Classification Logit Two-Sample Testing by Neural Networks for Differentiating Near Manifold Densities-Reference-Cited by-同舟云学术

Classification Logit Two-Sample Testing by Neural Networks for Differentiating Near Manifold Densities

Author:

Cheng Xiuyuan¹,Cloninger Alexander²^ORCID

Affiliation:

1. Department of Mathematics, Duke University, Durham, NC, USA

2. Department of Mathematics, Halicioğlu Data Science Institute, University of California at San Diego, San Diego, CA, USA

Funder

NSF

NIH

Alfred P. Sloan Foundation

Russel Sage Foundation

Intel Research

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Library and Information Sciences,Computer Science Applications,Information Systems

Link

Reference71 articles.

1. Gradient descent provably optimizes over-parameterized neural networks;du;Proc Int Conf Learn Represent,2018

2. Stochastic gradient descent for non-smooth optimization: Convergence results and optimal averaging schemes;shamir;Proc Int Conf Mach Learn,2013

3. Linking losses for density ratio and class-probability estimation;menon;Proc Int Conf Mach Learn,2016

4. Discriminative learning under covariate shift;bickel;J Mach Learn Res,2009

Cited by 3 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献