519 citations · 1.6k across the 49 of their papers we have counts for
4 papers · 1 filter
Online Learning with Predictable Sequences
Alexander Rakhlin, Karthik Sridharan
We present methods for online linear optimization that take advantage of benign (as opposed to worst-case) sequences. Specifically if the sequence encountered by the learner is des…
Minimizing The Misclassification Error Rate Using a Surrogate Convex Loss
Shai Ben-David, David Loker, Nathan Srebro +1
We carefully study how well minimizing convex surrogate loss functions, corresponds to minimizing the misclassification error rate for the problem of binary classification with lin…
Learning From An Optimization Viewpoint
Karthik Sridharan
In this dissertation we study statistical and online learning problems from an optimization viewpoint.The dissertation is divided into two parts : I. We first consider the question…
Relax and Localize: From Value to Algorithms
Alexander Rakhlin, Ohad Shamir, Karthik Sridharan
We show a principled way of deriving online learning algorithms from a minimax analysis. Various upper bounds on the minimax value, previously thought to be non-constructive, are s…