English
Related papers

Related papers: Spectral Edge Dynamics Reveal Functional Modes of …

200 papers

This work is part of an effort to understand the neural basis for our visual system's ability, or failure, to accurately track moving visual signals. We consider here a ring model of spiking neurons, intended as a simplified computational…

Neurons and Cognition · Quantitative Biology 2016-01-13 Guillaume Lajoie , Lai-Sang Young

The loss functions of deep neural networks are complex and their geometric properties are not well understood. We show that the optima of these complex loss functions are in fact connected by simple curves over which training and test…

Machine Learning · Statistics 2018-10-31 Timur Garipov , Pavel Izmailov , Dmitrii Podoprikhin , Dmitry Vetrov , Andrew Gordon Wilson

Stochastic gradient descent (SGD) is central to deep learning, yet the dynamical origin of its preference for flatter, more generalizable solutions remains unclear. Here, by analyzing SGD learning dynamics, we identify a nonequilibrium…

Machine Learning · Computer Science 2026-01-19 Ning Yang , Yikuan Zhang , Qi Ouyang , Chao Tang , Yuhai Tu

Stochastic Gradient Descent (SGD) is commonly modeled as a Langevin process, assuming that minibatch noise acts as Brownian motion. However, this approximation relies on a continuous-time limit and a sqrt(eta) noise scaling that does not…

In this work, we reveal a strong implicit bias of stochastic gradient descent (SGD) that drives overly expressive networks to much simpler subnetworks, thereby dramatically reducing the number of independent parameters, and improving…

Machine Learning · Computer Science 2024-05-30 Feng Chen , Daniel Kunin , Atsushi Yamamura , Surya Ganguli

In this paper we analyze the behaviour of the stochastic gradient descent (SGD), a widely used method in supervised learning for optimizing neural network weights via a minimization of non-convex loss functions. Since the pioneering work of…

Machine Learning · Computer Science 2025-05-13 Davide Barbieri , Matteo Bonforte , Peio Ibarrondo

Why depth yields a genuine computational advantage over shallow methods remains a central open question in learning theory. We study this question in a controlled high-dimensional Gaussian setting, focusing on compositional target…

Machine Learning · Statistics 2026-02-12 Hugo Tabanelli , Yatin Dandi , Luca Pesce , Florent Krzakala

We perform an experimental study of the dynamics of Stochastic Gradient Descent (SGD) in learning deep neural networks for several real and synthetic classification tasks. We show that in the initial epochs, almost all of the performance…

Machine Learning · Computer Science 2019-05-29 Preetum Nakkiran , Gal Kaplun , Dimitris Kalimeris , Tristan Yang , Benjamin L. Edelman , Fred Zhang , Boaz Barak

The main challenge in computing inclusive cross sections and decay spectra in QCD is posed by kinematic thresholds. The threshold region is characterized by stringent phase-space constraints that are reflected in large perturbative…

High Energy Physics - Phenomenology · Physics 2008-11-26 Einan Gardi

We discuss a general framework for recovering edges in piecewise smooth functions with finitely many jump discontinuities, where $[f](x):=f(x+)-f(x-) \neq 0$. Our approach is based on two main aspects--localization using appropriate…

Numerical Analysis · Mathematics 2025-10-20 Anne Gelb , Eitan Tadmor

We propose a homogeneous multilayer perceptron parameterization with polynomial hidden layer width pattern and analyze its training dynamics under stochastic gradient descent with depthwise gradient scaling in a general supervised learning…

Machine Learning · Computer Science 2025-05-20 Dávid Terjék

Standard transformer attention computes pairwise similarity between queries and keys, treating all tokens as equally salient regardless of their intrinsic informational content. In turbulent fluid dynamics, coherent structures -- the…

Machine Learning · Computer Science 2026-05-22 Athanasios Zeris

This letter presents a high-dimensional analysis of the training dynamics for a single-layer nonlinear contrastive learning model. The empirical distribution of the model weights converges to a deterministic measure governed by a…

Machine Learning · Computer Science 2024-06-12 Lineghuan Meng , Chuang Wang

Speculative decoding accelerates language model inference by separating generation into fast drafting and parallel verification. Its main limitation is drafter-verifier misalignment, which limits token acceptance and reduces overall…

Machine Learning · Computer Science 2025-11-14 Frédéric Berdoz , Peer Rheinboldt , Roger Wattenhofer

Gradient signals in LLM training are highly anisotropic: recurrent linguistic structure concentrates energy into a small set of dominant spectral directions, while context specific information resides in a long tail. We show that this spike…

We propose novel methodologies aimed at accelerating the grokking phenomenon, which refers to the rapid increment of test accuracy after a long period of overfitting as reported in~\cite{power2022grokking}. Focusing on the grokking…

Machine Learning · Computer Science 2024-05-28 Yeachan Park , Minseok Kim , Yeoneung Kim

Deep learning models in recommender systems are usually trained in the batch mode, namely iteratively trained on a fixed-size window of training data. Such batch mode training of deep learning models suffers from low training efficiency,…

Information Retrieval · Computer Science 2020-09-07 Yichao Wang , Huifeng Guo , Ruiming Tang , Zhirong Liu , Xiuqiang He

This paper proposes SplitSGD, a new dynamic learning rate schedule for stochastic optimization. This method decreases the learning rate for better adaptation to the local geometry of the objective function whenever a stationary phase is…

Machine Learning · Statistics 2024-02-20 Matteo Sordello , Niccolò Dalmasso , Hangfeng He , Weijie Su

Using statistical physics methods, we study generative diffusion models in the regime where the dimension of space and the number of data are large, and the score function has been trained optimally. Our analysis reveals three distinct…

Machine Learning · Computer Science 2025-01-08 Giulio Biroli , Tony Bonnaire , Valentin de Bortoli , Marc Mézard

We target open-world feature extrapolation problem where the feature space of input data goes through expansion and a model trained on partially observed features needs to handle new features in test data without further retraining. The…

Machine Learning · Computer Science 2023-06-14 Qitian Wu , Chenxiao Yang , Junchi Yan
‹ Prev 1 8 9 10 Next ›