Følg
Nicolas Flammarion
Nicolas Flammarion
Verificeret mail på epfl.ch - Startside
Titel
Citeret af
Citeret af
År
Square attack: a query-efficient black-box adversarial attack via random search
M Andriushchenko, F Croce, N Flammarion, M Hein
ECCV, 2020
8272020
Robustbench: a standardized adversarial robustness benchmark
F Croce, M Andriushchenko, V Sehwag, E Debenedetti, N Flammarion, ...
arXiv preprint arXiv:2010.09670, 2020
5052020
Understanding and Improving Fast Adversarial Training
M Andriushchenko, N Flammarion
Advances in Neural Information Processing Systems, 2020
2512020
Sampling can be faster than optimization
YA Ma, Y Chen, C Jin, N Flammarion, MI Jordan
Proceedings of the National Academy of Sciences 116 (42), 20881-20885, 2019
1882019
Harder, better, faster, stronger convergence rates for least-squares regression
A Dieuleveut, N Flammarion, F Bach
The Journal of Machine Learning Research 18 (1), 3520-3570, 2017
1642017
From averaging to acceleration, there is only a step-size
N Flammarion, F Bach
Conference on Learning Theory, 658-695, 2015
1442015
Is there an analog of Nesterov acceleration for gradient-based MCMC?
YA Ma, NS Chatterji, X Cheng, N Flammarion, PL Bartlett, MI Jordan
1402021
Averaging stochastic gradient descent on Riemannian manifolds
N Tripuraneni, N Flammarion, F Bach, MI Jordan
Conference On Learning Theory, 2018
1072018
On the theory of variance reduction for stochastic gradient Monte Carlo
NS Chatterji, N Flammarion, YA Ma, PL Bartlett, MI Jordan
International Conference on Machine Learning, 764--773, 2018
962018
On the effectiveness of adversarial training against common corruptions
K Kireev, M Andriushchenko, N Flammarion
Uncertainty in Artificial Intelligence, 1012-1021, 2022
912022
Towards understanding sharpness-aware minimization
M Andriushchenko, N Flammarion
International Conference on Machine Learning, 639-668, 2022
862022
Implicit bias of sgd for diagonal linear networks: a provable benefit of stochasticity
S Pesme, L Pillaud-Vivien, N Flammarion
Advances in Neural Information Processing Systems 34, 29218-29230, 2021
792021
Escaping from saddle points on Riemannian manifolds
Y Sun, N Flammarion, M Fazel
Advances in Neural Information Processing Systems, 7276-7286, 2019
782019
Fast mean estimation with sub-Gaussian rates
Y Cherapanamjeri, N Flammarion, PL Bartlett
Conference on Learning Theory, 786--806, 2019
772019
Sparse-rs: a versatile framework for query-efficient sparse black-box adversarial attacks
F Croce, M Andriushchenko, ND Singh, N Flammarion, M Hein
Proceedings of the AAAI Conference on Artificial Intelligence 36 (6), 6437-6445, 2022
742022
Optimal rates of statistical seriation
N Flammarion, C Mao, P Rigollet
692019
Improved bounds for discretization of Langevin diffusions: Near-optimal rates without convexity
W Mou, N Flammarion, MJ Wainwright, PL Bartlett
Bernoulli 28 (3), 1577-1601, 2022
592022
Sgd with large step sizes learns sparse features
M Andriushchenko, AV Varre, L Pillaud-Vivien, N Flammarion
International Conference on Machine Learning, 903-925, 2023
382023
Optimal robust linear regression in nearly linear time
Y Cherapanamjeri, E Aras, N Tripuraneni, MI Jordan, N Flammarion, ...
arXiv preprint arXiv:2007.08137, 2020
382020
Gradient flow dynamics of shallow relu networks for square loss and orthogonal inputs
E Boursier, L Pillaud-Vivien, N Flammarion
Advances in Neural Information Processing Systems 35, 20105-20118, 2022
362022
Systemet kan ikke foretage handlingen nu. Prøv igen senere.
Artikler 1–20