19 papers
Exact simulation of diffusions and improved algorithms for log-concave sampling
Fan Chen, Sinho Chewi, Alexander Rakhlin +1
We study exact simulation of diffusions via rejection sampling on path space using unbiased estimators of the density ratio obtained from Girsanov's theorem. When applied to the un…
Near-Lipschitz stability of the Kim--Milman flow map
Sinho Chewi, Katharina Eichinger, Aram-Alexandre Pooladian
We prove that the Kim--Milman flow map enjoys favorable stability properties with respect to variations in the target measure, provided that one of the target measures is sufficien…
Blind denoising diffusion models and the blessings of dimensionality
Zahra Kadkhodaie, Aram-Alexandre Pooladian, Sinho Chewi +1
Denoising diffusion models (DDMs) are state-of-the-art methods for learning densities from data across numerous domains, yet many aspects of the training and sampling pipeline rema…
Complexity of Non-Log-Concave Sampling in Fisher Information
Sinho Chewi, Andre Wibisono
We study the query complexity of obtaining a relative Fisher information guarantee for sampling from a log-smooth non-log-concave distribution; this is a sampling analog of finding…
High-accuracy log-concave sampling with stochastic queries
Fan Chen, Sinho Chewi, Constantinos Daskalakis +1
We show that high-accuracy guarantees for log-concave sampling -- that is, iteration and query complexities which scale as , where is the desired targ…
A proximal gradient algorithm for composite log-concave sampling
Linghai Liu, Sinho Chewi
We propose an algorithm to sample from composite log-concave distributions over , i.e., densities of the form , assuming access to gradient evalua…