Anmol Kabra

I will be joining Cornell’s Computer Science PhD program in Fall 2024 to work on AI/ML for science and climate problems.

I am a graduate student at Toyota Technological Institute at Chicago (TTIC), advised by Nati Srebro. At TTIC, I have studied ML for decision-making with a focus on game theory, multi-objective optimization, and privacy.

Previously, I was a Research Engineer at ASAPP at the Ithaca Research Lab, working with Kilian Weinberger, for a couple years — it was super fun!

I received my Bachelors in Science from Cornell University in Spring 2020 and was named a 2020 Merrill Presidential Scholar. At Cornell, I was generously supported by the Tata Scholarship and Telluride Scholarship, for which I’ll be eternally grateful. I studied Computer Science and Applied Mathematics, specializing in machine learning and optimization. I did research with Carla Gomes and the PhD students at the Computational Sustainability lab, where I first learned about the game theory and machine learning.

news

Oct 2023

Paper accepted to Findings of EMNLP 2023: Domain Private Transformers for Multi-Domain Dialog Systems.

Apr 2023

Presented at IDEAL Institute’s Workshop on Machine Learning, Interpretability, and Logic. Talk title: Reasonable modeling assumptions for real-world Principal-Agent games.

2022

Received the Best Poster Award at TTIC’s Annual Student Workshop.
Paper accepted to NeurIPS 2022 (Oral presentation): Exponential Family Model-Based Reinforcement Learning via Score Matching.
Joined ASAPP as a Research Intern.
Attended Deep Learning Theory Workshop and Summer School at the Simons Institute at Berkeley.
Visited the Simons Institute at Berkeley for the summer cluster on Interpretable ML.
Attended ML Theory summer school at Princeton.

2021

Started a PhD program at TTIC!
Paper accepted to AAAI 2021: Characterizing the Loss Landscape in Non-Negative Matrix Factorization.

2020

Joined ASAPP as a Research Engineer at the Ithaca Research Lab.
Graduated from Cornell!
- Recognized as a 2020 Merrill Presidential Scholar (top 1% of graduating class).
- Received the 2020 Computer Science Prize for Academic Excellence (highest undergraduate honor in the CS department).

2019

Featured among 10 out of 200 young researchers at the 2019 Heidelberg Laureate Forum.
Recognized for outstanding performance (top-10%) at 2019 ACM Summer School on HPC Architectures for AI and Dedicated Applications, Barcelona.
Recognized as an Outstanding Teaching Assistant for CS 4850: Math Foundations of the Info Age.
Paper accepted to ACM COMPASS 2019: GPU-accelerated Principal-Agent Game for Scalable Citizen Science.
- Best poster at 2019 Ivy League Undergraduate Research Symposium, UPenn.
- 2 awards at Cornell CIS’s BOOM 2019 project symposium (Sponsor Award by Air Liquide and Statistics Award by Cornell’s Statistics Department).
Joined ASAPP under Kilian Weinberger as a summer Research Engineer Intern.

selected papers

* equal contributions

Domain Private Transformers for Multi-Domain Dialog Systems

Anmol Kabra, and Ethan R. Elenberg

Findings-EMNLP (2023).

paper bibtex poster

@inproceedings{2023kabra_domain_privacy,
  title = {Domain Private Transformers for Multi-Domain Dialog Systems},
  author = {Kabra, Anmol and Elenberg, Ethan R.},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP},
  conference = {Findings-EMNLP},
  year = {2023},
}

Exponential Family Model-Based Reinforcement Learning via Score Matching

Gene Li, Junbo Li, Anmol Kabra, Nathan Srebro, Zhaoran Wang, and Zhuoran Yang

NeurIPS (2022). (Oral presentation).

paper bibtex code poster

@inproceedings{2022li_score_matching,
  title = {Exponential Family Model-Based Reinforcement Learning via Score Matching},
  author = {Li, Gene and Li, Junbo and Kabra, Anmol and Srebro, Nathan and Wang, Zhaoran and Yang, Zhuoran},
  booktitle = {Advances in Neural Information Processing Systems},
  conference = {NeurIPS},
  volume = {35},
  pages = {28474--28487},
  year = {2022},
}

Characterizing the Loss Landscape in Non-Negative Matrix Factorization

Johan Bjorck, Anmol Kabra, Kilian Q. Weinberger, and Carla P. Gomes

AAAI (2021).

paper bibtex

@inproceedings{2021bjorck_nmf,
  title = {Characterizing the Loss Landscape in Non-Negative Matrix Factorization},
  author = {Bjorck, Johan and Kabra, Anmol and Weinberger, Kilian Q. and Gomes, Carla P.},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
  conference = {AAAI},
  volume = {35},
  number = {8},
  pages = {6768--6776},
  year = {2021},
  doi = {10.1609/aaai.v35i8.16836},
  url = {https://doi.org/10.1609/aaai.v35i8.16836},
}

GPU-Accelerated Principal-Agent Game for Scalable Citizen Science

Anmol Kabra, Yexiang Xue, and Carla P. Gomes

COMPASS (2019).

paper bibtex code poster slides video

@inproceedings{2019kabra_avicaching,
  author = {Kabra, Anmol and Xue, Yexiang and Gomes, Carla P.},
  title = {GPU-Accelerated Principal-Agent Game for Scalable Citizen Science},
  year = {2019},
  isbn = {9781450367141},
  publisher = {Association for Computing Machinery},
  address = {New York, NY, USA},
  url = {https://doi.org/10.1145/3314344.3332495},
  doi = {10.1145/3314344.3332495},
  booktitle = {Proceedings of the 2nd ACM SIGCAS Conference on Computing and Sustainable Societies},
  conference = {COMPASS},
  pages = {165–173},
  numpages = {9},
  keywords = {parallel computation, mixed-integer programming, machine learning, computational sustainability, citizen science},
  location = {Accra, Ghana},
  series = {COMPASS ’19},
}

on a less academic note, I like

(listed in increasing order of number of characters in each bullet)

biking
cooking
playing Table Tennis
watching documentaries
following Formula 1 and motorsports
walking fast so that my legs heat up (and ache)
reading books, magazines, newspapers, research papers — mostly non-fiction these days