no code implementations • 14 Nov 2022 • Imon Banerjee, Harsha Honnappa, Vinayak Rao
Our statistical bounds depend on the logging policy through its mixing properties.
no code implementations • 12 Nov 2021 • Yao Ji, Gesualdo Scutari, Ying Sun, Harsha Honnappa
First, we establish statistical consistency of the estimator: under a suitable choice of the penalty parameter, the optimal solution of the penalized problem achieves near optimal minimax rate $\mathcal{O}(s \log d/N)$ in $\ell_2$-loss, where $s$ is the sparsity value, $d$ is the ambient dimension, and $N$ is the total sample size in the network -- this matches centralized sample rates.
no code implementations • 23 Jun 2021 • Prateek Jaiswal, Harsha Honnappa, Vinayak A. Rao
Bayesian posteriors afford a principled mechanism to incorporate data and prior knowledge into stochastic optimization problems.
no code implementations • 13 Jan 2021 • Imon Banerjee, Vinayak A. Rao, Harsha Honnappa
We present a PAC-Bayesian analysis of variational Bayes (VB) approximations to tempered Bayesian posterior distributions, bounding the model risk of the VB approximations.
Statistics Theory Statistics Theory
no code implementations • 1 Jan 2021 • Prateek Jaiswal, Harsha Honnappa, Vinayak Rao
This paper proposes a stochastic variational inference (SVI) method for computing an approximate posterior path measure of a Cox process.
no code implementations • 12 Jul 2020 • Ruixin Wang, Prateek Jaiwal, Harsha Honnappa
We present methodology for estimating the stochastic intensity of a doubly stochastic Poisson process.
no code implementations • pproximateinference AABI Symposium 2019 • Prateek Jaiswal, Harsha Honnappa, Vinayak A. Rao
We study system design problems stated as parameterized stochastic programs with a chance-constraint set.
no code implementations • 4 Nov 2019 • Prateek Jaiswal, Harsha Honnappa, Vinayak A. Rao
We also establish the asymptotic consistency of decision rules obtained from a `naive' variational Bayesian procedure.
no code implementations • 5 Feb 2019 • Prateek Jaiswal, Vinayak A. Rao, Harsha Honnappa
We study the asymptotic consistency properties of $\alpha$-R\'enyi approximate posteriors, a class of variational Bayesian methods that approximate an intractable Bayesian posterior with a member of a tractable family of distributions, the member chosen to minimize the $\alpha$-R\'enyi divergence from the true posterior.