5 papers
Strong log-concavity in probit regression
Martin Chak, Giacomo Zanella, Zoraida F. Rico
We show that strong log-concavity emerges in probit regression likelihoods without ridge penalization (i.e. Gaussian priors), unlike for the logistic case. Specifically, we provide…
Complexity of Markov Chain Monte Carlo for Generalized Linear Models
Martin Chak, Giacomo Zanella
Markov Chain Monte Carlo (MCMC), Laplace approximation (LA) and variational inference (VI) methods are popular approaches to Bayesian inference, each with trade-offs between comput…
On theoretical guarantees and a blessing of dimensionality for nonconvex sampling
Martin Chak
Guarantees for algorithms sampling from nonlogconcave target measures on are studied. For the class of measures with logdensities that have bounded Hessians and are…
Reflection coupling for unadjusted generalized Hamiltonian Monte Carlo in the nonconvex stochastic gradient case
Martin Chak, Pierre Monmarché
Contraction in Wasserstein 1-distance with explicit rates is established for generalized Hamiltonian Monte Carlo with stochastic gradients under possibly nonconvex conditions. The…
Regularity preservation in Kolmogorov equations for non-Lipschitz coefficients under Lyapunov conditions
Martin Chak
Given global Lipschitz continuity and differentiability of high enough order on the coefficients in Itô's equation, differentiability of associated semigroups, existence of twice…