Flow Perturbation to Accelerate Unbiased Sampling of Boltzmann distribution
This method accelerates unbiased Boltzmann sampling for high-dimensional molecular systems, addressing a bottleneck in computational biophysics.
The paper tackled the high computational cost of Jacobian calculations in flow-based generative models for Boltzmann distribution sampling by introducing the flow perturbation method, which achieved orders of magnitude speedup and accurately sampled the Chignolin protein with all atomic Cartesian coordinates.
Flow-based generative models have been employed for sampling the Boltzmann distribution, but their application to high-dimensional systems is hindered by the significant computational cost of obtaining the Jacobian of the flow. To overcome this challenge, we introduce the flow perturbation method, which incorporates optimized stochastic perturbations into the flow. By reweighting trajectories generated by the perturbed flow, our method achieves unbiased sampling of the Boltzmann distribution with orders of magnitude speedup compared to both brute force Jacobian calculations and the Hutchinson estimator. Notably, it accurately sampled the Chignolin protein with all atomic Cartesian coordinates explicitly represented, which, to our best knowledge, is the largest molecule ever Boltzmann sampled in such detail using generative models.