Statistical Learning
Distributed Estimation with Multiple Samples per User: Sharp Rates and Phase Transition
Moreover, this bound is achieved by a noninteractive communication protocol.
Understanding Global Feature Contributions With Additive Importance Measures
Understanding the inner workings of complex machine learning models is a longstanding problem and most recent research has focused on local interpretability.
Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination
Contextual bandits encompass both the general problem of statistical learning with function approximation (specifically, cost-sensitive classification) and the classical multi-armed bandit problem, yet present algorithmic challenges greater than the sum of both parts.
Convergence Rates of Stochastic Gradient Descent under Infinite Noise Variance
Work partially conducted while affiliated with the V ector Institute.
