paper-with-me

Papers

EarlyStopping: Implicit Regularization for Iterative Learning Procedures in Python

2025-03-20 · Eric Ziebell, Ratmir Miftachov, Bernhard Stankewitz, Laura Hucker

Iterative learning procedures are ubiquitous in machine learning and modern statistics. Regularision is typically required to prevent inflating the expected loss of a procedure in later iterations via the propagation of noise inherent in the data. Significant emphasis has been placed on achieving this regularisation implicitly by stopping procedures early. The EarlyStopping-package provides a toolbox of (in-sample) sequential early stopping rules for several well-known iterative estimation procedures, such as truncated SVD, Landweber (gradient descent), conjugate gradient descent, L2-boosting and regression trees. One of the central features of the package is that the algorithms allow the specification of the true data-generating process and keep track of relevant theoretical quantities. In this paper, we detail the principles governing the implementation of the EarlyStopping-package and provide a survey of recent foundational advances in the theoretical literature. We demonstrate how to use the EarlyStopping-package to explore core features of implicit regularisation and replicate results from the literature.

📄 PDF Abstract BibTeX arXiv:2503.16753

Code (1)

EarlyStop/EarlyStopping 공식 구현

Methods 이 논문이 사용한 방법론

Early Stopping Early Stopping is a regularization technique for deep neural networks that stops training when parameter updates no longer begin to yield improves on a validation set. In…

Similar Papers 제목 키워드 기반

Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval, Matrix Completion, and Blind Deconvolution

2017-11-28 · ICML 2018 · Cong Ma, Kaizheng Wang, Yuejie Chi, Yuxin Chen

Recent years have seen a flurry of activities in designing provably efficient nonconvex procedures for solving statistical estimation problems. Due to the highly nonconvex nature of the empirical loss, state-of-the-art p…

Low-Rank Matrix CompletionMatrix CompletionRetrieval

Towards stability and optimality in stochastic gradient descent

2015-05-10 · Panos Toulis, Dustin Tran, Edoardo M. Airoldi

Iterative procedures for parameter estimation based on stochastic gradient descent allow the estimation to scale to massive data sets. However, in both theory and practice, they suffer from numerical instability. Moreove…

parameter estimation

Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval and Matrix Completion

2018-07-01 · ICML 2018 7 · Cong Ma, Kaizheng Wang, Yuejie Chi, Yuxin Chen

Recent years have seen a flurry of activities in designing provably efficient nonconvex optimization procedures for solving statistical estimation problems. For various problems like phase retrieval or low-rank matr…

Low-Rank Matrix CompletionMatrix CompletionRetrieval

Iterative regularization for low complexity regularizers

2022-02-01 · Cesare Molinari, Mathurin Massias, Lorenzo Rosasco, Silvia Villa

Iterative regularization exploits the implicit bias of an optimization algorithm to regularize ill-posed problems. Constructing algorithms with such built-in regularization mechanisms is a classic challenge in inverse pr…

Evidence against implicitly recurrent computations in residual neural networks

2021-01-01 · Samuel Lippl, Benjamin Peters, Nikolaus Kriegeskorte

Recent work on residual neural networks (ResNets) has suggested that a ResNet's deep feedforward computation may be characterized as implicitly recurrent in that it iteratively refines the same representation like a recu…