English
Related papers

Related papers: Stochastic Gradient Descent-Induced Drift of Repre…

200 papers

We conjecture that the inherent difference in generalisation between adaptive and non-adaptive gradient methods in deep learning stems from the increased estimation noise in the flattest directions of the true loss surface. We demonstrate…

Machine Learning · Statistics 2022-03-17 Diego Granziol , Nicholas Baskerville

We analyze the implicit bias of constant step stochastic subgradient descent (SGD). We consider the setting of binary classification with homogeneous neural networks - a large class of deep neural networks with ReLU-type activation…

Machine Learning · Computer Science 2025-07-18 Sholom Schechtman , Nicolas Schreuder

Numerous empirical evidence has corroborated that the noise plays a crucial rule in effective and efficient training of neural networks. The theory behind, however, is still largely unknown. This paper studies this fundamental problem…

Machine Learning · Computer Science 2019-09-10 Mo Zhou , Tianyi Liu , Yan Li , Dachao Lin , Enlu Zhou , Tuo Zhao

Due to the massive size of the neural network models and training datasets used in machine learning today, it is imperative to distribute stochastic gradient descent (SGD) by splitting up tasks such as gradient evaluation across multiple…

Machine Learning · Computer Science 2020-03-13 Xiaoxi Zhang , Jianyu Wang , Gauri Joshi , Carlee Joe-Wong

We investigate the relationship between the effective diffusivity and effective drift of a particle moving in a random medium. The velocity of the particle combines a white noise diffusion process with a local drift term that depends…

Condensed Matter · Physics 2009-10-28 D. S. Dean , I. T. Drummond , R. R. Horgan

In centralized settings, it is well known that stochastic gradient descent (SGD) avoids saddle points and converges to local minima in nonconvex problems. However, similar guarantees are lacking for distributed first-order algorithms. The…

Optimization and Control · Mathematics 2022-03-07 Brian Swenson , Ryan Murray , H. Vincent Poor , Soummya Kar

The learning rate is perhaps the single most important parameter in the training of neural networks and, more broadly, in stochastic (nonconvex) optimization. Accordingly, there are numerous effective, but poorly understood, techniques for…

Machine Learning · Computer Science 2020-04-16 Bin Shi , Weijie J. Su , Michael I. Jordan

We study the problem of training a two-layer neural network (NN) of arbitrary width using stochastic gradient descent (SGD) where the input $\boldsymbol{x}\in \mathbb{R}^d$ is Gaussian and the target $y \in \mathbb{R}$ follows a…

Machine Learning · Statistics 2023-03-17 Alireza Mousavi-Hosseini , Sejun Park , Manuela Girotti , Ioannis Mitliagkas , Murat A. Erdogdu

The success of modern machine learning is due in part to the adaptive optimization methods that have been developed to deal with the difficulties of training large models over complex datasets. One such method is gradient clipping: a…

Machine Learning · Statistics 2024-10-08 Noah Marshall , Ke Liang Xiao , Atish Agarwala , Elliot Paquette

To better understand the temporal characteristics and the lifetime of fluctuations in stochastic processes in networks, we investigated diffusive persistence in various graphs. Global diffusive persistence is defined as the fraction of…

Statistical Mechanics · Physics 2024-06-04 Omar Malik , Melinda Varga , Alaa Moussawi , David Hunt , Boleslaw Szymanski , Zoltan Toroczkai , Gyorgy Korniss

Due to the over-smoothing issue, most existing graph neural networks can only capture limited dependencies with their inherently finite aggregation layers. To overcome this limitation, we propose a new kind of graph convolution, called…

Machine Learning · Computer Science 2022-06-30 Qi Chen , Yifei Wang , Yisen Wang , Jiansheng Yang , Zhouchen Lin

This paper concerns the mathematical analyses of the diffusion model in machine learning. The drift term of the backward sampling process is represented as a conditional expectation involving the data distribution and the forward diffusion.…

Machine Learning · Computer Science 2024-12-11 Yubin Lu , Zhongjian Wang , Guillaume Bal

Recently, we proposed to transform the outputs of each hidden neuron in a multi-layer perceptron network to have zero output and zero slope on average, and use separate shortcut connections to model the linear dependencies instead. We…

Machine Learning · Computer Science 2013-03-12 Tommi Vatanen , Tapani Raiko , Harri Valpola , Yann LeCun

Representations learned by pre-training a neural network on a large dataset are increasingly used successfully to perform a variety of downstream tasks. In this work, we take a closer look at how features are encoded in such pre-trained…

Machine Learning · Computer Science 2023-11-15 Vedant Nanda , Till Speicher , John P. Dickerson , Soheil Feizi , Krishna P. Gummadi , Adrian Weller

Part I of this paper considered optimization problems over networks where agents have individual objectives to meet, or individual parameter vectors to estimate, subject to subspace constraints that require the objectives across the network…

Multiagent Systems · Computer Science 2019-07-01 Roula Nassif , Stefan Vlaski , Ali H. Sayed

We study the limiting dynamics of a large class of noisy gradient descent systems in the overparameterized regime. In this regime the set of global minimizers of the loss is large, and when initialized in a neighbourhood of this zero-loss…

Machine Learning · Computer Science 2024-04-19 Anna Shalova , André Schlichting , Mark Peletier

For infinitesimal learning rates, stochastic gradient descent (SGD) follows the path of gradient flow on the full batch loss function. However moderately large learning rates can achieve higher test accuracies, and this generalization…

Machine Learning · Computer Science 2021-01-29 Samuel L. Smith , Benoit Dherin , David G. T. Barrett , Soham De

Analyzing neural network dynamics via stochastic gradient descent (SGD) is crucial to building theoretical foundations for deep learning. Previous work has analyzed structured inputs within the \textit{hidden manifold model}, often under…

Machine Learning · Statistics 2025-12-01 Jaeyong Bae , Hawoong Jeong

Recurrent neural networks (RNNs) are difficult to train on sequence processing tasks, not only because input noise may be amplified through feedback, but also because any inaccuracy in the weights has similar consequences as input noise. We…

Neural and Evolutionary Computing · Computer Science 2018-05-29 Michael C. Mozer , Denis Kazakov , Robert V. Lindsey

Diffusion models, though originally designed for generative tasks, have demonstrated impressive self-supervised representation learning capabilities. A particularly intriguing phenomenon in these models is the emergence of unimodal…

Machine Learning · Computer Science 2026-02-04 Xiao Li , Zekai Zhang , Xiang Li , Siyi Chen , Zhihui Zhu , Peng Wang , Qing Qu