Divyat Mahajan

I am a Ph.D. candidate at Mila & Université de Montréal, advised by Ioannis Mitliagkas. My research focus is on learning structured (causal/disentangled/object-centric) representations & compositional generalization, with emphasis on both theoretical guarantees and practical methods for better performance on downstream tasks. Please check my thesis proposal (report, slides) for more details.

I am extremely grateful for the amazing collaborations that have enrinched my Ph.D. journey. Currently, I am a visiting researcher at Meta FAIR advised by Pascal Vincent, also working closely with Kartik Ahuja and Mohammad Pezeshki on compositional generalization with energy-based models. I also did a summer internship at Microsoft Research Cambridge , where I worked on amortized learning and inference with Cheng Zhang and Meyer Scetbon. Further, in the initial years of my Ph.D. I worked with Vasilis Syrgkanis at Stanford on causal inference.

Prior to starting my Ph.D., I was a research fellow at Microsoft Research India, where I worked with Amit Sharma on trustworthy machine Learning from the lens of causality, specifically on out-of-distribution generalization, privacy, and explainable machine learning. Earlier, I completed my undergraduate in Mathematics and Computer Science from the Indian Institute of Technology, Kanpur.
Research Interests:
Compositional Generalization | Disentangled Representation Learning | Causal Inference

• Compositional Risk Minimization Divyat Mahajan, Mohammad Pezeshki, Ioannis Mitliagkas, Kartik Ahuja, Pascal Vincent
  Preprint. Under Review. [arxiv]
• Zero-Shot Learning of Causal Models Divyat Mahajan*, Jannes Gladrow, Agrin Hilmkil, Cheng Zhang, Meyer Scetbon*
  Preprint. Under Review. [arxiv] [code]
• Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimation Divyat Mahajan, Ioannis Mitliagkas, Brady Neal, Vasilis Syrgkanis
  ICLR 2024 (Spotlight)
  [arxiv] [code] [presentation] [poster]
• Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation Sébastien Lachapelle*, Divyat Mahajan*, Ioannis Mitliagkas, Simon Lacoste-Julien
  NeurIPS 2023 (Oral)
  [arxiv] [code] [blog] [talk(conference)] [talk(reading group)] [presentation] [poster]
• Interventional Causal Representation Learning Kartik Ahuja, Divyat Mahajan, Yixin Wang, Yoshua Bengio
  ICML 2023 (Oral)
  [arxiv] [code] [talk] [presentation] [poster]
• Domain Generalization using Causal Matching Divyat Mahajan, Shruti Tople, Amit Sharma
  ICML 2021 (Oral) [arxiv] [code] [talk] [presentation] [poster]
• 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]

• Outstanding Reviewer:   ICML 2022 ,   ML RC 2021 ,   ML RC 2022
• Top Reviewer:   NeurIPS 2022 ,   NeurIPS 2024
• FRQNT Doctoral Scholarship:   Competition 2024-25
• Academic Excellence Award, IIT Kanpur:   Session 2017-18

• 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