About Me

Hello everyone, welcome to my website!

My name is Donya, I am a Ph.D. candidate at TTIC (it's a wonderful place to focus on Machine Learning theory at UChicago) where I am fortunate to be advised by Avrim Blum. My research lies at the intersection of machine learning theory and theoretical computer science. I’m broadly interested in robustness, reliability, and explainability with provable guarantees, and in developing and applying algorithmic and statistical tools to study them. When I'm not thinking about very concrete research questions, I like philosophizing about the [not so well defined] higher-level related concepts, such as [the meaning and means of] trust and safety.

"The beauty of mathematics only shows itself to more patient followers," and I would be lying if I said I was patient enough during my undergrad. Back then, I worked as an intern in different places, from the Sharif University of Technology, Iran, to the Max Planck Institute, Germany, under the supervision of Peter Benner, and the University of Texas at Austin, USA. I had the opportunity to get to know fantastic people from all around the world and work with them. I was fortunate to work on my Bachelor's Thesis under the supervision of Keshav Pingali from the University of Texas at Austin. I was the first (and hopefully not the last) Bachelor's student in my university who has officially done her thesis internationally.

Education

Toyota Technological Institute at Chicago, IL, USA
March 2024—June 2028 (Expected)
Ph.D. Candidate in Computer Science
Advised by Avrim Blum
Toyota Technological Institute at Chicago, IL, USA
September 2022— June 2024
M.Sc. in Computer Science
Mentored by Nati Srebro
GPA: 4.0/4.0
University of Tehran, Iran
Sept. 2017—July 2022
B.Sc. in Electrical Engineering—Communications
GPA: Final year: 19.58/20.00 (Highest Distinctions)
Minor in Computer Engineering
Farzanegan High School, Iran
Sept. 2013—Jun. 2017
Diploma in Mathematics and Physics' Discipline
GPA: 20.00/20.00

Publications

Most of my publications have authors ordered alphabetically, indicated by (α–β), as is customary in theoretical computer science.

Proofs as Explanations: Short Certificates for Reliable Predictions
Avrim Blum, Steve Hanneke, Chirag Pabbaraju, Donya Saless(α–β)
Under Submission
PAC Learning with Improvements
Idan Attias, Avrim Blum, Keziah Naggita, Donya Saless, Dravyansh Sharma, and Matthew Walter(α–β)
Under Submission
Regularized Robustly Reliable Learners and Instance Targeted Attacks
Avrim Blum, Donya Saless(α–β)
Under Submission
HyperNetVec: Fast and scalable hierarchical embedding for hypergraphs
Sepideh Maleki, Donya Saless, Dennis P. Wall, Keshav Pingali
NetSci-X 2022
NetVec: A scalable hypergraph embedding system
Sepideh Maleki, Donya Saless, Dennis P. Wall, Keshav Pingali
ICML 2021 Workshop: Self-Supervised Learning for Reasoning and Perception

Languages

English, TOEFL iBT
Total: 114, Reading: 28, Listening: 30, Speaking: 30, Writing: 26
Apr. 2021
German, B2

Honors and Awards

  • Ranked in the top 0.1% among students taking part in Iran's National University Entrance Exam (Konkour) in the Mathematics & Physics Concentration.
    Nov. 2017

Contact

Email: