English
Related papers

Related papers: Implicit Bias in Deep Linear Discriminant Analysis

200 papers

Using weight decay to penalize the L2 norms of weights in neural networks has been a standard training practice to regularize the complexity of networks. In this paper, we show that a family of regularizers, including weight decay, is…

Machine Learning · Computer Science 2022-06-09 Ziquan Liu , Yufei Cui , Antoni B. Chan

Accurate image segmentation remains challenging, particularly in generating sharp, confident boundaries. While modern architectures have advanced the field, many of them still rely on standard loss functions like Cross-Entropy and Dice,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Adam Dawid Sztamborski , Raül Pérez-Gonzalo , Antonio Agudo

Conventional wisdom in deep learning states that increasing depth improves expressiveness but complicates optimization. This paper suggests that, sometimes, increasing depth can speed up optimization. The effect of depth on optimization is…

Machine Learning · Computer Science 2018-06-12 Sanjeev Arora , Nadav Cohen , Elad Hazan

We study gradient flow on the exponential loss for a classification problem with a one-layer softmax attention model, where the key and query weight matrices are trained separately. Under a separability assumption on the data, we show that…

Machine Learning · Computer Science 2024-03-14 Heejune Sheen , Siyu Chen , Tianhao Wang , Harrison H. Zhou

We study the implicit regularization effects of deep learning in tensor factorization. While implicit regularization in deep matrix and 'shallow' tensor factorization via linear and certain type of non-linear neural networks promotes…

Machine Learning · Computer Science 2022-07-27 Kais Hariz , Hachem Kadri , Stéphane Ayache , Maher Moakher , Thierry Artières

In recent years, understanding the implicit regularization of neural networks (NNs) has become a central task in deep learning theory. However, implicit regularization is itself not completely defined and well understood. In this work, we…

Machine Learning · Computer Science 2023-09-08 Leyang Zhang , Zhi-Qin John Xu , Tao Luo , Yaoyu Zhang

It remains a puzzle that why deep neural networks (DNNs), with more parameters than samples, often generalize well. An attempt of understanding this puzzle is to discover implicit biases underlying the training process of DNNs, such as the…

Machine Learning · Computer Science 2019-05-27 Yaoyu Zhang , Zhi-Qin John Xu , Tao Luo , Zheng Ma

Inspired by the remarkable success of large neural networks, there has been significant interest in understanding the generalization performance of over-parameterized models. Substantial efforts have been invested in characterizing how…

Machine Learning · Computer Science 2024-01-12 Haoyuan Sun , Khashayar Gatmiry , Kwangjun Ahn , Navid Azizan

Regularizing neural networks is important for anticipating model behavior in regions of the data space that are not well represented. In this work, we propose a regularization technique for enforcing a level of smoothness in the mapping…

Machine Learning · Computer Science 2025-03-05 Ali Hasan , Haoming Yang , Yuting Ng , Vahid Tarokh

We analyze the training dynamics for deep linear networks using a new metric - layer imbalance - which defines the flatness of a solution. We demonstrate that different regularization methods, such as weight decay or noise data…

Machine Learning · Computer Science 2020-07-21 Boris Ginsburg

In this work, we study the implications of the implicit bias of gradient flow on generalization and adversarial robustness in ReLU networks. We focus on a setting where the data consists of clusters and the correlations between cluster…

Machine Learning · Computer Science 2023-11-01 Spencer Frei , Gal Vardi , Peter L. Bartlett , Nathan Srebro

We investigate how shallow ReLU networks interpolate between known regions. Our analysis shows that empirical risk minimizers converge to a minimum norm interpolant as the number of data points and parameters tends to infinity when a weight…

Machine Learning · Statistics 2023-11-13 Jiyoung Park , Ian Pelakh , Stephan Wojtowytsch

Recent methods for imitation learning directly learn a $Q$-function using an implicit reward formulation rather than an explicit reward function. However, these methods generally require implicit reward regularization to improve stability…

Machine Learning · Computer Science 2023-03-02 Firas Al-Hafez , Davide Tateo , Oleg Arenz , Guoping Zhao , Jan Peters

It is believed that Gradient Descent (GD) induces an implicit bias towards good generalization in training machine learning models. This paper provides a fine-grained analysis of the dynamics of GD for the matrix sensing problem, whose goal…

Machine Learning · Computer Science 2023-01-30 Jikai Jin , Zhiyuan Li , Kaifeng Lyu , Simon S. Du , Jason D. Lee

In previous literature, backward error analysis was used to find ordinary differential equations (ODEs) approximating the gradient descent trajectory. It was found that finite step sizes implicitly regularize solutions because terms…

Machine Learning · Computer Science 2024-06-18 Matias D. Cattaneo , Jason M. Klusowski , Boris Shigida

Gradient descent for matrix factorization exhibits an implicit bias toward approximately low-rank solutions. While existing theories often assume the boundedness of iterates, empirically the bias persists even with unbounded sequences. This…

Machine Learning · Computer Science 2025-11-04 Yikun Hou , Suvrit Sra , Alp Yurtsever

We study implicit regularization when optimizing an underdetermined quadratic objective over a matrix $X$ with gradient descent on a factorization of $X$. We conjecture and provide empirical and theoretical evidence that with small enough…

Machine Learning · Statistics 2017-05-26 Suriya Gunasekar , Blake Woodworth , Srinadh Bhojanapalli , Behnam Neyshabur , Nathan Srebro

Direct loss minimization is a popular approach for learning predictors over structured label spaces. This approach is computationally appealing as it replaces integration with optimization and allows to propagate gradients in a deep net…

Machine Learning · Statistics 2021-06-15 Hedda Cohen Indelman , Tamir Hazan

We propose an optimization proxy in terms of iterative implicit gradient methods for solving constrained optimization problems with nonconvex loss functions. This framework can be applied to a broad range of machine learning settings,…

Optimization and Control · Mathematics 2025-10-14 Harshal D. Kaushik , Ming Jin

One of the mysteries in the success of neural networks is randomly initialized first order methods like gradient descent can achieve zero training loss even though the objective function is non-convex and non-smooth. This paper demystifies…

Machine Learning · Computer Science 2019-02-06 Simon S. Du , Xiyu Zhai , Barnabas Poczos , Aarti Singh