Moritz Hardt
Moritz Hardt
Verified email at berkeley.edu - Homepage
...
TitleCited byYear
Understanding deep learning requires rethinking generalization
C Zhang, S Bengio, M Hardt, B Recht, O Vinyals
ICLR 2017, 2017
11662017
Fairness through awareness
C Dwork, M Hardt, T Pitassi, O Reingold, R Zemel
ITCS 2012, 214-226, 2012
6562012
Equality of opportunity in supervised learning
M Hardt, E Price, N Srebro
NIPS 2016, 3315-3323, 2016
5842016
Train faster, generalize better: Stability of stochastic gradient descent
M Hardt, B Recht, Y Singer
ICML 2016, 1225-1234, 2015
3372015
A multiplicative weights mechanism for privacy-preserving data analysis
M Hardt, GN Rothblum
FOCS 2010, 61-70, 2010
2622010
A simple and practical algorithm for differentially private data release
M Hardt, K Ligett, F McSherry
NIPS 2012, 2348-2356, 2012
2612012
On the geometry of differential privacy
M Hardt, K Talwar
STOC 2010, 705-714, 2010
2482010
Understanding alternating minimization for matrix completion
M Hardt
FOCS 2014, 2014
185*2014
Preserving statistical validity in adaptive data analysis
C Dwork, V Feldman, M Hardt, T Pitassi, O Reingold, A Roth
STOC 2015, 2014
1762014
The reusable holdout: Preserving validity in adaptive data analysis
C Dwork, V Feldman, M Hardt, T Pitassi, O Reingold, A Roth
Science 349 (6248), 636-638, 2015
1732015
Identity matters in deep learning
M Hardt, T Ma
ICLR 2017, 2017
1632017
Avoiding discrimination through causal reasoning
N Kilbertus, MR Carulla, G Parascandolo, M Hardt, D Janzing, ...
NIPS 2017, 656-666, 2017
1272017
Privately releasing conjunctions and the statistical query barrier
A Gupta, M Hardt, A Roth, J Ullman
SIAM Journal on Computing 42 (4), 1494-1520, 2013
1142013
Generalization in adaptive data analysis and holdout reuse
C Dwork, V Feldman, M Hardt, T Pitassi, O Reingold, A Roth
NIPS 2015, 2350-2358, 2015
1092015
The noisy power method: A meta algorithm with applications
M Hardt, E Price
NIPS 2014, 2861-2869, 2014
108*2014
Sanity checks for saliency maps
J Adebayo, J Gilmer, M Muelly, I Goodfellow, M Hardt, B Kim
NeurIPS 2018, 2018
852018
Gradient descent learns linear dynamical systems
M Hardt, T Ma, B Recht
arXiv preprint arXiv:1609.05191, 2016
822016
Fast matrix completion without the condition number
M Hardt, M Wootters
COLT 2014, 638-678, 2014
782014
Beyond worst-case analysis in private singular vector computation
M Hardt, A Roth
STOC 2013, 331-340, 2013
752013
Preventing false discovery in interactive data analysis is hard
M Hardt, J Ullman
FOCS 2014, 454-463, 2014
712014
The system can't perform the operation now. Try again later.
Articles 1–20