Probability & Statistics Seminar

State-dependent temperature control for Langevin diffusions

  • 演讲者:许左权(香港理工大学)

  • 时间:2022-07-18 14:30-15:30

  • 地点:理学院大楼M1001报告厅

We study the temperature control problem for Langevin diffusions in the context of non-convex optimization. The classical optimal control of such a problem is of the bang-bang type, which is overly sensitive to errors. A remedy is to allow the diffusions to explore other temperature values and hence smooth out the bang-bang control. We accomplish this by a stochastic relaxed control formulation incorporating randomization of the temperature control and regularizing its entropy. We derive a state-dependent, truncated exponential distribution, which can be used to sample temperatures in a Langevin algorithm, in terms of the solution to an HJB partial differential equation. We carry out a numerical experiment on a one-dimensional baseline example, in which the HJB equation can be easily solved, to compare the performance of the algorithm with three other available algorithms in search of a global optimum. This is a joint work with Xuefeng Gao, The Chinese University of Hong Kong and Xun Yu Zhou, Columbia University.