Ravi B. Sojitra

Ravi B. Sojitra, Vasilis Syrgkanis

We consider Dynamic Treatment Regimes (DTRs) with One Sided Noncompliance that arise in applications such as digital recommendations and adaptive medical trials. These are settings where decision makers encourage individuals to take treatments over time, but adapt encouragements based on previous encouragements, treatments, states, and outcomes. Importantly, individuals may not comply with encouragements based on unobserved confounders. For settings with binary treatments and encouragements, we provide nonparametric identification, estimation, and inference for Dynamic Local Average Treatment Effects (LATEs), which are expected values of multiple time period treatment effect contrasts for the respective complier subpopulations. Under One Sided Noncompliance and sequential extensions of the assumptions in Imbens and Angrist (1994), we show that one can identify Dynamic LATEs that correspond to treating at single time steps. In Staggered Adoption settings, we show that the assumptions are sufficient to identify Dynamic LATEs for treating in multiple time periods. Moreover, this result extends to any setting where the effect of a treatment in one period is uncorrelated with the compliance event in a subsequent period.

Tomas Folke, ZhaoBin Li, Ravi B. Sojitra et al.

Adversarial images highlight how vulnerable modern image classifiers are to perturbations outside of their training set. Human oversight might mitigate this weakness, but depends on humans understanding the AI well enough to predict when it is likely to make a mistake. In previous work we have found that humans tend to assume that the AI's decision process mirrors their own. Here we evaluate if methods from explainable AI can disrupt this assumption to help participants predict AI classifications for adversarial and standard images. We find that both saliency maps and examples facilitate catching AI errors, but their effects are not additive, and saliency maps are more effective than examples.

Scott Cheng-Hsin Yang, Wai Keen Vong, Ravi B. Sojitra et al.

State-of-the-art deep-learning systems use decision rules that are challenging for humans to model. Explainable AI (XAI) attempts to improve human understanding but rarely accounts for how people typically reason about unfamiliar agents. We propose explicitly modeling the human explainee via Bayesian Teaching, which evaluates explanations by how much they shift explainees' inferences toward a desired goal. We assess Bayesian Teaching in a binary image classification task across a variety of contexts. Absent intervention, participants predict that the AI's classifications will match their own, but explanations generated by Bayesian Teaching improve their ability to predict the AI's judgements by moving them away from this prior belief. Bayesian Teaching further allows each case to be broken down into sub-examples (here saliency maps). These sub-examples complement whole examples by improving error detection for familiar categories, whereas whole examples help predict correct AI judgements of unfamiliar cases.