English
Related papers

Related papers: Identifying Generalization Properties in Neural Ne…

200 papers

Effective regularisation of neural networks is essential to combat overfitting due to the large number of parameters involved. We present an empirical analogue to the Lipschitz constant of a feed-forward neural network, which we refer to as…

Machine Learning · Statistics 2018-07-03 Henry Gouk , Bernhard Pfahringer , Eibe Frank , Michael Cree

We study transformers' generalization behavior on boolean domains from the perspective of the Fourier spectra of their target functions. In contrast to prior work (Edelman et al., 2022; Trauger & Tosh, 2024), which derived generalization…

Machine Learning · Computer Science 2026-05-27 Paul Lintilhac , Sair Shaikh

This paper studies identifiability and convergence behaviors for parameters of multiple types in finite mixtures, and the effects of model fitting with extra mixing components. First, we present a general theory for strong identifiability,…

Statistics Theory · Mathematics 2015-01-13 Nhat Ho , XuanLong Nguyen

Understanding generalization is crucial to confidently engineer and deploy machine learning models, especially when deployment implies a shift in the data domain. For such domain adaptation problems, we seek generalization bounds which are…

Machine Learning · Computer Science 2023-03-16 Adam Breitholtz , Fredrik D. Johansson

Overparameterized neural networks often show a benign overfitting property in the sense of achieving excellent generalization behavior despite the number of parameters exceeding the number of training examples. A promising direction to…

Machine Learning · Computer Science 2026-04-23 Yunwen Lei , Yufeng Xie

We present a universal approach to the investigation of the dynamics in generalized models. In these models the processes that are taken into account are not restricted to specific functional forms. Therefore a single generalized models can…

Chaotic Dynamics · Physics 2007-05-23 Thilo Gross , Ulrike Feudel

We study the approximation gap between the dynamics of a polynomial-width neural network and its infinite-width counterpart, both trained using projected gradient descent in the mean-field scaling regime. We demonstrate how to tightly bound…

Machine Learning · Statistics 2025-09-25 Margalit Glasgow , Denny Wu , Joan Bruna

Near an optimal learning point of a neural network, the learning performance of gradient descent dynamics is dictated by the Hessian matrix of the loss function with respect to the network parameters. We characterize the Hessian…

Machine Learning · Statistics 2025-12-18 Carlos Couto , José Mourão , Mário A. T. Figueiredo , Pedro Ribeiro

Despite their overwhelming capacity to overfit, deep learning architectures tend to generalize relatively well to unseen data, allowing them to be deployed in practice. However, explaining why this is the case is still an open area of…

Machine Learning · Computer Science 2017-11-15 Laurent Dinh , Razvan Pascanu , Samy Bengio , Yoshua Bengio

We show that the input correlation matrix of typical classification datasets has an eigenspectrum where, after a sharp initial drop, a large number of small eigenvalues are distributed uniformly over an exponentially large range. This…

Machine Learning · Computer Science 2022-06-23 Rubing Yang , Jialin Mao , Pratik Chaudhari

Probably Approximately Correct (PAC) bounds are widely used to derive probabilistic guarantees for the generalisation of machine learning models. They highlight the components of the model which contribute to its generalisation capacity.…

Machine Learning · Computer Science 2024-07-30 Thomas Walker , Alessio Lomuscio

We study the generalisation properties of majority voting on finite ensembles of classifiers, proving margin-based generalisation bounds via the PAC-Bayes theory. These provide state-of-the-art guarantees on a number of classification…

Machine Learning · Computer Science 2022-10-21 Felix Biggs , Valentina Zantedeschi , Benjamin Guedj

We develop dependent hierarchical normalized random measures and apply them to dynamic topic modeling. The dependency arises via superposition, subsampling and point transition on the underlying Poisson processes of these measures. The…

Machine Learning · Computer Science 2012-06-22 Changyou Chen , Nan Ding , Wray Buntine

The learning properties of finite size polynomial Support Vector Machines are analyzed in the case of realizable classification tasks. The normalization of the high order features acts as a squeezing factor, introducing a strong anisotropy…

Disordered Systems and Neural Networks · Physics 2009-10-31 Sebastian Risau-Gusman , Mirta B. Gordon

The paper deals with a comprehensive theory of mappings, whose local behavior can be described by means of linear subspaces, contained in the graphs of two (primal and dual) generalized derivatives. This class of mappings includes the…

Optimization and Control · Mathematics 2021-12-08 Helmut Gfrerer , Jiri V. Outrata

Stratified models depend in an arbitrary way on a selected categorical feature that takes $K$ values, and depend linearly on the other $n$ features. Laplacian regularization with respect to a graph on the feature values can greatly improve…

Machine Learning · Computer Science 2020-01-29 Jonathan Tuck , Stephen Boyd

The local optima network model has proved useful in the past in connection with combinatorial optimization problems. Here we examine its extension to the real continuous function domain. Through a sampling process, the model builds a…

Statistical Mechanics · Physics 2022-12-21 Marco Tomassini

Although overparameterized models have achieved remarkable practical success, their theoretical properties, particularly their generalization behavior, remain incompletely understood. The well known double descents phenomenon suggests that…

Machine Learning · Statistics 2026-01-06 Haoran Zhan , Yingcun Xia

We introduce a new notion of complexity of functions and we show that it has the following properties: (i) it governs a PAC Bayes-like generalization bound, (ii) for neural networks it relates to natural notions of complexity of functions…

Machine Learning · Computer Science 2023-03-15 Grzegorz Głuch , Rudiger Urbanke

Modern machine learning models with a large number of parameters often generalize well despite perfectly interpolating noisy training data - a phenomenon known as benign overfitting. A foundational explanation for this in linear…

Machine Learning · Statistics 2025-11-18 Yuta Kondo