Yamini Bansal

200

100

150

201820192020202141 81 196 65

Public access

2 articles

0 articles

available

not available

Based on funding mandates

David CoxIBM Director, MIT-IBM Watson AI Lab, IBM ResearchVerified email at ibm.com
Andrew SaxeSir Henry Dale Fellow & Associate Professor, Department of Experimental Psychology, OxfordVerified email at psy.ox.ac.uk
Gal KaplunPhD Student at Harvard UniversityVerified email at g.harvard.edu
Boaz BarakHarvard UniversityVerified email at boazbarak.org
Preetum NakkiranHarvard UniversityVerified email at cs.harvard.edu
Joel DapelloBioengineering PhD student, Harvard UniversityVerified email at g.harvard.edu

Yamini Bansal

Verified email at g.harvard.edu


Title Sort by citations Sort by year Sort by title	Cited by Cited by	Year
On the information bottleneck theory of deep learning AM Saxe, Y Bansal, J Dapello, M Advani, A Kolchinsky, BD Tracey, ... Journal of Statistical Mechanics: Theory and Experiment 2019 (12), 124020, 2019	212	2019
Deep Double Descent: Where Bigger Models and More Data Hurt P Nakkiran, G Kaplun, Y Bansal, T Yang, B Barak, I Sutskever arXiv preprint arXiv:1912.02292, 2019	157	2019
Minnorm training: an algorithm for training over-parameterized deep neural networks Y Bansal, M Advani, DD Cox, AM Saxe arXiv preprint arXiv:1806.00730, 2018	15*	2018
For self-supervised learning, Rationality implies generalization, provably Y Bansal, G Kaplun, B Barak arXiv preprint arXiv:2010.08508, 2020	2	2020
Distributional Generalization: A New Kind of Generalization P Nakkiran, Y Bansal arXiv preprint arXiv:2009.08092, 2020	1	2020
Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modelling A Srivastava, Y Bansal, Y Ding, C Hurwitz, K Xu, B Egger, P Sattigeri, ... arXiv preprint arXiv:2010.13187, 2020		2020

The system can't perform the operation now. Try again later.

Articles 1–6

Citations per year