a fifth-year computer science Ph.D. candidate at UC Irvine advised by Erik Sudderth.
My hobbies include board games, paddleboarding, and taking care of my dog Claude.
My research focuses on how we can introduce structure and constraints to deep generative models when we have prior knowledge but limited data. If you want to connect about research or pedagogy, feel free to contact me at firstname.last@gmail.com.
Undergraduate data science education: Who has the microphone
and what are they saying? M Dogucu, S Demirci, H Bendekgey, FZ Ricci, CM Medina. In submission. ArXiv Link Talks and Presentations: Electronic Conference on Teaching Statistics, 2024 |
Scaling study of diffusion in dynamic crowded spaces. H Bendekgey, G Huber, and D Yllanes. Journal of Physics A: Mathematical and Theoretical, 2024. ArXiv Link Talks and Presentations: March Meeting 2022 |
Unbiased Learning of Deep Generative Models with Structured
Discrete Representations. H Bendekgey, G Hope, E Sudderth. NeurIPS 2023. ArXiv Link Talks and Presentations: Pomona College Computer Science Colloquium Series |
Scalable & Stable Surrogates for Flexible Classifiers with
Fairness Constraints. H Bendekgey, E Sudderth. NeurIPS 2021. Talks and Presentations: Southern California Machine Learning Symposium 2021 |
Clustering Player Strategies from Variable-Length Game Logs
in Dominion H Bendekgey. AAAI Workshop on Knowledge Extraction from Games (KEG), 2019. ArXiv Link |