Bayesian Stochastic Gradient Descent for Stochastic Optimization with Streaming Input Data
From MaRDI portal
Publication:6188508
DOI10.1137/22M1478951arXiv2202.07581OpenAlexW4391223750MaRDI QIDQ6188508FDOQ6188508
Authors: Tianyi Liu, Yifan Lin, Enlu Zhou 
Publication date: 7 February 2024
Published in: SIAM Journal on Optimization (Search for Journal in Brave)
Abstract: We consider stochastic optimization under distributional uncertainty, where the unknown distributional parameter is estimated from streaming data that arrive sequentially over time. Moreover, data may depend on the decision of the time when they are generated. For both decision-independent and decision-dependent uncertainties, we propose an approach to jointly estimate the distributional parameter via Bayesian posterior distribution and update the decision by applying stochastic gradient descent on the Bayesian average of the objective function. Our approach converges asymptotically over time and achieves the convergence rates of classical SGD in the decision-independent case. We demonstrate the empirical performance of our approach on both synthetic test problems and a classical newsvendor problem.
Full work available at URL: https://arxiv.org/abs/2202.07581
Recommendations
- Distribution-free algorithms for predictive stochastic programming in the presence of streaming data
- Bayesian Distributionally Robust Optimization
- A Bayesian approach to data-driven multi-stage stochastic optimization
- A Bayesian risk approach to data-driven stochastic optimization: formulations and asymptotics
- Stochastic optimization on Bayesian nets
Cites Work
- Adaptive subgradient methods for online learning and stochastic optimization
- Title not available (Why is that?)
- Title not available (Why is that?)
- Convergence rates of posterior distributions for non iid observations
- An inventory model for deteriorating items with stock-dependent demand rate
- Distributionally Robust Control of Constrained Stochastic Systems
- Distributionally robust optimization under moment uncertainty with application to data-driven problems
- Online learning and online convex optimization
- Title not available (Why is that?)
- Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
- Quantitative Stability in Stochastic Programming: The Method of Probability Metrics
- A class of stochastic programs with decision dependent uncertainty
- Penalty Functions and Duality in Stochastic Programming Via ϕ-Divergence Functionals
- Data-driven chance constrained stochastic program
- Newsvendor-type models with decision-dependent uncertainty
- Multistage distributionally robust mixed-integer programming with decision-dependent moment-based ambiguity sets
- Title not available (Why is that?)
- ``Stack them high, let 'em fly: lot-sizing policies when inventories stimulate demand
- Data-driven robust optimization
- An approximate dynamic programming framework for modeling global climate policy under decision-dependent uncertainty
- High-dimensional Bayesian inference via the unadjusted Langevin algorithm
- Fast Langevin based algorithm for MCMC in high dimensions
- Simulation Budget Allocation for Selecting the Top-m Designs With Input Uncertainty
- Distributionally Robust Convex Optimization
- Optimization under decision-dependent uncertainty
- Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations
- A stochastic inventory model with stock dependent demand items.
- Numerical integration of the Langevin equation: Monte Carlo simulation
- Probability
- What you should know about simulation and derivatives
- About the non-asymptotic behaviour of Bayes estimators
- Analysis of Langevin Monte Carlo via convex optimization
- Wasserstein Distributionally Robust Stochastic Control: A Data-Driven Approach
- Decision-dependent probabilities in stochastic programs with recourse
- Distributionally robust optimization with decision dependent ambiguity sets
- Augmented nested sampling for stochastic programs with recourse and endogenous uncertainty
- A Bayesian risk approach to data-driven stochastic optimization: formulations and asymptotics
- Lectures on stochastic programming. Modeling and theory
- On some recent advances on high dimensional Bayesian statistics
- Robust ranking and selection with optimal computing budget allocation
- Bayesian Distributionally Robust Optimization
Cited In (4)
- Distribution-free algorithms for predictive stochastic programming in the presence of streaming data
- A Bayesian approach to data-driven multi-stage stochastic optimization
- Stochastic approximation for multi-period simulation optimization with streaming input data
- Stochastic Optimization with Decision-Dependent Distributions
This page was built for publication: Bayesian Stochastic Gradient Descent for Stochastic Optimization with Streaming Input Data
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6188508)
