While ERM suffices to attain near-optimal generalization error in the
st...
We present the first diffusion-based framework that can learn an unknown...
Imperfect score-matching leads to a shift between the training and the
s...
We provide time- and sample-efficient algorithms for learning and testin...
We study the optimization landscape of the log-likelihood function and t...
We prove fast mixing and characterize the stationary distribution of the...
Much of modern learning theory has been split between two regimes: the
c...
We consider a general statistical estimation problem wherein binary labe...
We introduce the technique of generic chaining and majorizing measures f...
Laws of large numbers guarantee that given a large enough sample from so...
Answering multiple counting queries is one of the best-studied problems ...
Given one sample X ∈{± 1}^n from an Ising model [X=x]∝(x^ J x/2), whose ...
We study binary classification algorithms for which the prediction on an...
Local differential privacy (LDP) is a model where users send privatized ...
Statistical learning theory has largely focused on learning and
generali...
We study the problem of learning a d-dimensional log-concave distributio...
We show that fundamental learning tasks, such as finding an approximate
...
`Twenty questions' is a guessing game played by two players: Bob thinks ...
We study a sequential resource allocation problem between a fixed number...
We study the problem of identifying correlations in multivariate data, u...