# Differentiable User Models

arXiv: https://arxiv.org/abs/2211.16277 · HTML: https://mlsanity.com/paper/2211.16277/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 37 references that are in the map.
- First posted on arXiv 29 Nov 2022.

## Builds on (most cited first, 16 of 16)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Conditional Neural Processes](https://mlsanity.com/paper/1807.01613/) (2018)
- [On the Utility of Learning about Humans for Human-AI Coordination](https://mlsanity.com/paper/1910.05789/) (2019)
- [Neural Processes](https://mlsanity.com/paper/1807.01622/) (2018)
- [Attentive Neural Processes](https://mlsanity.com/paper/1901.05761/) (2019)
- [Machine Theory of Mind](https://mlsanity.com/paper/1802.07740/) (2018)
- [Recasting Gradient-Based Meta-Learning as Hierarchical Bayes](https://mlsanity.com/paper/1801.08930/) (2018)
- [Collaborating with Humans without Human Data](https://mlsanity.com/paper/2110.08176/) (2021)
- [Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizations](https://mlsanity.com/paper/1308.3513/) (2013)
- [Online Bayesian Goal Inference for Boundedly-Rational Planning Agents](https://mlsanity.com/paper/2006.07532/) (2020)
- [Bayesian Optimization for Likelihood-Free Inference of Simulator-Based Statistical Models](https://mlsanity.com/paper/1501.03291/) (2015)
- [Meta-Learning surrogate models for sequential decision making](https://mlsanity.com/paper/1903.11907/) (2019)
- [The Lumiere Project: Bayesian User Modeling for Inferring the Goals and Needs of Software Users](https://mlsanity.com/paper/1301.7385/) (2013)
- [Nested Reasoning About Autonomous Agents Using Probabilistic Programs](https://mlsanity.com/paper/1812.01569/) (2018)
- [Interactive AI with a Theory of Mind](https://mlsanity.com/paper/1912.05284/) (2019)
- [User Modelling for Avoiding Overfitting in Interactive Knowledge Elicitation for Prediction](https://mlsanity.com/paper/1710.04881/) (2017)

## Abstract (arXiv)

Probabilistic user modeling is essential for building machine learning systems in the ubiquitous cases with humans in the loop. However, modern advanced user models, often designed as cognitive behavior simulators, are incompatible with modern machine learning pipelines and computationally prohibitive for most practical applications. We address this problem by introducing widely-applicable differentiable surrogates for bypassing this computational bottleneck; the surrogates enable computationally efficient inference with modern cognitive models. We show experimentally that modeling capabilities comparable to the only available solution, existing likelihood-free inference methods, are achievable with a computational cost suitable for online applications. Finally, we demonstrate how AI-assistants can now use cognitive models for online interaction in a menu-search task, which has so far required hours of computation during interaction.