Summary of Testing and Improving the Robustness Of Amortized Bayesian Inference For Cognitive Models, by Yufei Wu et al.
Testing and Improving the Robustness of Amortized Bayesian Inference for Cognitive Models
by Yufei Wu, Stefan Radev, Francis Tuerlinckx
First submitted to arxiv on: 29 Dec 2024
Categories
- Main: Machine Learning (stat.ML)
- Secondary: Machine Learning (cs.LG); Applications (stat.AP); Methodology (stat.ME)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The research paper investigates ways to improve the robustness of parameter estimation in cognitive models when dealing with contaminants and outliers. The study uses amortized Bayesian inference (ABI) with neural networks to test and improve the robustness of parameter estimation. This is achieved by conducting systematic analyses on a toy example, as well as analyzing synthetic and real data using the Drift Diffusion Models (DDM). The sensitivity of ABI to contaminants is studied using tools from robust statistics, such as the empirical influence function and breakdown point. A data augmentation approach that incorporates a contamination distribution into the training process is proposed. The performance and cost of different candidate distributions are evaluated in terms of accuracy and efficiency loss relative to a standard estimator. The results show that introducing contaminants from a Cauchy distribution during training significantly increases the robustness of the neural density estimator. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The study aims to make cognitive models more robust by reducing the impact of outliers and contaminants. It uses a new method called amortized Bayesian inference with neural networks to do this. The researchers tested their method using a simple example, as well as real data from a popular model called Drift Diffusion Models. They found that introducing some noise into the training process makes the model more robust. This is useful in fields where it’s hard to detect or remove outliers. |
Keywords
» Artificial intelligence » Bayesian inference » Data augmentation
