mlsanityData to 14 Oct 2026

Continuous Delayed-Memory Stochastic Gradient Descent and Continuous-Time Reinforcement Learning from History of Astrophysical Time Series Studies

arXiv 2609.20906 ↗First posted 17 Sep 2026cs.LG stat.APcited by 0

On the map: Deep reinforcement learning methods → RL theory and sample complexity

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods. Builds on 7 of its 20 references that are in the map. First posted on arXiv 17 Sep 2026.

Builds on

7 of 20 references.

References · 7

  1. 2018Neural Ordinary Differential Equationscited by 3,779
  2. 2016Optimization Methods for Large-Scale Machine Learningcited by 1,150
  3. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 554
  4. 2020Neural Controlled Differential Equations for Irregular Time Seriescited by 506
  5. 2020Scalable Gradients for Stochastic Differential Equationscited by 271
  6. 2019Neural Jump Stochastic Differential Equationscited by 150
  7. 2025Modeling Irregular Astronomical Time Series with Neural Stochastic Delay Differential Equationscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026From Ticks to Flows: Dynamics of Neural Reinforcement Learning in Continuous Environments
  2. 2023On the different regimes of Stochastic Gradient Descent
  3. 2024A Differential and Pointwise Control Approach to Reinforcement Learning
  4. 2023Self-Driving Telescopes: Autonomous Scheduling of Astronomical Observation Campaigns with Offline Reinforcement Learning
  5. 2026Continuous-Time Reinforcement Learning for Controlled Hawkes Jump-Diffusions
  6. 2024Non-asymptotic Analysis of Biased Adaptive Stochastic Approximation
  7. 2026Boundary-aware Reinforcement Learning for Hypercube State Spaces via Deterministic Policy Gradient
  8. 2023Temporal Difference Learning with Compressed Updates: Error-Feedback meets Reinforcement Learning