# Automatic Gradient Estimation for Calibrating Crowd Models with Discrete Decision Making

arXiv: https://arxiv.org/abs/2404.04678 · HTML: https://mlsanity.com/paper/2404.04678/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 36 references that are in the map.
- First posted on arXiv 6 Apr 2024.

## Builds on (most cited first, 8 of 8)

- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [The frontier of simulation-based inference](https://mlsanity.com/paper/1911.01429/) (2019)
- [Automatic Differentiation of Programs with Discrete Randomness](https://mlsanity.com/paper/2210.08572/) (2022)
- [Deep Social Force](https://mlsanity.com/paper/2109.12081/) (2021)
- [Differentiable Hybrid Traffic Simulation](https://mlsanity.com/paper/2210.08046/) (2022)
- [Smoothing Methods for Automatic Differentiation Across Conditional Branches](https://mlsanity.com/paper/2310.03585/) (2023)
- [Differentiable Programming: Efficient Smoothing of Control-Flow-Induced Discontinuities](https://mlsanity.com/paper/2305.06692/) (2023)
- [Parameter Calibration in Crowd Simulation Models using Approximate Bayesian Computation](https://mlsanity.com/paper/2001.10330/) (2020)

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

- [Dimensional Peeking for Low-Variance Gradients in Zeroth-Order Discrete Optimization via Simulation](https://mlsanity.com/paper/2602.00075/) (2026)

## Abstract (arXiv)

Recently proposed gradient estimators enable gradient descent over stochastic programs with discrete jumps in the response surface, which are not covered by automatic differentiation (AD) alone. Although these estimators' capability to guide a swift local search has been shown for certain problems, their applicability to models relevant to real-world applications remains largely unexplored. As the gradients governing the choice in candidate solutions are calculated from sampled simulation trajectories, the optimization procedure bears similarities to metaheuristics such as particle swarm optimization, which puts the focus on the different methods' calibration progress per function evaluation. Here, we consider the calibration of force-based crowd evacuation models based on the popular Social Force model augmented by discrete decision making. After studying the ability of an AD-based estimator for branching programs to capture the simulation's rugged response surface, calibration problems are tackled using gradient descent and two metaheuristics. As our main insights, we find 1) that the estimation's fidelity benefits from disregarding jumps of large magnitude inherent to the Social Force model, and 2) that the common problem of calibration by adjusting a simulation input distribution obviates the need for AD across the Social Force calculations, allowing gradient descent to excel.