Fartash Faghri
Fartash Faghri
University of Toronto, Vector Institute
Verified email at cs.toronto.edu
Cited by
Cited by
Technical report on the cleverhans v2.1.0 adversarial examples library
N Papernot, F Faghri, N Carlini, I Goodfellow, R Feinman, A Kurakin, ...
arXiv preprint arXiv:1610.00768, 2018
VSE++: Improving Visual-Semantic Embeddings with Hard Negatives
F Faghri, DJ Fleet, JR Kiros, S Fidler
British Machine Vision Conference (BMVC), 2018
Adversarial Spheres
J Gilmer, L Metz, F Faghri, SS Schoenholz, M Raghu, M Wattenberg, ...
International Conference on Learning Representations (ICLR), Workshop Track, 2018
Adversarial Manipulation of Deep Representations
S Sabour, Y Cao, F Faghri, DJ Fleet
International Conference on Learning Representations (ICLR), 2016
NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantization
A Ramezani-Kebrya, F Faghri, I Markov, V Aksenov, D Alistarh, DM Roy
Journal of Machine Learning Research 22 (114), 1-43, 2021
Adaptive gradient quantization for data-parallel sgd
F Faghri, I Tabrizian, I Markov, D Alistarh, D Roy, A Ramezani-Kebrya
arXiv preprint arXiv:2010.12460, 2020
A Study of Gradient Variance in Deep Learning
F Faghri, D Duvenaud, DJ Fleet, J Ba
arXiv preprint arXiv:2007.04532, 2020
SOAR: Second-Order Adversarial Regularization
A Ma, F Faghri, N Papernot, A Farahmand
arXiv e-prints, arXiv: 2004.01832, 2020
Graph based semi-supervised human pose estimation: When the output space comes to help
N Pourdamghani, HR Rabiee, F Faghri, MH Rohban
Pattern Recognition Letters 33 (12), 1529-1535, 2012
Bridging the Gap Between Adversarial Robustness and Optimization Bias
F Faghri, S Gowal, C Vasconcelos, DJ Fleet, F Pedregosa, N Le Roux
arXiv preprint arXiv:2102.08868, 2021
A Non-asymptotic comparison of SVRG and SGD: tradeoffs between compute and speed
Q Zhang, Y Wu, F Faghri, T Zhang, J Ba
The system can't perform the operation now. Try again later.
Articles 1–11