06-10 Andrea Montanari , Yiqiao Zhong

We propose a general theory of estimating interpolation error for smooth functions in two and three dimensions. In our theory, the error of interpolation is bound in terms of the diameter of a simplex and a geometric parameter. In the…

Numerical Analysis · Mathematics 2021-06-10 Hiroki Ishizaka , Kenta Kobayashi , Takuya Tsuchiya

Modern machine learning systems based on neural networks have shown great success in learning complex data patterns while being able to make good predictions on unseen data points. However, the limited interpretability of these systems…

Machine Learning · Computer Science 2020-07-22 Sarath Shekkizhar , Antonio Ortega