Srinadh Bhojanapalli

Citirano

	Sve	Od 2019.
Citati	7806	7087
H-indeks	28	26
i10-indeks	37	34

1700

850

425

1275

201520162017201820192020202120222023202472 121 155 325 554 830 1032 1332 1631 1689

Javni pristup

Prikaži sve

5 članaka

0 članaka

dostupno

nije dostupno

Na temelju uvjeta financiranja

Suautori

Nathan SrebroProfessor, TTIC and University of ChicagoPotvrđena adresa e-pošte na ttic.edu
Sujay SanghaviAssociate Professor, Electrical and Computer Engineering, University of Texas, AustinPotvrđena adresa e-pošte na mail.utexas.edu
Prateek JainGoogle Research IndiaPotvrđena adresa e-pošte na google.com
Ayan ChakrabartiGoogle ResearchPotvrđena adresa e-pošte na google.com
Anastasios KyrillidisAssociate Professor, Computer Science Department, Ken Kennedy Institute Fellow, Rice UniversityPotvrđena adresa e-pošte na rice.edu
Rachel WardUT Austin / Microsoft ResearchPotvrđena adresa e-pošte na math.utexas.edu
Yudong ChenAssociate Professor, University of Wisconsin-MadisonPotvrđena adresa e-pošte na wisc.edu
Zhiyuan LiAssistant Professor, Toyota Technological Institute at ChicagoPotvrđena adresa e-pošte na ttic.edu
Yann LeCunChief AI Scientist at Facebook & Silver Professor at the Courant Institute, New York UniversityPotvrđena adresa e-pošte na cs.nyu.edu
Constantine CaramanisProfessor of Electrical and Computer Engineering, UT AustinPotvrđena adresa e-pošte na utexas.edu
Dohyung ParkThe University of Texas at AustinPotvrđena adresa e-pošte na utexas.edu
Praneeth NetrapalliGoogle ResearchPotvrđena adresa e-pošte na google.com
Amir KalevInformation Sciences Institute, University of Southern CaliforniaPotvrđena adresa e-pošte na isi.edu
Nicolas BoumalEcole Polytechnique Fédérale de Lausanne (EPFL)Potvrđena adresa e-pošte na epfl.ch
Alexandros G DimakisProfessor, ECE University of Texas at AustinPotvrđena adresa e-pošte na austin.utexas.edu
Behnam NeyshaburMember of Technical Staff, Anthropic
David McAllesterProfessor, Toyota Technological Institute at ChicagoPotvrđena adresa e-pošte na ttic.edu

Prati

Srinadh Bhojanapalli

Research Scientist, Google Research

Potvrđena adresa e-pošte na google.com - Početna stranica

Machine learning Algorithms


Naslov Poredaj po navodima Poredaj po godini Poredaj po naslovu	Citirano Citirano	Godina
Exploring generalization in deep learning B Neyshabur, S Bhojanapalli, D McAllester, N Srebro Advances in neural information processing systems 30, 2017	1469	2017
Large batch optimization for deep learning: Training bert in 76 minutes Y You, J Li, S Reddi, J Hseu, S Kumar, S Bhojanapalli, X Song, J Demmel, ... arXiv preprint arXiv:1904.00962, 2019	1061	2019
A pac-bayesian approach to spectrally-normalized margin bounds for neural networks B Neyshabur, S Bhojanapalli, N Srebro arXiv preprint arXiv:1707.09564, 2017	687	2017
Towards understanding the role of over-parametrization in generalization of neural networks B Neyshabur, Z Li, S Bhojanapalli, Y LeCun, N Srebro arXiv preprint arXiv:1805.12076, 2018	622	2018
Implicit regularization in matrix factorization S Gunasekar, BE Woodworth, S Bhojanapalli, B Neyshabur, N Srebro Advances in neural information processing systems 30, 2017	557	2017
Global optimality of local search for low rank matrix recovery S Bhojanapalli, B Neyshabur, N Srebro Advances in Neural Information Processing Systems, 3873-3881, 2016	459	2016
Understanding robustness of transformers for image classification S Bhojanapalli, A Chakrabarti, D Glasner, D Li, T Unterthiner, A Veit Proceedings of the IEEE/CVF international conference on computer vision …, 2021	454	2021
Does label smoothing mitigate label noise? M Lukasik, S Bhojanapalli, A Menon, S Kumar International Conference on Machine Learning, 6448-6458, 2020	393	2020
Are transformers universal approximators of sequence-to-sequence functions? C Yun, S Bhojanapalli, AS Rawat, SJ Reddi, S Kumar arXiv preprint arXiv:1912.10077, 2019	359	2019
Dropping convexity for faster semi-definite optimization S Bhojanapalli, A Kyrillidis, S Sanghavi Conference on Learning Theory, 530-582, 2016	187	2016
Modifying memories in transformer models C Zhu, AS Rawat, M Zaheer, S Bhojanapalli, D Li, F Yu, S Kumar arXiv preprint arXiv:2012.00363, 2020	158	2020
Coherent matrix completion. Y Chen, S Bhojanapalli, S Sanghavi, R Ward arXiv preprint arXiv:1306.2979, 2013	151	2013
Universal matrix completion S Bhojanapalli, P Jain International Conference on Machine Learning, 1881-1889, 2014	130	2014
Stabilizing GAN training with multiple random projections B Neyshabur, S Bhojanapalli, A Chakrabarti arXiv preprint arXiv:1705.07831, 2017	108	2017
Completing any low-rank matrix, provably Y Chen, S Bhojanapalli, S Sanghavi, R Ward The Journal of Machine Learning Research 16 (1), 2999-3034, 2015	99	2015
Low-rank bottleneck in multi-head attention models S Bhojanapalli, C Yun, AS Rawat, S Reddi, S Kumar International conference on machine learning, 864-873, 2020	87	2020
Coping with label shift via distributionally robust optimisation J Zhang, A Menon, A Veit, S Bhojanapalli, S Kumar, S Sra arXiv preprint arXiv:2010.12230, 2020	76	2020
O (n) connections are expressive enough: Universal approximability of sparse transformers C Yun, YW Chang, S Bhojanapalli, AS Rawat, S Reddi, S Kumar Advances in Neural Information Processing Systems 33, 13783-13794, 2020	74	2020
The lazy neuron phenomenon: On emergence of activation sparsity in transformers Z Li, C You, S Bhojanapalli, D Li, AS Rawat, SJ Reddi, K Ye, F Chern, ... arXiv preprint arXiv:2210.06313, 2022	73	2022
A simple and effective positional encoding for transformers PC Chen, H Tsai, S Bhojanapalli, HW Chung, YW Chang, CS Ferng arXiv preprint arXiv:2104.08698, 2021	69	2021

Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.

Članci 1–20

Godišnji broj citata

Dvostruki navodi

Spojeni navodi

Dodavanje suautoraSuautori

Prati

Citirano

Suautori