Lingqing Shen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Lingqing Shen has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Abhishek Roy
Halıcıoğlu Data Science Institute University of California San
1 shared publication - Fatma Kılınç-Karzan
Tepper School of Business, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213
1 shared publication - Krishnakumar Balasubramanian
Department of Statistics University of California Davis
1 shared publication - Nam Ho-Nguyen
Discipline of Business Analytics, The University of Sydney, Sydney, Australia
1 shared publication - Saeed Ghadimi
Department of Management Science & Engineering University of Waterloo
1 shared publication
Latest Publications
- 13 October 2022
- Published by Springer Nature in Mathematical Programming
- Vol. 198 (2) , 1519-1582
An online convex optimization-based framework for convex bilevel optimization
- 13 October 2022
- Published by Springer Nature in Mathematical Programming
- Vol. 198 (2) , 1519-1582
An online convex optimization-based framework for convex bilevel optimization
- Open Access
Stochastic Zeroth-order Discretizations of Langevin Diffusions for Bayesian Inference
Discretizations of Langevin diffusions provide a powerful method for sampling and Bayesian inference. However, such discretizations require evaluation of the gradient of the potential function. In several real-world scenarios, obtaining gradient evaluations might either be computationally expensive, or simply impossible. In this work, we propose and analyze stochastic zeroth-order sampling algorithms for discretizing overdamped and underdamped Langevin diffusions. Our approach is based on estimating the gradients, based on Gaussian Stein's identities, widely used in the stochastic optimization literature. We provide a comprehensive sample complexity analysis -- number noisy function evaluations to be made to obtain an $\epsilon$-approximate sample in Wasserstein distance -- of stochastic zeroth-order discretizations of both overdamped and underdamped Langevin diffusions, under various noise models. We also propose a variable selection technique based on zeroth-order gradient estimates and establish its theoretical guarantees. Our theoretical contributions extend the practical applicability of sampling algorithms to the noisy black-box and high-dimensional settings.
Open AccessStochastic Zeroth-order Discretizations of Langevin Diffusions for Bayesian Inference
Discretizations of Langevin diffusions provide a powerful method for sampling and Bayesian inference. However, such discretizations require evaluation of the gradient of the potential function. In several real-world scenarios, obtaining gradient evaluations might either be computationally expensive, or simply impossible. In this work, we propose and analyze stochastic zeroth-order sampling algorithms for discretizing overdamped and underdamped Langevin diffusions. Our approach is based on estimating the gradients, based on Gaussian Stein's identities, widely used in the stochastic optimization literature. We provide a comprehensive sample complexity analysis -- number noisy function evaluations to be made to obtain an $\epsilon$-approximate sample in Wasserstein distance -- of stochastic zeroth-order discretizations of both overdamped and underdamped Langevin diffusions, under various noise models. We also propose a variable selection technique based on zeroth-order gradient estimates and establish its theoretical guarantees. Our theoretical contributions extend the practical applicability of sampling algorithms to the noisy black-box and high-dimensional settings.