I am a postdoctoral scholar at Stanford working with Jure Leskovec. I obtained my PhD from MIT CSAIL and LIDS in 2023 advised by Stefanie Jegelka and Suvrit Sra.

I develop new learning algorithms for structured data such as graphs, eigenvectors, and relational databases.

News

• Paper on equivariant contrastive learning accepted at ICLR 2024!
• Paper on a new strong eigenvector-based graph positional encoding accepted at ICLR 2024!
• Beta release of RelBench, a benchmark for deep learning on relational databases.
• New preprint advocating for a new blueprint for deep learning on relational databases.
• I am co-lecturing CS224W (Fall 2023) along with Jure.
• Paper on sign equivariant neural networks for eigenvectors accepted at NeurIPS 2023 with a spotlight! Preliminary version here.
• Our Sign and Basis networks for learning graph positional encodings is accepted at ICLR 2023 with a spotlight!
• Excited to share new paper on a new scalable contrastive masked autoencoder!
• New NeurIPS 2022 paper on neural network friendly extensions of non-differentiable set functions!
• Highlighted reviewer at ICLR 2022.
• I spent a very enjoyable summer 2022 at Google Research working with Dilip Krishnan.
• I am helping organize the LoG Conference, a new conference specifically dedicated to graph machine learning!
• MIT news wrote a story about our NeurIPS 2021 paper on shortcut learning.
• Paper on the use of shortcuts in contrastive learning accepted at NeurIPS 2021.
• reviewer award (top 10% of reviewers) at ICML 2021.
• Awarded the runner-up prize for the 2021 Two Sigma PhD fellowship.
• Paper on contrastive learning with hard negative samples accepted at ICLR 2021!
• Reviewer award (top 10% of reviewers) at NeurIPS 2020.
• Paper on debiased contrastive learning accepted at NeurIPS 2020 with a spotlight!
• Paper on optimal minibatch selection at the ICML 2020 Workshop on Real World Experiment Design and Active Learning.
• Spent the summer 2020 at Amazon Web Services working as an Applied Scientist.
• Paper on understanding theoretical foundations of pretraining embeddings using weak supervision accepted at ICML 2020!
• Paper on a new probabilistic model for diversity accepted at NeurIPS 2019.

Core review service: NeurIPS, ICLR, ICML, JMLR

Other review service: Nature Communications, COLT, CVPR, ECCV, TMLR

Teaching:

Lecturer: CS224W Machine Learning with Graphs – Stanford Fall 2023

TA: 6.867 Machine Learning (graduate level) – MIT Fall 2021