English
Related papers

Related papers: Jamming in multilayer supervised learning models

200 papers

Despite decades of work, gaining a first-principle understanding of amorphous materials remains an extremely challenging problem. However, recent theoretical breakthroughs have led to the formulation of an exact solution in the mean-field…

Disordered Systems and Neural Networks · Physics 2017-04-20 Patrick Charbonneau , Jorge Kurchan , Giorgio Parisi , Pierfrancesco Urbani , Francesco Zamponi

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

Large language models based on the Transformer architecture have demonstrated impressive capabilities to learn in context. However, existing theoretical studies on how this phenomenon arises are limited to the dynamics of a single layer of…

Machine Learning · Statistics 2024-06-04 Juno Kim , Taiji Suzuki

Simplicial map neural networks (SMNNs) are topology-based neural networks with interesting properties such as universal approximation ability and robustness to adversarial examples under appropriate conditions. However, SMNNs present some…

Machine Learning · Computer Science 2024-03-22 Eduardo Paluzo-Hidalgo , Miguel A. Gutiérrez-Naranjo , Rocio Gonzalez-Diaz

Despite the tremendous successes of deep neural networks (DNNs) in various applications, many fundamental aspects of deep learning remain incompletely understood, including DNN trainability. In a trainability study, one aims to discern what…

Machine Learning · Computer Science 2023-05-19 Yueyao Yu , Yin Zhang

As machine learning models, specifically neural networks, are becoming increasingly popular, there are concerns regarding their trustworthiness, specially in safety-critical applications, e.g. actions of an autonomous vehicle must be safe.…

Machine Learning · Computer Science 2023-12-15 Kshitij Goyal , Sebastijan Dumancic , Hendrik Blockeel

The jamming transition of non-spherical particles is fundamentally different from the spherical case. Non-spherical particles are hypostatic at their jamming points, while isostaticity is ensured in the case of the jamming of spherical…

Soft Condensed Matter · Physics 2020-03-17 Harukuni Ikeda , Carolina Brito , Matthieu Wyart

We investigate the Schelling model of social segregation, formulated as an intrinsically non-equilibrium system, in which the agents occupy districts (or patches) rather than sites on a grid. We show that this allows the equations governing…

Statistical Mechanics · Physics 2012-04-25 Tim Rogers , Alan J. McKane

Equivariant neural networks provide a principled framework for incorporating symmetry into learning architectures and have been extensively analyzed through the lens of their separation power, that is, the ability to distinguish inputs…

Machine Learning · Computer Science 2026-02-04 Marco Pacini , Gabriele Santin , Bruno Lepri , Shubhendu Trivedi

Convolutional neural networks are ubiquitous in Machine Learning applications for solving a variety of problems. They however can not be used in their native form when the domain of the data is commonly encountered manifolds such as the…

Computer Vision and Pattern Recognition · Computer Science 2018-08-08 Rudrasis Chakraborty , Monami Banerjee , Baba C. Vemuri

We present a fully constructive analysis of deep ReLU neural networks for classification and function approximation tasks. First, we prove that any dataset with $N$ distinct points in $\mathbb{R}^d$ and $M$ output classes can be exactly…

Machine Learning · Statistics 2025-06-25 Martín Hernández , Enrique Zuazua

Domain shifts in the training data are common in practical applications of machine learning; they occur for instance when the data is coming from different sources. Ideally, a ML model should work well independently of these shifts, for…

Classical multidimensional scaling is a widely used method in dimensionality reduction and manifold learning. The method takes in a dissimilarity matrix and outputs a low-dimensional configuration matrix based on a spectral decomposition.…

Methodology · Statistics 2019-05-15 Gongkai Li , Minh Tang , Nichlas Charon , Carey E Priebe

Classical Recurrent Neural Networks (RNNs) summarize musical context into a deterministic hidden state vector, imposing an information bottleneck that fails to capture the inherent ambiguity in music. We propose the Density Matrix RNN…

Machine Learning · Computer Science 2026-01-09 Joonwon Seo , Mariana Montiel

The jamming transition between flow and amorphous-solid states exhibits paradoxical properties characterized by hyperuniformity (suppressed spatial fluctuations) and criticality (hyperfluctuations), whose origin remains unclear. Here we…

Soft Condensed Matter · Physics 2025-06-23 Jin Shang , Yinqiao Wang , Deng Pan , Yuliang Jin , Jie Zhang

We present a novel mechanism for the anomalous behaviour of the specific heat in low-temperature amorphous solids. The analytic solution of a mean-field model belonging to the same universality class as high-dimensional glasses, the…

Disordered Systems and Neural Networks · Physics 2019-07-29 Silvio Franz , Thibaud Maimbourg , Giorgio Parisi , Antonello Scardicchio

Neural collapse is a highly symmetric geometric pattern of neural networks that emerges during the terminal phase of training, with profound implications on the generalization performance and robustness of the trained networks. To…

Machine Learning · Computer Science 2022-04-26 Wenlong Ji , Yiping Lu , Yiliang Zhang , Zhun Deng , Weijie J. Su

Neural collapse ($\mathcal{NC}$) is a phenomenon observed in classification tasks where top-layer representations collapse into their class means, which become equinorm, equiangular and aligned with the classifiers. These behaviours --…

Machine Learning · Computer Science 2024-11-27 Robert Wu , Vardan Papyan

Neural networks (NNs) have emerged as a state-of-the-art method for modeling nonlinear systems in model predictive control (MPC). However, the robustness of NNs, in terms of sensitivity to small input perturbations, remains a critical…

Systems and Control · Electrical Eng. & Systems 2023-08-29 Wallace Tan Gian Yion , Zhe Wu

We show that both an LSTM and a unitary-evolution recurrent neural network (URN) can achieve encouraging accuracy on two types of syntactic patterns: context-free long distance agreement, and mildly context-sensitive cross serial…

Computation and Language · Computer Science 2022-08-12 Jean-Philippe Bernardy , Shalom Lappin