Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Deconstructing Distributions: A Pointwise Framework of Learning



Gal Kaplun , Nikhil Ghosh , Saurabh Garg , Boaz Barak , Preetum Nakkiran

* GK and NG contributed equally 

   Access Paper or Ask Questions

Revisiting Model Stitching to Compare Neural Representations



Yamini Bansal , Preetum Nakkiran , Boaz Barak


   Access Paper or Ask Questions

Named Tensor Notation



David Chiang , Alexander M. Rush , Boaz Barak


   Access Paper or Ask Questions

For self-supervised learning, Rationality implies generalization, provably



Yamini Bansal , Gal Kaplun , Boaz Barak


   Access Paper or Ask Questions

Deep Double Descent: Where Bigger Models and More Data Hurt



Preetum Nakkiran , Gal Kaplun , Yamini Bansal , Tristan Yang , Boaz Barak , Ilya Sutskever

* G.K. and Y.B. contributed equally 

   Access Paper or Ask Questions

SGD on Neural Networks Learns Functions of Increasing Complexity



Preetum Nakkiran , Gal Kaplun , Dimitris Kalimeris , Tristan Yang , Benjamin L. Edelman , Fred Zhang , Boaz Barak

* Submitted to NeurIPS 2019 

   Access Paper or Ask Questions

(Nearly) Efficient Algorithms for the Graph Matching Problem on Correlated Random Graphs



Boaz Barak , Chi-Ning Chou , Zhixian Lei , Tselil Schramm , Yueqi Sheng


   Access Paper or Ask Questions

Noisy Tensor Completion via the Sum-of-Squares Hierarchy



Boaz Barak , Ankur Moitra

* 24 pages 

   Access Paper or Ask Questions

Dictionary Learning and Tensor Decomposition via the Sum-of-Squares Method



Boaz Barak , Jonathan A. Kelner , David Steurer


   Access Paper or Ask Questions

Sum-of-squares proofs and the quest toward optimal algorithms



Boaz Barak , David Steurer

* Survey. To appear in proceedings of ICM 2014 

   Access Paper or Ask Questions

1
2
>>