Estimation of the complete distribution of a random variable is a useful...
When feedback is partial, leveraging all available information is critic...
For infinite action contextual bandits, smoothed regret and reduction to...
In an era of countless content offerings, recommender systems alleviate
...
Modern decision-making systems, from robots to web recommendation engine...
This work introduces the Eigen Memory Tree (EMT), a novel online memory ...
Modern analytical workloads are highly heterogeneous and massively compl...
We desire to apply contextual bandits to scenarios where average-case
st...
A confidence sequence (CS) is an anytime-valid sequential inference prim...
Contextual bandit algorithms are ubiquitous tools for active sequential
...
Designing efficient general-purpose contextual bandit algorithms that wo...
A central problem in sequential decision making is to develop algorithms...
Consider the problem setting of Interaction-Grounded Learning (IGL), in ...
The use of pessimism, when reasoning about datasets lacking exhaustive
e...
Consider a prosthetic arm, learning to adapt to its user's control signa...
We propose the ChaCha (Champion-Challengers) algorithm for making an onl...
We study session-based recommendation scenarios where we want to recomme...
We develop confidence bounds that hold uniformly over time for off-polic...
We apply empirical likelihood techniques to contextual bandit policy val...
In this work, we describe practical lessons we have learned from success...
We design and study a Contextual Memory Tree (CMT), a learning memory
co...
We create a new online reduction of multiclass classification to binary
...
We propose a general framework for sequential and dynamic acquisition of...
Extreme classification problems are multiclass and multilabel classifica...
We present RandomizedCCA, a randomized algorithm for computing canonical...
We introduce online learning algorithms which are independent of feature...
Representing examples in a way that is compatible with the underlying
cl...
We propose a sampling scheme suitable for reducing a data set prior to
s...