Exact simulation of diffusions and improved algorithms for log-concave sampling
Fan Chen, Sinho Chewi, Alexander Rakhlin, Matthew S. Zhang
Abstract
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 underdamped Langevin diffusion, it yields an algorithm for sampling from a strongly log-concave and log-smooth distribution with condition number κ, in dimension d, to accuracy in Rényi divergence, in O(κ2/3 d1/3\,polylog(1/)) queries. Under a third derivative bound, the dimension dependence improves to d1/5. This improves substantially over the prior state-of-the-art complexity of O(κd1/2\,polylog(1/)) for the Metropolis-adjusted Langevin algorithm, and over the d1/4 dimension dependence of Metropolized Hamiltonian Monte Carlo under the same third derivative bound. We also present applications to the mirror Langevin diffusion, and for obtaining Fisher information bounds in the non-log-concave case.
Create a lesson
Related papers
A Near-Optimal Space Lower Bound for Euclidean Diameter Estimation in Dynamic Streams
Ashwin Padaki, Krish Singal, Erik Waingarten
A Walk From Free Probability to Matrix Discrepancy I: Matrix Spencer
Tarun Kathuria
A Walk From Free Probability to Matrix Discrepancy II: Weaver's Problem and the Kadison-Singer Conjecture
Tarun Kathuria
Degree-Free Spectral Independence for Log-Concave Holant Measures
Xiaoyu Chen, Zejia Chen, Xinyuan Zhang
Optimizing Both Checking and Update Costs in Random Walk Search
Simon Apers, Marin Costes
Routing Multiple Agents Below the Sum of Distances
Matthias Bentert, Eduard Eiben, Fedor V. Fomin et al.