Web: http://arxiv.org/abs/2206.07758

June 17, 2022, 1:12 a.m. | Niv Haim, Gal Vardi, Gilad Yehudai, Ohad Shamir, Michal Irani

stat.ML updates on arXiv.org arxiv.org

Understanding to what extent neural networks memorize training data is an
intriguing question with practical and theoretical implications. In this paper
we show that in some cases a significant fraction of the training data can in
fact be reconstructed from the parameters of a trained neural network
classifier. We propose a novel reconstruction scheme that stems from recent
theoretical results about the implicit bias in training neural networks with
gradient-based methods. To the best of our knowledge, our results are …

arxiv data lg networks neural neural networks training training data

More from arxiv.org / stat.ML updates on arXiv.org

Machine Learning Researcher - Saalfeld Lab

@ Howard Hughes Medical Institute - Chevy Chase, MD | Ashburn, Virginia

Project Director, Machine Learning in US Health

@ ideas42.org | Remote, US

Data Science Intern

@ NannyML | Remote

Machine Learning Engineer NLP/Speech

@ Play.ht | Remote

Research Scientist, 3D Reconstruction

@ Yembo | Remote, US

Clinical Assistant or Associate Professor of Management Science and Systems

@ University at Buffalo | Buffalo, NY