Divyat Mahajan

I am a graduate student at MILA & Université de Montréal, advised by Ioannis Mitliagkas. Prior to joining MILA, I was a Research Fellow at Microsoft Research Lab India, where I worked with Amit Sharma on Machine Learning and Causal Inference. I had completed my undergraduate double major program in Mathematics and Computer Science from the Indian Institute of Technology, Kanpur.

I have focused on causal regularizers to improve explainability and out-of-distribution generalization of deep learning models. In future, I plan to work on core problems in causality (causal effect estimation, causal discovery); along with its applications to develop robust ML models. I am also interested in general about optimization under uncertainity.
Research Interests:
Machine Learning | Causal Inference | Explainability, Out-of-Distribution Generalization and Robustness in Deep Learning

Causal Representation Learning & Out-of-Distribution Generalization

• Domain Generalization using Causal Matching Divyat Mahajan, Shruti Tople, Amit Sharma
  ICML 2021 (Oral) [arxiv] [code] [presentation] [poster]
• Towards efficient representation identification in supervised learning Kartik Ahuja*, Divyat Mahajan*, Vasilis Syrgkanis, Ioannis Mitliagkas
  CleaR 2022
  [arxiv] [code]

Causal Inference

• Split Treatment Analysis to Rank Heterogeneous Causal Effects for Prospective Interventions Yanbo Xu, Divyat Mahajan, Liz Manrao, Amit Sharma, Emre Kiciman
  WSDM 2021 (Oral) [arxiv] [code] [presentation] [poster]

Explainable Machine Learning

• Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers Divyat Mahajan, Chenhao Tan, Amit Sharma
  CausalML@NeurIPS 2019 (Oral) [arxiv] [code] [talk] [presentation] [poster]
• Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End Ramaravind K. Mothilal, Divyat Mahajan, Chenhao Tan, Amit Sharma
  AIES 2021, RAI@ICLR 2021 (Oral) [arxiv] [code] [talk] [presentation] [poster]

Miscellaneous

• The Connection between Out-of-Distribution Generalization and Privacy of ML Models Divyat Mahajan, Shruti Tople, Amit Sharma
  PPML@NeurIPS 2020
  [abstract] [code]
• A Generative Framework for Zero-Shot Learning with Adversarial Domain Adaptation Varun Khare*, Divyat Mahajan*, Homanga Bharadhwaj, Vinay Verma, Piyush Rai
  WACV 2020 [arxiv] [code] [presentation] [poster]

• RobustDG Toolkit for Building Robust ML models that generalize to unseen domains | Github | Microsoft

• Diverse Counterfactual Explanations (DiCE) for ML Toolkit to generate truthful explainations for machine learning models | Github | InterpretML