The issue of ensuring privacy for users who share their personal informa...
We present a new effective and scalable framework for training GNNs in
s...
We consider model selection for sequential decision making in stochastic...
We investigate the problem of online collaborative filtering under
no-re...
We study contextual bandit (CB) problems, where the user can sometimes
r...
We consider the problem of Learning from Label Proportions (LLP), a weak...
Object-goal navigation (Object-nav) entails searching, recognizing and
n...
We study the problem of model selection in bandit scenarios in the prese...
We investigate a nonstochastic bandit setting in which the loss of an ac...
The ability to train complex and highly effective models often requires ...
A major research direction in contextual bandits is to develop algorithm...
Motivated by problems of learning to rank long item sequences, we introd...
We investigate the problem of active learning in the streaming setting i...
We propose a simple model selection approach for algorithms in stochasti...
Motivated by a natural problem in online model selection with bandit
inf...
We present a new active learning algorithm that adaptively partitions th...
We investigate active learning by pairwise similarity over the leaves of...
A reciprocal recommendation problem is one where the goal of learning is...
Boltzmann exploration is a classic strategy for sequential decision-maki...
We investigate contextual online learning with nonparametric (Lipschitz)...
We investigate a novel cluster-of-bandit algorithm CAB for collaborative...
We investigate an efficient context-dependent clustering technique for
r...
Classical collaborative filtering, and content-based filtering methods t...
We present and study a partial-information model of online learning, whe...
We introduce a novel algorithmic approach to content recommendation base...
We consider the partial observability model for multi-armed bandits,
int...
Multi-armed bandit problems are receiving a great deal of attention beca...
We investigate the problem of active learning on a given tree whose node...
Motivated by social balance theory, we develop a theory of link
classifi...
We present very efficient active learning algorithms for link classifica...
We investigate the problem of sequentially predicting the binary labels ...