Surbhi Goel
Surbhi Goel
Postdoctoral Researcher, Microsoft Research NYC
Verified email at microsoft.com - Homepage
Title
Cited by
Cited by
Year
Reliably learning the relu in polynomial time
S Goel, V Kanade, A Klivans, J Thaler
Conference on Learning Theory (COLT) 2017, 2016
1022016
Learning neural networks with two nonlinear layers in polynomial time
S Goel, A Klivans
Conference on Learning Theory (COLT) 2019, 2017
74*2017
Learning one convolutional layer with overlapping patches
S Goel, A Klivans, R Meka
International Conference on Machine Learning (ICML) 2018, 2018
602018
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
262020
Time/accuracy tradeoffs for learning a relu with respect to gaussian marginals
S Goel, S Karmalkar, A Klivans
arXiv preprint arXiv:1911.01462, 2019
262019
Eigenvalue decay implies polynomial-time learnability for neural networks
S Goel, A Klivans
Proceedings of the 31st International Conference on Neural Information …, 2017
262017
Approximation schemes for relu regression
I Diakonikolas, S Goel, S Karmalkar, AR Klivans, M Soltanolkotabi
Conference on Learning Theory, 1452-1485, 2020
222020
Statistical-query lower bounds via functional gradients
S Goel, A Gollakota, A Klivans
arXiv preprint arXiv:2006.15812, 2020
182020
Quantifying perceptual distortion of adversarial examples
M Jordan, N Manoj, S Goel, AG Dimakis
arXiv preprint arXiv:1902.08265, 2019
182019
Efficiently learning adversarially robust halfspaces with noise
O Montasser, S Goel, I Diakonikolas, N Srebro
International Conference on Machine Learning, 7010-7021, 2020
142020
Improved learning of one-hidden-layer convolutional neural networks with overlaps
SS Du, S Goel
arXiv preprint arXiv:1805.07798, 2018
132018
Learning Ising models with independent failures
S Goel, DM Kane, AR Klivans
Conference on Learning Theory (COLT) 2019, 2019
112019
Tight hardness results for training depth-2 ReLU networks
S Goel, A Klivans, P Manurangsi, D Reichman
arXiv preprint arXiv:2011.13550, 2020
72020
Learning ising and potts models with latent variables
S Goel
International Conference on Artificial Intelligence and Statistics, 3557-3566, 2020
6*2020
Learning Mixtures of Graphs from Epidemic Cascades
J Hoffmann, S Basu, S Goel, C Caramanis
International Conference on Machine Learning, 4342-4352, 2020
42020
Statistical Estimation from Dependent Data
Y Dagan, C Daskalakis, N Dikkala, S Goel, AV Kandiros
arXiv preprint arXiv:2107.09773, 2021
2*2021
Investigating the Role of Negatives in Contrastive Representation Learning
JT Ash, S Goel, A Krishnamurthy, D Misra
arXiv preprint arXiv:2106.09943, 2021
22021
Gone Fishing: Neural Active Learning with Fisher Embeddings
JT Ash, S Goel, A Krishnamurthy, S Kakade
arXiv preprint arXiv:2106.09675, 2021
12021
Acceleration via Fractal Learning Rate Schedules
N Agarwal, S Goel, C Zhang
arXiv preprint arXiv:2103.01338, 2021
12021
Anti-Concentrated Confidence Bonuses for Scalable Exploration
JT Ash, C Zhang, S Goel, A Krishnamurthy, S Kakade
arXiv preprint arXiv:2110.11202, 2021
2021
The system can't perform the operation now. Try again later.
Articles 1–20