Continuous Delayed-Memory Stochastic Gradient Descent and Continuous-Time Reinforcement Learning from History of Astrophysical Time Series Studies
Abstract
Quasars are luminous objects in the universe that exhibit stochastic brightness variations encoding information about the supermassive black holes powering them, and modeling these variations from ground-based survey data time series, known as light curves, is a statistical challenge. This paper reviews how stochastic differential equations (SDEs) have been adapted with neural network parameterizations to overcome this challenge in history. We create the Continuous-Delayed-Memory Stochastic Gradient Descent which depend on the past state of the discrete iteration process. We performed the simulation on some 2-dimensional landscape and observed some wider-exploration and more precise convergent behavior compared to Vanilla SGD by adjusting hyperparameters. Besides, we proposed a reinforcement learning structure with continuous time policy gradients for exploratory policies without solving HJB PDE, and we show that its optimality conditions recover the Gibbs policy of previous works.
Related
- Continuous-Time Reinforcement Learning for N-Player Stochastic Differential Games with Exploratory Policies
- Reinforcement learning for constrained stochastic linear--quadratic control in continuous time
- Model-free Reinforcement Learning for Continuous Time and State: A Stochastic Maximum Principle Approach
- A Stochastic Proximal-Gradient Method for Regularized Generally Constrained Continuous Optimization
- Image AID via continuous-time reinforcement learning
BibTeX
@misc{yi2026continuous,
title = {{Continuous Delayed-Memory Stochastic Gradient Descent and Continuous-Time Reinforcement Learning from History of Astrophysical Time Series Studies}},
author = {Juncheng Yi},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.20906},
eprint = {2609.20906},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.20906},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Continuous Delayed-Memory Stochastic Gradient Descent and Continuous-Time Reinforcement Learning from History of Astrophysical Time Series Studies
AU - Juncheng Yi
PY - 2026
DA - 2026/09/22
PB - arXiv
DO - 10.48550/arxiv.2609.20906
UR - https://arxiv.org/abs/2609.20906
AB - Quasars are luminous objects in the universe that exhibit stochastic brightness variations encoding information about the supermassive black holes powering them, and modeling these variations from ground-based survey data time series, known as light curves, is a statistical challenge. This paper reviews how stochastic differential equations (SDEs) have been adapted with neural network parameterizations to overcome this challenge in history. We create the Continuous-Delayed-Memory Stochastic Gradient Descent which depend on the past state of the discrete iteration process. We performed the simulation on some 2-dimensional landscape and observed some wider-exploration and more precise convergent behavior compared to Vanilla SGD by adjusting hyperparameters. Besides, we proposed a reinforcement learning structure with continuous time policy gradients for exploratory policies without solving HJB PDE, and we show that its optimality conditions recover the Gibbs policy of previous works.
ER -