Surbhi Goel

Cited by

	All	Since 2020
Citations	1832	1692
h-index	21	20
i10-index	29	28

620

310

155

465

20172018201920202021202220232024202517 51 68 120 165 224 447 619 116

Public access

View all

13 articles

0 articles

available

not available

Based on funding mandates

Co-authors

Adam KlivansProfessor of Computer Science, University of Texas at AustinVerified email at cs.utexas.edu
Cyril ZhangMicrosoft Research NYCVerified email at microsoft.com
Sham M KakadeHarvard UniversityVerified email at seas.harvard.edu
Jordan T. AshMicrosoft Research NYCVerified email at princeton.edu
Akshay KrishnamurthyUniversity of Massachusetts AmherstVerified email at cs.umass.edu
Benjamin L. EdelmanHarvard UniversityVerified email at g.harvard.edu
Bingbin LiuPostdoc research fellow at Simons Institute; PhD from Carnegie Mellon UniversityVerified email at cs.cmu.edu
Sushrut KarmalkarUniversity of Wisconsin-MadisonVerified email at cs.utexas.edu
Eran MalachKempner Institute, HarvardVerified email at fas.harvard.edu
Dipendra MisraStaff Research Scientist, Mosaic Team, DatabricksVerified email at databricks.com
Aravind GollakotaAppleVerified email at apple.com
Justin ThalerGeorgetown UniversityVerified email at georgetown.edu
Varun KanadeUniversity of OxfordVerified email at cs.ox.ac.uk
Raghu MekaUniversity of California, Los AngelesVerified email at cs.ucla.edu
Ilias DiakonikolasUniversity of Wisconsin-MadisonVerified email at wisc.edu
Boaz BarakHarvard UniversityVerified email at boazbarak.org
Nikunj SaunshiResearch Scientist, GoogleVerified email at google.com
Sanjeev AroraProfessor of Computer Science, Princeton UniversityVerified email at princeton.edu
Zhihan JinETH ZurichVerified email at student.ethz.ch
Nathan SrebroProfessor, TTIC and University of ChicagoVerified email at ttic.edu

Surbhi Goel

Assistant Professor, University of Pennsylvania

Verified email at cis.upenn.edu - Homepage

Learning Theory Machine Learning


Title Sort by citations Sort by year Sort by title	Cited by Cited by	Year
Transformers learn shortcuts to automata B Liu, JT Ash, S Goel, A Krishnamurthy, C Zhang arXiv preprint arXiv:2210.10749, 2022	200	2022
Hidden progress in deep learning: Sgd learns parities near the computational limit B Barak, B Edelman, S Goel, S Kakade, E Malach, C Zhang Advances in Neural Information Processing Systems 35, 21750-21764, 2022	153	2022
Reliably learning the relu in polynomial time S Goel, V Kanade, A Klivans, J Thaler Conference on Learning Theory (COLT) 2017, 2016	148	2016
Inductive biases and variable creation in self-attention mechanisms BL Edelman, S Goel, S Kakade, C Zhang International Conference on Machine Learning, 5793-5831, 2022	147	2022
Understanding contrastive learning requires incorporating inductive biases N Saunshi, J Ash, S Goel, D Misra, C Zhang, S Arora, S Kakade, ... International Conference on Machine Learning, 19250-19286, 2022	131	2022
Learning neural networks with two nonlinear layers in polynomial time S Goel, A Klivans Conference on Learning Theory (COLT) 2019, 2017	117*	2017
Gone fishing: Neural active learning with fisher embeddings J Ash, S Goel, A Krishnamurthy, S Kakade Advances in Neural Information Processing Systems 34, 8927-8939, 2021	89	2021
Learning one convolutional layer with overlapping patches S Goel, A Klivans, R Meka International Conference on Machine Learning (ICML) 2018, 2018	89	2018
Superpolynomial lower bounds for learning one-layer neural networks using gradient descent S Goel, A Gollakota, Z Jin, S Karmalkar, A Klivans International Conference on Machine Learning, 3587-3596, 2020	85	2020
Statistical-query lower bounds via functional gradients S Goel, A Gollakota, A Klivans Advances in Neural Information Processing Systems 33, 2147-2158, 2020	68	2020
Approximation schemes for relu regression I Diakonikolas, S Goel, S Karmalkar, AR Klivans, M Soltanolkotabi Conference on learning theory, 1452-1485, 2020	62	2020
Time/accuracy tradeoffs for learning a relu with respect to gaussian marginals S Goel, S Karmalkar, A Klivans Advances in neural information processing systems 32, 2019	60	2019
Investigating the role of negatives in contrastive representation learning JT Ash, S Goel, A Krishnamurthy, D Misra arXiv preprint arXiv:2106.09943, 2021	56	2021
Exposing attention glitches with flip-flop language modeling B Liu, J Ash, S Goel, A Krishnamurthy, C Zhang Advances in Neural Information Processing Systems 36, 2023	50	2023
Tight hardness results for training depth-2 ReLU networks S Goel, A Klivans, P Manurangsi, D Reichman arXiv preprint arXiv:2011.13550, 2020	49	2020
The evolution of statistical induction heads: In-context learning markov chains E Edelman, N Tsilivis, B Edelman, E Malach, S Goel Advances in Neural Information Processing Systems 37, 64273-64311, 2024	40	2024
Efficiently learning adversarially robust halfspaces with noise O Montasser, S Goel, I Diakonikolas, N Srebro International Conference on Machine Learning, 7010-7021, 2020	37	2020
Eigenvalue decay implies polynomial-time learnability for neural networks S Goel, A Klivans Advances in Neural Information Processing Systems 30, 2017	30	2017
Acceleration via fractal learning rate schedules N Agarwal, S Goel, C Zhang International Conference on Machine Learning, 87-99, 2021	29	2021
Quantifying perceptual distortion of adversarial examples M Jordan, N Manoj, S Goel, AG Dimakis arXiv preprint arXiv:1902.08265, 2019	29	2019

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

Articles 1–20

Citations per year

Duplicate citations

Merged citations

Add co-authorsCo-authors

Follow

Cited by

Co-authors