paper-with-me

Papers

Generalization Properties and Implicit Regularization for Multiple Passes SGM

2016-05-26 · Junhong Lin, Raffaello Camoriano, Lorenzo Rosasco

We study the generalization properties of stochastic gradient methods for learning with convex loss functions and linearly parameterized functions. We show that, in the absence of penalizations or constraints, the stability and approximation properties of the algorithm can be controlled by tuning either the step-size or the number of passes over the data. In this view, these parameters can be seen to control a form of implicit regularization. Numerical results complement the theoretical findings.

📄 PDF Abstract BibTeX arXiv:1605.08375

Code (1)

Adeikalam/Generalization-Properties-of-Algorithms-in-ML

Similar Papers 제목 키워드 기반

Can Implicit Bias Explain Generalization? Stochastic Convex Optimization as a Case Study

2020-03-13 · NeurIPS 2020 12 · Assaf Dauber, Meir Feder, Tomer Koren, Roi Livni

The notion of implicit bias, or implicit regularization, has been suggested as a means to explain the surprising generalization ability of modern-days overparameterized learning algorithms. This notion refers to the tend…

On the Generalization Effects of DenseNet Model Structures

2018-01-01 · ICLR 2018 1 · Yin Liu, Vincent Chen

Modern neural network architectures take advantage of increasingly deeper layers, and various advances in their structure to achieve better performance. While traditional explicit regularization techniques like dropout, …

Data Augmentationmodel

Stochastic Training is Not Necessary for Generalization

2021-09-29 · ICLR 2022 4 · Jonas Geiping, Micah Goldblum, Phillip E. Pope, Michael Moeller 외

It is widely believed that the implicit regularization of SGD is fundamental to the impressive generalization behavior we observe in neural networks. In this work, we demonstrate that non-stochastic full-batch training c…

Data Augmentation

Mirror, Mirror of the Flow: How Does Regularization Shape Implicit Bias?

2025-04-17 · Tom Jacobs, Chao Zhou, Rebekka Burkholz

Implicit bias plays an important role in explaining how overparameterized models generalize well. Explicit regularization like weight decay is often employed in addition to prevent overfitting. While both concepts have b…

Optimal Rates for Multi-pass Stochastic Gradient Methods

2016-05-28 · Junhong Lin, Lorenzo Rosasco

We analyze the learning properties of the stochastic gradient method when multiple passes over the data and mini-batches are allowed. We study how regularization properties are controlled by the step-size, the number of …