Distributionally Constrained Black-Box Stochastic Gradient Estimation and Optimization

05/19/2021
by   Henry Lam, et al.
0

We consider stochastic gradient estimation using only black-box function evaluations, where the function argument lies within a probability simplex. This problem is motivated from gradient-descent optimization procedures in multiple applications in distributionally robust analysis and inverse model calibration involving decision variables that are probability distributions. We are especially interested in obtaining gradient estimators where one or few sample observations or simulation runs apply simultaneously to all directions. Conventional zeroth-order gradient schemes such as simultaneous perturbation face challenges as the required moment conditions that allow the "canceling" of higher-order biases cannot be satisfied without violating the simplex constraints. We investigate a new set of required conditions on the random perturbation generator, which leads us to a class of implementable gradient estimators using Dirichlet mixtures. We study the statistical properties of these estimators and their utility in constrained stochastic approximation, including both Frank-Wolfe and mirror descent update schemes. We demonstrate the effectiveness of our procedures and compare with benchmarks via several numerical examples.

READ FULL TEXT
research
07/08/2020

Minimax Efficient Finite-Difference Stochastic Gradient Estimators Using Black-Box Function Evaluations

We consider stochastic gradient estimation using noisy black-box functio...
research
09/30/2019

Min-Max Optimization without Gradients: Convergence and Applications to Adversarial ML

In this paper, we study the problem of constrained robust (min-max) opti...
research
09/30/2022

Online Multi-Agent Decentralized Byzantine-robust Gradient Estimation

In this paper, we propose an iterative scheme for distributed Byzantiner...
research
11/22/2019

Low-variance Black-box Gradient Estimates for the Plackett-Luce Distribution

Learning models with discrete latent variables using stochastic gradient...
research
10/11/2022

Zeroth-Order Hard-Thresholding: Gradient Error vs. Expansivity

ℓ_0 constrained optimization is prevalent in machine learning, particula...
research
05/06/2023

The Fundamental Limits of Structure-Agnostic Functional Estimation

Many recent developments in causal inference, and functional estimation ...
research
11/27/2015

Gradient Estimation with Simultaneous Perturbation and Compressive Sensing

This paper aims at achieving a "good" estimator for the gradient of a fu...

Please sign up or login with your details

Forgot password? Click here to reset