We study K-armed bandit problems where the reward distributions of the a...
In sparse linear bandits, a learning agent sequentially selects an actio...
Imitation learning (IL) is a general learning paradigm for tackling
sequ...
We study the problem of online multi-task learning where the tasks are
p...
The fast spreading adoption of machine learning (ML) by companies across...
The growing use of machine learning models in consequential settings has...
Heart disease is the number one killer, and ECGs can assist in the early...
We study multi-task reinforcement learning (RL) in tabular episodic Mark...
We develop a computationally-efficient PAC active learning algorithm for...
In many real-world applications, multiple agents seek to learn how to pe...
Online machine learning systems need to adapt to domain shifts. Meanwhil...
We study stochastic structured bandits for minimizing regret. The fact t...
We create a computationally tractable algorithm for contextual bandits w...
This paper is concerned with computationally efficient learning of
homog...
In this work we study active learning of homogeneous s-sparse halfspaces...
We design a new algorithm for batch active learning with deep neural net...
We study the problem of efficient online multiclass linear classificatio...
We study contextual bandit learning with an abstract policy class and
co...
We investigate the feasibility of learning from both fully-labeled super...
We study the problem of efficient PAC active learning of homogeneous lin...
We consider learning parameters of Binomial Hidden Markov Models, which ...
We present an efficient second-order algorithm with
Õ(1/η√(T)) regret fo...
It has been a long-standing problem to efficiently learn a halfspace usi...
We investigate active learning with access to two distinct oracles: Labe...
An active learner is given a hypothesis class, a large set of unlabeled
...
We develop a latent variable model and an efficient spectral algorithm
m...
We study agnostic active learning, where the goal is to learn a classifi...