About Me

I’m a 5th year PhD student in the CS Theory Group at CU Boulder, advised by Rafael Frongillo and Bo Waggoner. I am generally interested in theoretical machine learning, game theory, and algorithmic economics, with a focus on learning from strategic agents. I was previously an undergraduate at Caltech, where I majored in Math and Computer Science. In between, I spent 2 years at Google where I helped build and launch Vertex AI for structured data.

Publications

(authors listed alphabetically signify equal contributions)

Forecasting Competitions

Efficient Competitions and Online Learning with Strategic Forecasters
Rafael Frongillo, Robert Gomez, Anish Thilagar, Bo Waggoner
[EC 2021] [arxiv]

Hedging and Approximate Truthfulness in Traditional Forecasting Competitions
Mary Monroe, Anish Thilagar, Melody Hsu, Rafael Frongillo
[AAAI 2025] [arxiv]

Forecasting Competitions with Correlated Events
Rafael Frongillo, Manuel Lladser, Anish Thilagar, Bo Waggoner
[AAAI 2025] [arxiv]

Approximately Truthful Forecasting Competitions
Anish Thilagar
[Thesis]

WOMAC: A Mechanism to Combat Leaderboard Hacking
Siddarth Srinivasan, Tao Lin, Connacher Murphy, Anish Thilagar, Yiling Chen, Ezra Karger
[arxiv]

Surrogate Losses

Consistent Polyhedral Surrogates for Top-k Classification and Variants
Jessie Finocchiaro, Rafael Frongillo, Emma Goodwill, Anish Thilagar
[ICML 2022] [arxiv]

Consistency Conditions for Differentiable Surrogate Losses
Drona Khurana, Anish Thilagar, Dhamma Kimpara, Rafael Frongillo
[arxiv]