A Continuous-time Stochastic Gradient Descent Method for Continuous Data

Kexin Jin, Jonas Latz, Chenguang Liu, Carola-Bibiane Schönlieb

Research output: Contribution to journalArticlepeer-review

34 Downloads (Pure)


Optimization problems with continuous data appear in, e.g., robust machine learning, functional data analysis, and variational inference. Here, the target function is given as an integral over a family of (continuously) indexed target functions - integrated with respect to a probability measure. Such problems can often be solved by stochastic optimization methods: performing optimization steps with respect to the indexed target function with randomly switched indices. In this work, we study a continuous-time variant of the stochastic gradient descent algorithm for optimization problems with continuous data. This so-called stochastic gradient process consists in a gradient flow minimizing an indexed target function that is coupled with a continuous-time index process determining the index. Index processes are, e.g., reflected diffusions, pure jump processes, or other L\'evy processes on compact spaces. Thus, we study multiple sampling patterns for the continuous data space and allow for data simulated or streamed at runtime of the algorithm. We analyze the approximation properties of the stochastic gradient process and study its longtime behavior and ergodicity under constant and decreasing learning rates. We end with illustrating the applicability of the stochastic gradient process in a polynomial regression problem with noisy functional data, as well as in a physics-informed neural network.
Original languageEnglish
JournalJournal of Machine Learning Research
Issue number274
Publication statusPublished - 2023


  • Stochastic optimization
  • functional data analysis
  • robust learning
  • arbitrary data sources
  • Markov processes


Dive into the research topics of 'A Continuous-time Stochastic Gradient Descent Method for Continuous Data'. Together they form a unique fingerprint.

Cite this