Learning data manifolds with a cutting plane method

DOI10.1162/NECO_A_01119MaRDI QIDQ5157241zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Sueyeon Chung, Uri Cohen, Haim Sompolinsky, Daniel D. Lee

Publication date 12 October 2021

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1705.09944

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Statistics on manifolds (62R30) Learning and adaptive systems in artificial intelligence (68T05) Applications of mathematical programming (90C90)

Abstract: We consider the problem of classifying data manifolds where each manifold represents invariances that are parameterized by continuous degrees of freedom. Conventional data augmentation methods rely upon sampling large numbers of training examples from these manifolds; instead, we propose an iterative algorithm called M_{CP} based upon a cutting-plane approach that efficiently solves a quadratic semi-infinite programming problem to find the maximum margin solution. We provide a proof of convergence as well as a polynomial bound on the number of iterations required for a desired tolerance in the objective function. The efficiency and performance of M_{CP} are demonstrated in high-dimensional simulations and on image manifolds generated from the ImageNet dataset. Our results indicate that M_{CP} is able to rapidly learn good classifiers and shows superior generalization performance compared with conventional maximum margin methods using data augmentation methods.

Recommendations

• Semi-supervised learning on Riemannian manifolds
• A study of the classification of low-dimensional data with supervised manifold learning
• Unsupervised Learning of Curved Manifolds
• Manifold regularization: a geometric framework for learning from labeled and unlabeled examples
• On active learning methods for manifold data

Cites work

• A Central Cutting Plane Algorithm for Convex Semi-Infinite Programming Problems
• A new quadratic semi-infinite programming algorithm based on dual parametrization
• Cutting planes in integer and mixed integer programming
• scientific article; zbMATH DE number 1332320 (Why is no real title available?)
• scientific article; zbMATH DE number 1950576 (Why is no real title available?)
• Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
• Large margin methods for structured and interdependent output variables
• Manifold regularization: a geometric framework for learning from labeled and unlabeled examples
• On Projection Algorithms for Solving Convex Feasibility Problems
• Solving quadratic semi-infinite programming problems by using relaxed cutting-plane scheme
• Unsupervised learning of invariant representations

Cited in

(2)

• Data sharpening on unknown manifold
• An algorithm for learning representations of models with scarce data

Describes a project that uses

Uses Software

• ImageNet
• AlexNet
• RSVM

This page was built for publication: Learning data manifolds with a cutting plane method

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5157241)