Search Results for author: Prateek Jaiswal

Found 7 papers, 0 papers with code

Generalized Regret Analysis of Thompson Sampling using Fractional Posteriors

no code implementations12 Sep 2023 Prateek Jaiswal, Debdeep Pati, Anirban Bhattacharya, Bani K. Mallick

Both the sub-Gaussian and exponential family models satisfy our general conditions on the reward distribution.

Thompson Sampling

Facial De-morphing: Extracting Component Faces from a Single Morph

no code implementations7 Sep 2022 Sudipta Banerjee, Prateek Jaiswal, Arun Ross

In this work, we propose a novel de-morphing method that can recover images of both identities simultaneously from a single morphed face image without needing a reference image or prior information about the morphing process.

Generative Adversarial Network MORPH

Bayesian Joint Chance Constrained Optimization: Approximations and Statistical Consistency

no code implementations23 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.

Stochastic Optimization

Variational inference for diffusion modulated Cox processes

no code implementations1 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.

Variational Inference

Asymptotic Consistency of Loss-Calibrated Variational Bayes

no code implementations4 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.

Decision Making

Asymptotic Consistency of $α-$Rényi-Approximate Posteriors

no code implementations5 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.

Cannot find the paper you are looking for? You can Submit a new open access paper.