About Me

I am a second-year PhD student at Boston University, advised by Krzysztof Onak. Before BU, I completed my undergrad at Dartmouth College, and spent two wonderful years as a software engineer at the Microsoft Windows Base Kernel team.

LinkedIn, Google Scholar

CV

Email: tharis at bu dot edu

Research Interests

My research lies at the intersection of theoretical computer science and artificial intelligence. I seek to understand how theoretically principled approaches can help us do Machine Learning sustainably, efficiently and securely. Most recently, I have been thinking about the following topics:

• Theoretical insights for LLMs and Transformers
• Property testing for real-valued functions on hypergrid domains
• Efficient differentially private algorithms
• Local algorithms for Markov Chains
• Adversarially robust randomized algorithms.

News

May 2025

• Our paper on Compression Barriers for Autoregressive Transformers was accepted to COLT 2025!
• I will be interning at the National Institute of Informatics (NII) for the summer, alongside Professor Yuichi Yoshida.

April 2025

• I will be presenting a poster at a learning theory workshop, held at Nanyang Technological University (NTU Singapore)
• I attended ICLR 2025 in Singapore and presented a poster on my work on $k$-NN Attention.
• I presented my paper at a reading group seminar at MIT CSAIL, kindly hosted by Piotr Indyk.
• I presented a poster on adversarial robustness for search problems at the Workshop on Algorithms for Large Data (WALDO).
  • Poster