519 citations · 2.8k across the 80 of their papers we have counts for
4 papers · 2 filters
Size-Independent Sample Complexity of Neural Networks
Noah Golowich, Alexander Rakhlin, Ohad Shamir
We study the sample complexity of learning neural networks, by providing new bounds on their Rademacher complexity assuming norm constraints on the parameter matrix of each layer.…
Fisher-Rao Metric, Geometry, and Complexity of Neural Networks
Tengyuan Liang, Tomaso Poggio, Alexander Rakhlin +1
We study the relationship between geometry and capacity measures for deep neural networks from an invariance viewpoint. We introduce a new notion of capacity --- the Fisher-Rao nor…
ZigZag: A new approach to adaptive online learning
Dylan J. Foster, Alexander Rakhlin, Karthik Sridharan
We develop a novel family of algorithms for the online learning setting with regret against any data sequence bounded by the empirical Rademacher complexity of that sequence. To de…
Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis
Maxim Raginsky, Alexander Rakhlin, Matus Telgarsky
Stochastic Gradient Langevin Dynamics (SGLD) is a popular variant of Stochastic Gradient Descent, where properly scaled isotropic Gaussian noise is added to an unbiased estimate of…