Alexander Rakhlin
Alexander Rakhlin
Professor, MIT
Adresse e-mail validée de - Page d'accueil
Citée par
Citée par
Making gradient descent optimal for strongly convex stochastic optimization
A Rakhlin, O Shamir, K Sridharan
International Conference on Machine Learning (ICML), 2011
Size-independent sample complexity of neural networks
N Golowich, A Rakhlin, O Shamir
Conference On Learning Theory, 297-299, 2018
Non-convex learning via stochastic gradient langevin dynamics: a nonasymptotic analysis
M Raginsky, A Rakhlin, M Telgarsky
Conference on Learning Theory, 1674-1703, 2017
Competing in the dark: An efficient algorithm for bandit linear optimization
JD Abernethy, E Hazan, A Rakhlin
Optimization, learning, and games with predictable sequences
S Rakhlin, K Sridharan
Advances in Neural Information Processing Systems 26, 2013
Online learning with predictable sequences
A Rakhlin, K Sridharan
Conference on Learning Theory, 993-1019, 2013
Just interpolate: Kernel “ridgeless” regression can generalize
T Liang, A Rakhlin
The Annals of Statistics 48 (3), 1329-1347, 2020
Adaptive online gradient descent
PL Bartlett, E Hazan, A Rakhlin
Advances in Neural Information Processing Systems, 65-72, 2007
Online optimization: Competing with dynamic comparators
A Jadbabaie, A Rakhlin, S Shahrampour, K Sridharan
Artificial Intelligence and Statistics, 398-406, 2015
Stochastic convex optimization with bandit feedback
A Agarwal, DP Foster, DJ Hsu, SM Kakade, A Rakhlin
Advances in Neural Information Processing Systems 24, 2011
Fisher-rao metric, geometry, and complexity of neural networks
T Liang, T Poggio, A Rakhlin, J Stokes
The 22nd international conference on artificial intelligence and statistics …, 2019
Does data interpolation contradict statistical optimality?
M Belkin, A Rakhlin, AB Tsybakov
The 22nd International Conference on Artificial Intelligence and Statistics …, 2019
Optimal strategies and minimax lower bounds for online convex games
J Abernethy, PL Bartlett, A Rakhlin, A Tewari
Stability of -Means Clustering
A Rakhlin, A Caponnetto
Advances in neural information processing systems 19, 2006
Online learning: Random averages, combinatorial parameters, and learnability
A Rakhlin, K Sridharan, A Tewari
Advances in Neural Information Processing Systems 23, 2010
Near optimal finite time identification of arbitrary linear dynamical systems
T Sarkar, A Rakhlin
International Conference on Machine Learning, 5610-5618, 2019
Partial monitoring—classification, regret bounds, and algorithms
G Bartók, DP Foster, D Pál, A Rakhlin, C Szepesvári
Mathematics of Operations Research 39 (4), 967-997, 2014
Theory of deep learning IIb: Optimization properties of SGD
C Zhang, Q Liao, A Rakhlin, B Miranda, N Golowich, T Poggio
arXiv preprint arXiv:1801.02254, 2018
High-probability regret bounds for bandit online linear optimization
PL Bartlett, V Dani, T Hayes, S Kakade, A Rakhlin, A Tewari
Conference on Learning Theory, 2008
A stochastic view of optimal regret through minimax duality
J Abernethy, A Agarwal, PL Bartlett, A Rakhlin
Conference on Learning Theory, 2009
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–20