Polynomial time guarantees for sampling based posterior inference in high-dimensional generalised linear models

📅 2022-08-28
🏛️ arXiv.org
📈 Citations: 4
Influential: 1
📄 PDF

career value

238K/year
🤖 AI Summary
This work addresses posterior functional computation in high-dimensional generalized linear models under non-log-concave likelihoods. To overcome the lack of non-asymptotic theoretical guarantees for conventional MCMC methods under non-convex posteriors, we propose a gradient-driven MCMC algorithm that achieves statistically optimal posterior sampling in polynomial time, requiring only local likelihood regularity and a suitable initial point. Our contribution is the first non-asymptotic convergence theory for posterior sampling that operates outside the M-estimation framework—free from asymptotic assumptions and scalable to high dimensions—applicable to density estimation, nonparametric regression, and PDE inverse problems. Crucially, the theoretical guarantees hold rigorously under non-log-concave likelihoods. Empirical evaluations confirm the method’s effectiveness and computational efficiency in both generalized linear models and PDE inverse problems.
📝 Abstract
The problem of computing posterior functionals in general high-dimensional statistical models with possibly non-log-concave likelihood functions is considered. Based on the proof strategy of [49], but using only local likelihood conditions and without relying on M-estimation theory, nonasymptotic statistical and computational guarantees are provided for a gradient based MCMC algorithm. Given a suitable initialiser, these guarantees scale polynomially in key algorithmic quantities. The abstract results are applied to several concrete statistical models, including density estimation, nonparametric regression with generalised linear models and a canonical statistical non-linear inverse problem from PDEs.
Problem

Research questions and friction points this paper is trying to address.

Computing posterior functionals in high-dimensional models
Non-log-concave likelihood functions in statistical models
Polynomial time guarantees for gradient based MCMC
Innovation

Methods, ideas, or system contributions that make the work stand out.

Gradient based MCMC algorithm guarantees
Local likelihood conditions without M-estimation
Polynomial scaling in algorithmic quantities