Polynomial complexity sampling from multimodal distributions using Sequential Monte Carlo
By: Ruiyu Han, Gautam Iyer, Dejan Slepčev
Potential Business Impact:
Helps computers find best answers faster.
We study a sequential Monte Carlo algorithm to sample from the Gibbs measure with a non-convex energy function at a low temperature. We use the practical and popular geometric annealing schedule, and use a Langevin diffusion at each temperature level. The Langevin diffusion only needs to run for a time that is long enough to ensure local mixing within energy valleys, which is much shorter than the time required for global mixing. Our main result shows convergence of Monte Carlo estimators with time complexity that, approximately, scales like the forth power of the inverse temperature, and the square of the inverse allowed error. We also study this algorithm in an illustrative model scenario where more explicit estimates can be given.
Similar Papers
Convergence of a Sequential Monte Carlo algorithm towards multimodal distributions on Rd
Computation
Helps computers find patterns in complex data.
Convergence of a Sequential Monte Carlo algorithm towards multimodal distributions on Rd
Computation
Helps computers find patterns in complex data.
Operator-Level Quantum Acceleration of Non-Logconcave Sampling
Quantum Physics
Quantum computers solve tough problems faster.