Jerry Li
Jerry Li
Microsoft Research AI
Email verificata su mit.edu - Home page
TitoloCitata daAnno
QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding
D Alistarh, D Grubic, J Li, R Tomioka, M Vojnovic
Advances in Neural Information Processing Systems, 1707-1718, 2017
261*2017
Robust estimators in high-dimensions without the computational intractability
I Diakonikolas, G Kamath, D Kane, J Li, A Moitra, A Stewart
SIAM Journal on Computing 48 (2), 742-864, 2019
1472019
The spraylist: A scalable relaxed priority queue
D Alistarh, J Kopinsky, J Li, N Shavit
Proceedings of the 20th ACM SIGPLAN Symposium on Principles and Practice of …, 2015
822015
Zipml: Training linear models with end-to-end low precision, and a little bit of deep learning
H Zhang, J Li, K Kara, D Alistarh, J Liu, C Zhang
Proceedings of the 34th International Conference on Machine Learning-Volume …, 2017
80*2017
Being robust (in high dimensions) can be practical
I Diakonikolas, G Kamath, DM Kane, J Li, A Moitra, A Stewart
Proceedings of the 34th International Conference on Machine Learning-Volume …, 2017
572017
Sever: A robust meta-algorithm for stochastic optimization
I Diakonikolas, G Kamath, DM Kane, J Li, J Steinhardt, A Stewart
arXiv preprint arXiv:1803.02815, 2018
532018
Computationally efficient robust sparse estimation in high dimensions
S Balakrishnan, SS Du, J Li, A Singh
Conference on Learning Theory, 169-212, 2017
53*2017
Robustly learning a gaussian: Getting optimal error, efficiently
I Diakonikolas, G Kamath, DM Kane, J Li, A Moitra, A Stewart
Proceedings of the Twenty-Ninth Annual ACM-SIAM Symposium on Discrete …, 2018
522018
Sample-optimal density estimation in nearly-linear time
J Acharya, I Diakonikolas, J Li, L Schmidt
Proceedings of the Twenty-Eighth Annual ACM-SIAM Symposium on Discrete …, 2017
462017
Byzantine stochastic gradient descent
D Alistarh, Z Allen-Zhu, J Li
Advances in Neural Information Processing Systems, 4613-4623, 2018
422018
Mixture models, robustness, and sum of squares proofs
SB Hopkins, J Li
Proceedings of the 50th Annual ACM SIGACT Symposium on Theory of Computing …, 2018
392018
On the limitations of first-order approximation in gan dynamics
J Li, A Madry, J Peebles, L Schmidt
arXiv preprint arXiv:1706.09884, 2017
38*2017
Spectral signatures in backdoor attacks
B Tran, J Li, A Madry
Advances in Neural Information Processing Systems, 8000-8010, 2018
372018
Fast and near-optimal algorithms for approximating distributions by histograms
J Acharya, I Diakonikolas, C Hegde, JZ Li, L Schmidt
Proceedings of the 34th ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of …, 2015
262015
Robust and proper learning for mixtures of gaussians via systems of polynomial inequalities
J Li, L Schmidt
Conference on Learning Theory, 1302-1382, 2017
25*2017
Communication-efficient distributed learning of discrete distributions
I Diakonikolas, E Grigorescu, J Li, A Natarajan, K Onak, L Schmidt
Advances in Neural Information Processing Systems, 6391-6401, 2017
232017
Lower bounds for exact model counting and applications in probabilistic databases
P Beame, J Li, S Roy, D Suciu
arXiv preprint arXiv:1309.6815, 2013
222013
Provably robust deep learning via adversarially trained smoothed classifiers
H Salman, J Li, I Razenshteyn, P Zhang, H Zhang, S Bubeck, G Yang
Advances in Neural Information Processing Systems, 11289-11300, 2019
172019
The power of choice in priority scheduling
D Alistarh, J Kopinsky, J Li, G Nadiradze
Proceedings of the ACM Symposium on Principles of Distributed Computing, 283-292, 2017
142017
Model counting of query expressions: Limitations of propositional methods
P Beame, J Li, S Roy, D Suciu
arXiv preprint arXiv:1312.4125, 2013
132013
Il sistema al momento non può eseguire l'operazione. Riprova più tardi.
Articoli 1–20