Online learning: Stochastic, constrained, and smoothed adversaries

A Rakhlin, K Sridharan… - Advances in neural …, 2011‏ - proceedings.neurips.cc
Learning theory has largely focused on two main learning scenarios: the classical statistical
setting where instances are drawn iid from a fixed distribution, and the adversarial scenario …

Efficient algorithms for learning functions with bounded variation

PM Long - Information and Computation, 2004‏ - Elsevier
We show that the class F BV of [0, 1]-valued functions with total variation at most 1 can be
agnostically learned with respect to the absolute loss in polynomial time from O 1 ϵ 2log 1 δ …

[PDF][PDF] On the sample complexity of learning functions with bounded variation

PM Long - Proceedings of the eleventh annual conference on …, 1998‏ - dl.acm.org
We show that the class 3nv of [0, l]-valued functions with total variation at most 1 can be
agnostically learned with respect to the absolute loss in polynomial time from 0 (5 log+) …

[کتاب][B] Nonparametric estimation, regression, and prediction under minimal regularity conditions

SE Posner - 1995‏ - search.proquest.com
We explore consistent nonparametric techniques in the contexts of estimation, regression,
and prediction. The common element of the topics is that each one can be viewed as a noisy …

[فهرست منابع][C] On bandit problems with side observations and learnability

SR Kulkarni - Proc. 31st Allerton Conf. Commun. Contr. Comp, 1993