paper-with-me

홈 › Papers

Incremental Learning in Diagonal Linear Networks

2022-08-31 · Raphaël Berthier

Diagonal linear networks (DLNs) are a toy simplification of artificial neural networks; they consist in a quadratic reparametrization of linear regression inducing a sparse implicit regularization. In this paper, we describe the trajectory of the gradient flow of DLNs in the limit of small initialization. We show that incremental learning is effectively performed in the limit: coordinates are successively activated, while the iterate is the minimizer of the loss constrained to have support on the active coordinates only. This shows that the sparse implicit regularization of DLNs decreases with time. This work is restricted to the underparametrized regime with anti-correlated features for technical reasons.

📄 PDF Abstract BibTeX arXiv:2208.14673

Code (0)

등록된 구현이 없습니다.

Tasks

Incremental Learningregression

Methods 이 논문이 사용한 방법론

Linear Regression Linear Regression is a method for modelling a relationship between a dependent variable and independent variables. These models can be fit with numerous approaches. The most…

Similar Papers 제목 키워드 기반

The Implicit Bias of Depth: How Incremental Learning Drives Generalization

2019-09-26 · ICLR 2020 1 · Daniel Gissin, Shai Shalev-Shwartz, Amit Daniely

A leading hypothesis for the surprising generalization of neural networks is that the dynamics of gradient descent bias the model towards simple solutions, by searching through the solution space in an incremental order …

Binary ClassificationIncremental Learning

Precise Dynamics of Diagonal Linear Networks: A Unifying Analysis by Dynamical Mean-Field Theory

2025-10-02 · Sota Nishiyama, Masaaki Imaizumi arxiv

Diagonal linear networks (DLNs) are a tractable model that captures several nontrivial behaviors in neural network training, such as initialization-dependent solutions and incremental learning. These phenomena are typica…

Incremental Learning

Saddle-to-Saddle Dynamics in Diagonal Linear Networks

2023-04-02 · NeurIPS 2023 11

In this paper we fully describe the trajectory of gradient flow over diagonal linear networks in the limit of vanishing initialisation. We show that the limiting flow successively jumps from a saddle of the training loss…

ARCIncremental Learning

Diagonal Linear Networks and the Lasso Regularization Path

2025-09-23 · Raphaël Berthier arxiv

Diagonal linear networks are neural networks with linear activation and diagonal weight matrices. Their theoretical interest is that their implicit regularization can be rigorously analyzed: from a small initialization, …

It's Enough: Relaxing Diagonal Constraints in Linear Autoencoders for Recommendation

2023-05-22 · Jaewan Moon, Hye-Young Kim, Jongwuk Lee

Linear autoencoder models learn an item-to-item weight matrix via convex optimization with L2 regularization and zero-diagonal constraints. Despite their simplicity, they have shown remarkable performance compared to sop…

DenoisingL2 Regularization