For distributions over discrete product spaces ∏_i=1^n Ω_i',
Glauber dyn...
Score matching is an alternative to maximum likelihood (ML) for estimati...
We provide the first polynomial-time convergence guarantees for the
prob...
In the field of sampling algorithms, MCMC (Markov Chain Monte Carlo) met...
In this paper, we focus on the theoretical analysis of diffusion-based
g...
We prove two lower bounds for the complexity of non-log-concave sampling...
Noise Contrastive Estimation (NCE) is a popular approach for learning
pr...
Score-based generative modeling (SGM) has grown to be a hugely successfu...
Score-based generative modeling (SGM) is a highly successful approach fo...
We consider Ising models on the hypercube with a general interaction mat...
Approximating the partition function of the ferromagnetic Ising model wi...
Normalizing flows are a widely used class of latent-variable generative
...
Identification of a linear time-invariant dynamical system from partial
...
We give a algorithm for exact sampling from the Bingham distribution
p(x...
We consider the problem of online prediction in a marginally stable line...
Estimating the normalizing constant of an unnormalized probability
distr...
Mode connectivity is a surprising phenomenon in the loss landscape of de...
The optimal predictor for a linear dynamical system (with hidden state a...
Given a sequence of convex functions f_0, f_1, ..., f_T, we study the
pr...
A key task in Bayesian machine learning is sampling from distributions t...
We give a polynomial-time algorithm for learning latent-state linear
dyn...
A key task in Bayesian statistics is sampling from distributions that ar...