English
Related papers

Related papers: Topological Invariance and Breakdown in Learning

200 papers

Deep neural networks trained using gradient descent with a fixed learning rate $\eta$ often operate in the regime of "edge of stability" (EOS), where the largest eigenvalue of the Hessian equilibrates about the stability threshold $2/\eta$.…

Machine Learning · Statistics 2025-03-03 Avrajit Ghosh , Soo Min Kwon , Rongrong Wang , Saiprasad Ravishankar , Qing Qu

We empirically demonstrate that full-batch gradient descent on neural network training objectives typically operates in a regime we call the Edge of Stability. In this regime, the maximum eigenvalue of the training loss Hessian hovers just…

Machine Learning · Computer Science 2022-11-24 Jeremy M. Cohen , Simran Kaur , Yuanzhi Li , J. Zico Kolter , Ameet Talwalkar

Dropout is a standard training technique for neural networks that consists of randomly deactivating units at each step of their gradient-based training. It is known to improve performance in many settings, including in the large-scale…

Machine Learning · Computer Science 2025-10-10 Lénaïc Chizat , Pierre Marion , Yerkin Yesbay

Deep learning systems achieve remarkable empirical performance, yet the stability of the training process itself remains poorly understood. Training unfolds as a high-dimensional dynamical system in which small perturbations to…

Machine Learning · Computer Science 2026-01-21 Zhipeng Zhang , Zhenjie Yao , Kai Li , Lei Yang

A longstanding goal in deep learning research has been to precisely characterize training and generalization. However, the often complex loss landscapes of neural networks have made a theory of learning dynamics elusive. In this work, we…

The theory underlying robust distributed learning algorithms, designed to resist adversarial machines, matches empirical observations when data is homogeneous. Under data heterogeneity however, which is the norm in practical scenarios,…

Machine Learning · Computer Science 2023-10-31 Youssef Allouah , Rachid Guerraoui , Nirupam Gupta , Rafaël Pinot , Geovani Rizk

This paper introduces a new probabilistic framework for supervised learning in neural systems. It is designed to model complex, uncertain systems whose random outputs are strongly non-Gaussian given deterministic inputs. The architecture…

Machine Learning · Statistics 2025-12-12 Christian Soize

This work studies the (non)robustness of two-layer neural networks in various high-dimensional linearized regimes. We establish fundamental trade-offs between memorization and robustness, as measured by the Sobolev-seminorm of the model…

Machine Learning · Statistics 2021-06-07 Elvis Dohmatob

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…

Small neural networks with a constrained number of trainable parameters, can be suitable resource-efficient candidates for many simple tasks, where now excessively large models are used. However, such models face several problems during the…

Machine Learning · Computer Science 2021-09-21 Alexander Kovalenko , Pavel Kordík , Magda Friedjungová

In this work we study biological neural networks from an algorithmic perspective, focusing on understanding tradeoffs between computation time and network complexity. Our goal is to abstract real neural networks in a way that, while not…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-04-30 Nancy Lynch , Cameron Musco , Merav Parter

In computational neuroscience, fixed points of recurrent neural networks are commonly used to model neural responses to static or slowly changing stimuli. These applications raise the question of how to train the weights in a recurrent…

Neurons and Cognition · Quantitative Biology 2023-07-28 Vicky Zhu , Robert Rosenbaum

According to a popular viewpoint, neural networks learn from data by first identifying low-dimensional representations, and subsequently fitting the best model in this space. Recent works provide a formalization of this phenomenon when…

Machine Learning · Computer Science 2026-02-27 Andrea Montanari , Zihao Wang

Understanding the optimization dynamics of neural networks is necessary for closing the gap between theory and practice. Stochastic first-order optimization algorithms are known to efficiently locate favorable minima in deep neural…

Machine Learning · Computer Science 2023-06-22 Charles Guille-Escuret , Hiroki Naganuma , Kilian Fatras , Ioannis Mitliagkas

Neural network optimization remains one of the most consequential yet poorly understood challenges in modern AI research, where improvements in training algorithms can lead to enhanced feature learning in foundation models,…

Machine Learning · Computer Science 2025-12-23 Ansh Nagwekar

We initiate a line of investigation into biological neural networks from an algorithmic perspective. We develop a simplified but biologically plausible model for distributed computation in stochastic spiking neural networks and study…

Neural and Evolutionary Computing · Computer Science 2016-10-10 Nancy Lynch , Cameron Musco , Merav Parter

We study feature learning in two-layer neural networks within the linear-width regime, where the number of hidden neurons, sample size, and input dimension scale proportionally. While recent work has analyzed feature learning via a single…

Machine Learning · Statistics 2026-05-25 Behrad Moniri , Hamed Hassani

Deep neural networks can achieve remarkable generalization performances while interpolating the training data perfectly. Rather than the U-curve emblematic of the bias-variance trade-off, their test error often follows a "double descent" -…

Machine Learning · Computer Science 2020-04-06 Stéphane d'Ascoli , Maria Refinetti , Giulio Biroli , Florent Krzakala

Differentiable physical networks provide a simple setting in which learning can be studied through the interaction between trainable parameters and physical equilibrium constraints. We investigate sequential learning in differentiable…

Machine Learning · Computer Science 2026-05-05 Maniru Ibrahim

Discovery processes have been an important topic in the network science field. The exploration of nodes can be understood as the knowledge acquisition process taking place in the network, where nodes represent concepts and edges are the…

Social and Information Networks · Computer Science 2021-03-16 Lucas Guerreiro , Filipi N. Silva , Diego R. Amancio
‹ Prev 1 3 4 5 6 7 10 Next ›