English
Related papers

Related papers: Implicit Regularization Leads to Benign Overfittin…

200 papers

Good generalization performance on high-dimensional data crucially hinges on a simple structure of the ground truth and a corresponding strong inductive bias of the estimator. Even though this intuition is valid for regularized models, in…

Machine Learning · Statistics 2022-10-28 Konstantin Donhauser , Nicolo Ruggeri , Stefan Stojanovic , Fanny Yang

We consider the problem of supervised learning with convex loss functions and propose a new form of iterative regularization based on the subgradient method. Unlike other regularization approaches, in iterative regularization no constraint…

Machine Learning · Statistics 2015-04-02 Junhong Lin , Lorenzo Rosasco , Ding-Xuan Zhou

Continuous sparsification strategies are among the most effective methods for reducing the inference costs and memory demands of large-scale neural networks. A key factor in their success is the implicit $L_1$ regularization induced by…

Machine Learning · Computer Science 2025-02-13 Tom Jacobs , Rebekka Burkholz

While much work has been devoted to understanding the implicit (and explicit) regularization of deep nonlinear networks in the supervised setting, this paper focuses on unsupervised learning, i.e., autoencoders are trained with the…

Machine Learning · Computer Science 2021-10-25 Harald Steck , Dario Garcia Garcia

Recent empirical and theoretical studies have established the generalization capabilities of large machine learning models that are trained to (approximately or exactly) fit noisy data. In this work, we prove a surprising result that even…

Machine Learning · Computer Science 2024-01-26 Yifan Hao , Tong Zhang

Adversarial training is an effective methodology for training deep neural networks that are robust against adversarial, norm-bounded perturbations. However, the computational cost of adversarial training grows prohibitively as the size of…

In this paper, we leverage over-parameterization to design regularization-free algorithms for the high-dimensional single index model and provide theoretical guarantees for the induced implicit regularization phenomenon. Specifically, we…

Machine Learning · Statistics 2021-11-18 Jianqing Fan , Zhuoran Yang , Mengxin Yu

Overparameterized neural networks can interpolate a given dataset in many different ways, prompting the fundamental question: which among these solutions should we prefer, and what explicit regularization strategies will provably yield…

Machine Learning · Statistics 2026-01-28 Julia Nakhleh , Robert D. Nowak

With the capability of accurately representing a functional relationship between the inputs of a physical system's model and output quantities of interest, neural networks have become popular for surrogate modeling in scientific…

Machine Learning · Statistics 2022-04-06 Subhayan De , Alireza Doostan

Sparse regularization such as $\ell_1$ regularization is a quite powerful and widely used strategy for high dimensional learning problems. The effectiveness of sparse regularization has been supported practically and theoretically by…

Machine Learning · Statistics 2018-02-23 Masaaki Takada , Taiji Suzuki , Hironori Fujisawa

Data augmentation is used in machine learning to make the classifier invariant to label-preserving transformations. Usually this invariance is only encouraged implicitly by including a single augmented input during training. However,…

Machine Learning · Computer Science 2022-03-08 Aleksander Botev , Matthias Bauer , Soham De

In contemporary deep learning practice, models are often trained to near zero loss i.e. to nearly interpolate the training data. However, the number of parameters in the model is usually far more than the number of data points n, the…

Machine Learning · Computer Science 2025-11-04 Santanu Das , Jatin Batra , Piyush Srivastava

The phenomenon of implicit regularization has attracted interest in recent years as a fundamental aspect of the remarkable generalizing ability of neural networks. In a nutshell, it entails that gradient descent dynamics in many neural…

Machine Learning · Computer Science 2024-02-28 Hong T. M. Chu , Subhro Ghosh , Chi Thanh Lam , Soumendu Sundar Mukherjee

Learning sparse models from data is an important task in all those frameworks where relevant information should be identified within a large dataset. This can be achieved by formulating and solving suitable sparsity promoting optimization…

Optimization and Control · Mathematics 2025-02-18 V. Cerone , S. M. Fosson , D. Regruto , A. Salam

Large learning rates, when applied to gradient descent for nonconvex optimization, yield various implicit biases including the edge of stability (Cohen et al., 2021), balancing (Wang et al., 2022), and catapult (Lewkowycz et al., 2020).…

Machine Learning · Computer Science 2023-12-13 Yuqing Wang , Zhenghao Xu , Tuo Zhao , Molei Tao

We investigate two causes for adversarial vulnerability in deep neural networks: bad data and (poorly) trained models. When trained with SGD, deep neural networks essentially achieve zero training error, even in the presence of label noise,…

Machine Learning · Computer Science 2020-07-09 Amartya Sanyal , Puneet K Dokania , Varun Kanade , Philip H. S. Torr

Motivated by surprisingly good generalization properties of learned deep neural networks in overparameterized scenarios and by the related double descent phenomenon, this paper analyzes the relation between smoothness and low generalization…

Machine Learning · Computer Science 2021-10-29 Yuege Xie , Hung-Hsu Chou , Holger Rauhut , Rachel Ward

We propose a physics-based regularization technique for function learning, inspired by statistical mechanics. By drawing an analogy between optimizing the parameters of an interpolator and minimizing the energy of a system, we introduce…

Machine Learning · Computer Science 2025-08-20 Abhisek Ganguly , Alessandro Gabbana , Vybhav Rao , Sauro Succi , Santosh Ansumali

Recently, over-parameterized deep networks, with increasingly more network parameters than training samples, have dominated the performances of modern machine learning. However, when the training data is corrupted, it has been well-known…

Machine Learning · Computer Science 2022-08-04 Sheng Liu , Zhihui Zhu , Qing Qu , Chong You

Sparse neural networks are highly desirable in deep learning in reducing its complexity. The goal of this paper is to study how choices of regularization parameters influence the sparsity level of learned neural networks. We first derive…

Machine Learning · Computer Science 2024-08-07 Lixin Shen , Rui Wang , Yuesheng Xu , Mingsong Yan