# Towards Learning Stochastic Population Models by Gradient Descent

arXiv: https://arxiv.org/abs/2404.07049 · HTML: https://mlsanity.com/paper/2404.07049/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 36 references that are in the map.
- First posted on arXiv 10 Apr 2024.

## Builds on (most cited first, 10 of 10)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Grammar Variational Autoencoder](https://mlsanity.com/paper/1703.01925/) (2017)
- [Automatic Differentiation of Programs with Discrete Randomness](https://mlsanity.com/paper/2210.08572/) (2022)
- [Differentiable Agent-based Epidemiology](https://mlsanity.com/paper/2207.09714/) (2022)
- [Bayesian differential programming for robust systems identification under uncertainty](https://mlsanity.com/paper/2004.06843/) (2020)
- [Machine learning for protein folding and dynamics](https://mlsanity.com/paper/1911.09811/) (2019)
- [The Fine-Grained Hardness of Sparse Linear Regression](https://mlsanity.com/paper/2106.03131/) (2021)
- [Smoothing Methods for Automatic Differentiation Across Conditional Branches](https://mlsanity.com/paper/2310.03585/) (2023)
- [Reactmine: a statistical search algorithm for inferring chemical reactions from time series data](https://mlsanity.com/paper/2209.03185/) (2022)
- [Evolutionary sparse data-driven discovery of complex multibody system dynamics](https://mlsanity.com/paper/2210.11656/) (2022)

## Built on by (most cited first, 1 of 1)

- [Learning surrogate equations for the analysis of an agent-based cancer model](https://mlsanity.com/paper/2503.01718/) (2025)

## Abstract (arXiv)

Increasing effort is put into the development of methods for learning mechanistic models from data. This task entails not only the accurate estimation of parameters but also a suitable model structure. Recent work on the discovery of dynamical systems formulates this problem as a linear equation system. Here, we explore several simulation-based optimization approaches, which allow much greater freedom in the objective formulation and weaker conditions on the available data. We show that even for relatively small stochastic population models, simultaneous estimation of parameters and structure poses major challenges for optimization procedures. Particularly, we investigate the application of the local stochastic gradient descent method, commonly used for training machine learning models. We demonstrate accurate estimation of models but find that enforcing the inference of parsimonious, interpretable models drastically increases the difficulty. We give an outlook on how this challenge can be overcome.