English
Related papers

Related papers: Exact expressions for double descent and implicit …

200 papers

Different gradient-based methods for optimizing overparameterized models can all achieve zero training error yet converge to distinctly different solutions inducing different generalization properties. We provide the first complete…

Machine Learning · Computer Science 2025-12-08 Chen Fan , Mark Schmidt , Christos Thrampoulidis

Over the past years, there has been significant interest in understanding the implicit bias of gradient descent optimization and its connection to the generalization properties of overparametrized neural networks. Several works observed…

Optimization and Control · Mathematics 2025-03-11 Hung-Hsu Chou , Johannes Maly , Claudio Mayrink Verdun , Bernardo Freitas Paulo da Costa , Heudson Mirandola

In deep learning, often the training process finds an interpolator (a solution with 0 training loss), but the test loss is still low. This phenomenon, known as benign overfitting, is a major mystery that received a lot of recent attention.…

Machine Learning · Computer Science 2023-05-29 Mo Zhou , Rong Ge

In distributed second order optimization, a standard strategy is to average many local estimates, each of which is based on a small sketch or batch of the data. However, the local estimates on each machine are typically biased, relative to…

Machine Learning · Computer Science 2020-07-06 Michał Dereziński , Burak Bartan , Mert Pilanci , Michael W. Mahoney

In optimal transport, quadratic regularization is an alternative to entropic regularization when sparse couplings or small regularization parameters are desired. Quadratic regularization penalizes transport couplings by the squared $L^2$…

Optimization and Control · Mathematics 2026-05-20 Alberto González-Sanz , Marcel Nutz , Andrés Riveros Valdevenito

We study the generalization behavior of transfer learning of deep neural networks (DNNs). We adopt the overparameterization perspective -- featuring interpolation of the training data (i.e., approximately zero train error) and the double…

Machine Learning · Computer Science 2023-06-13 Yehuda Dar , Lorenzo Luzi , Richard G. Baraniuk

The theory of bias-variance used to serve as a guide for model selection when applying Machine Learning algorithms. However, modern practice has shown success with over-parameterized models that were expected to overfit but did not. This…

Machine Learning · Computer Science 2022-11-21 Luis Sa-Couto , Jose Miguel Ramos , Miguel Almeida , Andreas Wichert

We study the implicit regularization of mini-batch stochastic gradient descent, when applied to the fundamental problem of least squares regression. We leverage a continuous-time stochastic differential equation having the same moments as…

Machine Learning · Statistics 2020-06-23 Alnur Ali , Edgar Dobriban , Ryan J. Tibshirani

Stochastic gradient descent procedures have gained popularity for parameter estimation from large data sets. However, their statistical properties are not well understood, in theory. And in practice, avoiding numerical instability requires…

Methodology · Statistics 2016-09-29 Panos Toulis , Edoardo M. Airoldi

Sparsity regularized loss minimization problems play an important role in various fields including machine learning, data mining, and modern statistics. Proximal gradient descent method and coordinate descent method are the most popular…

Machine Learning · Computer Science 2023-11-13 Runxue Bao , Bin Gu , Heng Huang

This paper develops a new framework for indirect statistical inference with guaranteed necessity and sufficiency, applicable to continuous random variables. We prove that when comparing exponentially transformed order statistics from an…

Statistics Theory · Mathematics 2025-09-25 Z Zhang , X Hu , C Lu , T Liu

Deep networks are typically trained with many more parameters than the size of the training dataset. Recent empirical evidence indicates that the practice of overparameterization not only benefits training large models, but also assists -…

Machine Learning · Computer Science 2020-12-17 Xiangyu Chang , Yingcong Li , Samet Oymak , Christos Thrampoulidis

The volume of the distribution of weight sets associated with a loss value may be the source of implicit regularization from overparameterization due to the phenomenon of contracting volume with increasing dimensions for geometric figures…

Machine Learning · Computer Science 2022-09-27 Nicholas J. Teague

Stochastic gradient descent (SGD) exhibits strong algorithmic regularization effects in practice, which has been hypothesized to play an important role in the generalization of modern machine learning approaches. In this work, we seek to…

Machine Learning · Computer Science 2022-07-12 Difan Zou , Jingfeng Wu , Vladimir Braverman , Quanquan Gu , Dean P. Foster , Sham M. Kakade

We analyze gradient descent with randomly weighted data points in a linear regression model, under a generic weighting distribution. This includes various forms of stochastic gradient descent, importance sampling, but also extends to…

Machine Learning · Statistics 2025-12-12 Gabriel Clara , Yazan Mash'al

Classical regression has a simple geometric description in terms of a projection of the training labels onto the column space of the design matrix. However, for over-parameterized models -- where the number of fit parameters is large enough…

Machine Learning · Statistics 2021-04-28 Jason W. Rocks , Pankaj Mehta

Ordinary Differential Equations are widespread tools to model chemical, physical, biological process but they usually rely on parameters which are of critical importance in terms of dynamic and need to be estimated directly from the data.…

Methodology · Statistics 2014-10-29 Nicolas Brunel , Quentin Clairon

Classical optimisation theory guarantees monotonic objective decrease for gradient descent (GD) when employed in a small step size, or ``stable", regime. In contrast, gradient descent on neural networks is frequently performed in a large…

Machine Learning · Computer Science 2025-10-21 Lachlan Ewen MacDonald , Hancheng Min , Leandro Palma , Salma Tarmoun , Ziqing Xu , René Vidal

One classical canon of statistics is that large models are prone to overfitting, and model selection procedures are necessary for high dimensional data. However, many overparameterized models, such as neural networks, perform very well in…

Machine Learning · Statistics 2021-01-05 Xi Chen , Qiang Liu , Xin T. Tong

Despite being highly over-parametrized, and having the ability to fully interpolate the training data, deep networks are known to generalize well to unseen data. It is now understood that part of the reason for this is that the training…

Machine Learning · Computer Science 2023-02-21 Danil Akhtiamov , Babak Hassibi
‹ Prev 1 4 5 6 7 8 10 Next ›