Stochastic Delay

Stochastic delay, the unpredictable timing of events or feedback in dynamic systems, is a significant challenge across diverse fields, from machine learning to robotics and finance. Current research focuses on developing robust algorithms and models, such as those based on stochastic delay differential equations (SDDEs) and reinforcement learning, to mitigate the negative impacts of these delays on system performance and stability. These efforts are driven by the need to improve the efficiency and reliability of complex systems operating under conditions of uncertainty, with applications ranging from optimizing distributed computing to controlling robots in remote environments. The development of accurate and efficient methods for handling stochastic delay is crucial for advancing numerous scientific and engineering disciplines.

Papers

June 17, 2024

Distributed Stochastic Gradient Descent with Staleness: A Stochastic Delay Differential Equation Based Framework
Siyuan Yu, Wei Chen, H. Vincent Poor
New Framework Gradient Descent Stochastic Gradient Descent Asynchronous Stochastic Gradient Descent Staleness Problem Stochastic Delay

April 8, 2024

Tree Search-Based Policy Optimization under Stochastic Execution Delay
David Valensi, Esther Derman, Shie Mannor, Gal Dalal
Markov Decision Process Markovian Policy Stochastic Delay

October 29, 2023

Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation
Nikki Lijing Kuang, Ming Yin, Mengdi Wang, Yu-Xiang Wang, Yi-An Ma
Reinforcement Learning High Dimensional Posterior Sampling Linear Function Approximation Delayed Feedback Order Optimal Regret Stochastic Delay

July 12, 2023

Stochastic Delay Differential Games: Financial Modeling and Machine Learning Algorithms
Robert Balkin, Hector D. Ceniceros, Ruimeng Hu
Neural Network Nash Equilibrium Machine Learning Algorithm Stochastic Game Quantitative Finance Differential Game Stochastic Delay

May 26, 2023

Adaptive PD Control using Deep Reinforcement Learning for Local-Remote Teleoperation with Stochastic Time Delays
Luc McCutcheon, Saber Fallah
Reinforcement Learning Deep Reinforcement Learning Model Based Reinforcement Learning Robot Teleoperation Delay Differential Equation Stochastic Delay Remote Manipulation

March 14, 2023

Delay-SDE-net: A deep learning approach for time series modelling with memory and uncertainty estimates
Mari Dahl Eggen, Alise Danielle Midtfjord
Time Series High Uncertainty Anticipation Deep Learning Approach Memory Trace Neural Network Model Stochastic Model Stochastic Delay

Stochastic Delay

Papers

Distributed Stochastic Gradient Descent with Staleness: A Stochastic Delay Differential Equation Based Framework

Tree Search-Based Policy Optimization under Stochastic Execution Delay

Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation

Stochastic Delay Differential Games: Financial Modeling and Machine Learning Algorithms

Adaptive PD Control using Deep Reinforcement Learning for Local-Remote Teleoperation with Stochastic Time Delays

Delay-SDE-net: A deep learning approach for time series modelling with memory and uncertainty estimates