3 papers
stat.CO2025
Asymptotically exact variational flows via involutive MCMC kernels
Zuheng Xu, Trevor Campbell
Most expressive variational families -- such as normalizing flows -- lack practical convergence guarantees, as their theoretical assurances typically hold only at the intractable g…
stat.ML2025
Nearly Dimension-Independent Convergence of Mean-Field Black-Box Variational Inference
Kyurae Kim, Yi-An Ma, Trevor Campbell +1
We prove that, given a mean-field location-scale variational family, black-box variational inference (BBVI) with the reparametrization gradient converges at a rate that is nearly i…
stat.ML2025
Tuning Sequential Monte Carlo Samplers via Greedy Incremental Divergence Minimization
Kyurae Kim, Zuheng Xu, Jacob R. Gardner +1
The performance of sequential Monte Carlo (SMC) samplers heavily depends on the tuning of the Markov kernels used in the path proposal. For SMC samplers with unadjusted Markov kern…