Rapid Convergence of the Unadjusted Langevin Algorithm: Isoperimetry Suffices
Santosh Vempala, Andre Wibisono
–Neural Information Processing Systems
Notably, we do not assume convexity or bounds on higher derivatives. We also prove convergence guarantees in Rényi divergence of order q>1 assuming the limit of ULA satisfies either log-Sobolev or Poincaré inequality.
Neural Information Processing Systems
Feb-11-2025, 22:08:04 GMT
- Country:
- Europe (0.68)
- North America > United States (0.46)
- Industry:
- Information Technology > Security & Privacy (0.68)
- Technology: