paper-with-me

Papers

Generalization in Machine Learning via Analytical Learning Theory

2018-02-21 · Kenji Kawaguchi, Yoshua Bengio, Vikas Verma, Leslie Pack Kaelbling

This paper introduces a novel measure-theoretic theory for machine learning that does not require statistical assumptions. Based on this theory, a new regularization method in deep learning is derived and shown to outperform previous methods in CIFAR-10, CIFAR-100, and SVHN. Moreover, the proposed theory provides a theoretical basis for a family of practically successful regularization methods in deep learning. We discuss several consequences of our results on one-shot learning, representation learning, deep learning, and curriculum learning. Unlike statistical learning theory, the proposed learning theory analyzes each problem instance individually via measure theory, rather than a set of problem instances via statistics. As a result, it provides different types of results and insights when compared to statistical learning theory.

📄 PDF Abstract BibTeX arXiv:1802.07426

Code (2)

Learning-and-Intelligent-Systems/Analytical-Learning-Theory 공식 구현 pytorch
Learning-and-Intelligent-Systems/DualCutout 공식 구현 pytorch

Tasks

BIG-bench Machine LearningDeep LearningLearning TheoryOne-Shot LearningRepresentation Learning

Similar Papers 제목 키워드 기반

Out-of-Distribution Generalization in Kernel Regression

2021-06-04 · NeurIPS 2021 12 · Abdulkadir Canatar, Blake Bordelon, Cengiz Pehlevan

In real word applications, data generating process for training a machine learning model often differs from what the model encounters in the test stage. Understanding how and whether machine learning models generalize un…

BIG-bench Machine LearningOut-of-Distribution Generalizationregression

QT-Routenet: Improved GNN generalization to larger 5G networks by fine-tuning predictions from queueing theory

2022-07-13 · Bruno Klaus de Aquino Afonso, Lilian Berton

In order to promote the use of machine learning in 5G, the International Telecommunication Union (ITU) proposed in 2021 the second edition of the ITU AI/ML in 5G challenge, with over 1600 participants from 82 countries. …

Graph Neural Network

A mathematical theory of balancing relational generalization and memorization

2026-05-21 · Luke Cheng, Samuel Lippl arxiv

Humans, animals, and modern machine learning models exhibit impressive abilities to learn complex behaviors and generalize these behaviors to unseen situations. This ability requires us to learn rules and regularities th…

Neural tangent kernel eigenvalues accurately predict generalization

2021-09-29 · James B Simon, Madeline Dickens, Michael Deweese

Finding a quantitative theory of neural network generalization has long been a central goal of deep learning research. We extend recent results to demonstrate that, by examining the eigensystem of a neural network's "neu…

Inductive Bias

Spectral Bias and Task-Model Alignment Explain Generalization in Kernel Regression and Infinitely Wide Neural Networks

2020-06-23 · Abdulkadir Canatar, Blake Bordelon, Cengiz Pehlevan

Generalization beyond a training dataset is a main goal of machine learning, but theoretical understanding of generalization remains an open problem for many models. The need for a new theory is exacerbated by recent obs…

BIG-bench Machine LearningInductive Biasregression