English
Related papers

Related papers: Feature Lottery? A Bifurcation Theory of Concept E…

200 papers

Bifurcation theory is a powerful tool for studying how the dynamics of a neural network model depends on its underlying neurophysiological parameters. However, bifurcation theory has been developed mostly for smooth dynamical systems and…

Neurons and Cognition · Quantitative Biology 2019-01-16 Diego Fasoli , Stefano Panzeri

Neural networks often rely on spurious shortcuts for many epochs before discovering structured representations. However, the mechanism governing when this transition occurs and whether its timing can be predicted remains unclear. Prior work…

Machine Learning · Computer Science 2026-03-10 Truong Xuan Khanh , Truong Quynh Hoa

Understanding the training dynamics of quantum neural networks is a fundamental task in quantum information science with wide impact in physics, chemistry and machine learning. In this work, we show that the late-time training dynamics of…

Quantum Physics · Physics 2024-10-31 Bingzhi Zhang , Junyu Liu , Xiao-Chuan Wu , Liang Jiang , Quntao Zhuang

Bifurcations can cause dynamical systems with slowly varying parameters to transition to far-away attractors. The terms ``critical transition'' or ``tipping point'' have been used to describe this situation. Critical transitions have been…

Dynamical Systems · Mathematics 2015-03-17 Christian Kuehn

Moment systems arise in a wide range of contexts and applications, e.g. in network modeling of complex systems. Since moment systems consist of a high or even infinite number of coupled equations, an indispensable step in obtaining a…

Adaptation and Self-Organizing Systems · Physics 2024-03-19 Christian Kuehn , Jan Mölter

The advent of Scientific Machine Learning has heralded a transformative era in scientific discovery, driving progress across diverse domains. Central to this progress is uncovering scientific laws from experimental data through symbolic…

Methodology · Statistics 2025-09-25 Somjit Roy , Pritam Dey , Debdeep Pati , Bani K. Mallick

Current sparse autoencoder (SAE) approaches to neural network interpretability assume that activations can be decomposed through linear superposition into sparse, interpretable features. Despite high reconstruction fidelity, SAEs…

Neurons and Cognition · Quantitative Biology 2025-12-10 Omar Claflin

A generic saddle-node bifurcation is proposed to modelize fast transitions of finite amplitude arising in geophysical (and perhaps other) contexts, when they result from the intrinsic dynamics of the system. The fast transition is…

Chaotic Dynamics · Physics 2012-09-10 Yves Pomeau , Martine Le Berre

Rich feature learning in tasks that unfold over time often requires the model to pass through bifurcations, constituting qualitative changes in the underlying model dynamics. We develop a local theory of gradient descent near these…

Machine Learning · Computer Science 2026-05-14 James Hazelden , Eric Shea-Brown

Recent work by Power et al. (2022) highlighted a surprising "grokking" phenomenon in learning arithmetic tasks: a neural net first "memorizes" the training set, resulting in perfect training accuracy but near-random test accuracy, and after…

Machine Learning · Computer Science 2024-04-03 Kaifeng Lyu , Jikai Jin , Zhiyuan Li , Simon S. Du , Jason D. Lee , Wei Hu

Understanding the structure of real data is paramount in advancing modern deep-learning methodologies. Natural data such as images are believed to be composed of features organized in a hierarchical and combinatorial manner, which neural…

Machine Learning · Statistics 2024-12-25 Antonio Sclocchi , Alessandro Favero , Matthieu Wyart

We present a comprehensive analysis of how two-layer neural networks learn features to solve the modular addition task. Our work provides a full mechanistic interpretation of the learned model and a theoretical explanation of its training…

Machine Learning · Computer Science 2026-02-20 Jianliang He , Leda Wang , Siyu Chen , Zhuoran Yang

We investigate the data-driven discovery of constitutive closures in nonlinear reaction-diffusion systems with known governing PDE structures. Our objective is to robustly recover diffusion and reaction laws from spatiotemporal observations…

Computational Engineering, Finance, and Science · Computer Science 2026-04-03 Hanbing Liang , Ze Tao , Fujun Liu

Spontaneous symmetry breaking in statistical mechanics primarily occurs during phase transitions at the thermodynamic limit where the Hamiltonian preserves inversion symmetry, yet the low-temperature free energy exhibits reduced symmetry.…

Computation and Language · Computer Science 2026-03-02 Shalom Rosner , Ronit D. Gross , Ella Koresh , Ido Kanter

For three decades statistical mechanics has been providing a framework to analyse neural networks. However, the theoretically tractable models, e.g., perceptrons, random features models and kernel machines, or multi-index models and…

Machine Learning · Statistics 2025-06-02 Jean Barbier , Francesco Camilli , Minh-Toan Nguyen , Mauro Pastore , Rudy Skerk

Predicting labels of nodes in a network, such as community memberships or demographic variables, is an important problem with applications in social and biological networks. A recently-discovered phase transition puts fundamental limits on…

Social and Information Networks · Computer Science 2014-11-20 Pan Zhang , Cristopher Moore , Lenka Zdeborová

Training loss and accuracy are the standard signals used to monitor generalization during deep neural network training. Two well-documented phenomena complicate this picture: in grokking, train loss falls rapidly while test performance…

Machine Learning · Computer Science 2026-05-29 Chi-Ning Chou , Oscar Uzdelewicz , Neng-Chun Chiu , Yao-Yuan Yang , SueYeon Chung

Many natural and man-made systems are prone to critical transitions -- abrupt and potentially devastating changes in dynamics. Deep learning classifiers can provide an early warning signal (EWS) for critical transitions by learning generic…

Quantitative Methods · Quantitative Biology 2024-02-12 Thomas M. Bury , Daniel Dylewsky , Chris T. Bauch , Madhur Anand , Leon Glass , Alvin Shrier , Gil Bub

Understanding how deep neural networks learn remains a fundamental challenge in modern machine learning. A growing body of evidence suggests that training dynamics undergo a distinct phase transition, yet our understanding of this…

Machine Learning · Computer Science 2025-05-21 Zhanpeng Zhou , Yongyi Yang , Mahito Sugiyama , Junchi Yan

The bifurcation theory of ordinary differential equations (ODEs), and its application to deterministic population models, are by now well established. In this article, we begin to develop a complementary theory for diffusion-like…

Dynamical Systems · Mathematics 2021-01-22 Eric Foxall
‹ Prev 1 2 3 10 Next ›