Divyat Mahajan

I am a Ph.D. 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.

My research focus is on learning representations where we can provably identify/recover the latent factors from observations, which falls into the area of disentanglement/object-centric learning or more broadly causal representation learning. I also work on treatment effect estimation (causal inference) and trustworthy machine learning, where I have specifically tackled problems in out-of-distribution generalization, privacy robustness, and explainability of machine learning models.
Research Interests:
Causal Representation Learning | Trustworthy Machine Learning

Causal Representation Learning & Out-of-Distribution Generalization

• Compositional Risk Minimization Divyat Mahajan, Mohammad Pezeshki, Ioannis Mitliagkas, Kartik Ahuja, Pascal Vincent
  Preprint. Under Review. [arxiv]
• Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation Sébastien Lachapelle*, Divyat Mahajan*, Ioannis Mitliagkas, Simon Lacoste-Julien
  NeurIPS 2023 (Oral)
  [arxiv] [code] [poster]
• Interventional Causal Representation Learning Kartik Ahuja, Divyat Mahajan, Yixin Wang, Yoshua Bengio
  ICML 2023 (Oral)
  [arxiv] [code] [talk] [presentation] [poster]
• Synergies Between Disentanglement and Sparsity: a Multi-Task Learning Perspective Sébastien Lachapelle*, Tristan Deleu*, Divyat Mahajan, Ioannis Mitliagkas, Yoshua Bengio, Simon Lacoste-Julien, Quentin Bertrand
  ICML 2023
  [arxiv] [code] [talk]
• Towards efficient representation identification in supervised learning Kartik Ahuja*, Divyat Mahajan*, Vasilis Syrgkanis, Ioannis Mitliagkas
  CleaR 2022
  [arxiv] [code] [presentation]
• Domain Generalization using Causal Matching Divyat Mahajan, Shruti Tople, Amit Sharma
  ICML 2021 (Oral) [arxiv] [code] [talk] [presentation] [poster]

Causal Inference

• Zero-Shot Learning of Causal Models Divyat Mahajan*, Jannes Gladrow, Agrin Hilmkil, Cheng Zhang, Meyer Scetbon*
  Preprint. Under Review. [arxiv]
• Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimation Divyat Mahajan, Ioannis Mitliagkas, Brady Neal, Vasilis Syrgkanis
  ICLR 2024 (Spotlight)
  [arxiv] [code]
• 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 [arxiv] [code] [talk] [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