log in  |  register  |  feedback?  |  help  |  web accessibility
Forward and Reverse Causal Inference: Building Blocks of Model Explanation and Decision-Making
Virtual - https://umd.zoom.us/j/93207947099?pwd=c096Z3JrZ1FGSXVEVjFWL29PQUV1dz09
Wednesday, April 14, 2021, 11:00 am-12:00 pm Calendar
  • You are subscribed to this talk through .
  • You are watching this talk through .
  • You are subscribed to this talk. (unsubscribe, watch)
  • You are watching this talk. (unwatch, subscribe)
  • You are not subscribed to this talk. (watch, subscribe)
Supervised machine learning was never aimed for decision-making, yet machine learning models are increasingly used for decision-making in critical domains like healthcare and governance. The supervision loss optimizes
for prediction assuming that all relationships stay the same, whereas decision-making involves intervening to change exactly those relationships. Correspondingly, two directions are gaining popularity: explanation methods that allow people to check whether a model learns the right features, and training methods that correct correlational biases learnt by the model.

In this talk, I will show how both model explanation and real-world decision-making are fundamentally causal problems, and propose a unified framework to address them. Specifically, these problems are special cases of forward (what will happen if I do this?) and reverse causal questions (why did something happen?). In model explanation, we are interested in the backward question for the model's output; the forward question is trivial. In decision-making, the focus is on the forward question; the backward question is often intractable. Using the proposed causal methods, I will describe case studies on medical risk prediction, face classification, and user ranking for recommender systems. This work has led to two open-source libraries, DiCE and DoWhy, that are being widely used for applying causal reasoning to new applications.
Amit Sharma is a Senior Researcher at Microsoft Research India and likes to think of modern algorithms as interventions in the world. His work focuses on understanding such algorithms' impact and developing methods to build better algorithmic interventions. Methodologically, his work bridges causal inference techniques with machine learning, with the goal of building machine learning models that generalize better, are explainable, and avoid hidden biases. To this end, Amit has co-led the development of the open-source DoWhy library for causal inference and the DiCE library for counterfactual model explanations. Amit is also passionate about deploying technology-based interventions, especially in mental healthcare where he collaborates with National Institute of Mental Health and Neuro-Sciences (NIMHANS), IndiaHis work has received many awards including a Best Paper at ACM CHI (2021),  Best Paper Honorable Mention at ACM CSCW (2016), the 2012 Yahoo! Key Scientific Challenges Award and the 2009 Honda Young Engineer and Scientist Award. Amit received his Ph.D. in computer science from Cornell University and B.Tech. in Computer Science and Engineering from Indian Institute of Technology (IIT) Kharagpur. 
This talk is organized by Wei Ai