519 citations · 2.8k across the 80 of their papers we have counts for
6 papers · 1 filter
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.…
Pediatric Bone Age Assessment Using Deep Convolutional Neural Networks
Vladimir Iglovikov, Alexander Rakhlin, Alexandr Kalinin +1
Skeletal bone age assessment is a common clinical practice to diagnose endocrine and metabolic disorders in child development. In this paper, we describe a fully automated deep lea…
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…
Weighted Message Passing and Minimum Energy Flow for Heterogeneous Stochastic Block Models with Side Information
T. Tony Cai, Tengyuan Liang, Alexander Rakhlin
We study the misclassification error for community detection in general heterogeneous stochastic block models (SBM) with noisy or partial label information. We establish a connecti…
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…