We prove that the single-site Glauber dynamics for sampling proper
q-col...
Learning with expert advice and multi-armed bandit are two classic onlin...
The problem of bandit with graph feedback generalizes both the multi-arm...
The problem of uniformly sampling hypergraph independent sets is revisit...
Outcome labeling ambiguity and subjectivity are ubiquitous in real-world...
The bandit problem with graph feedback, proposed in [Mannor and Shamir,
...
We extend the notion of spectral independence (introduced by Anari, Liu,...
Matrix decomposition is one of the fundamental tools to discover knowled...
Principal component analysis (PCA) is one of the most widely used dimens...
We give new algorithms based on Markov chains to sample and approximatel...
We present fully polynomial-time (deterministic or randomised) approxima...
Matrix decomposition is a popular and fundamental approach in machine
le...
We give a fully polynomial-time approximation scheme (FPTAS) to count th...