About

I am a PhD student at the University of Helsinki and a machine learning research engineer at Time Atlas Labs. I am advised by Teemu Roos and my research interests include approximate nearest neighbor search, vector databases, and ML systems.

In the past, I worked on machine learning systems with Tianqi Chen at Carnegie Mellon University in Pittsburgh, US and designed information-retrieval algorithms at iKVA in Cambridge, UK. I received my BSc and MSc degrees in Computer Science from the University of Helsinki.

Selected Publications

E. Jääsaari, V. Hyvönen, T. Roos. LoRANN: Low-rank matrix factorization for approximate nearest neighbor search. Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS 2024). [pdf]

V. Hyvönen, E. Jääsaari, T. Roos. A Multilabel Classification Framework for Approximate Nearest Neighbor Search. Journal of Machine Learning Research 25(46):1–51 (JMLR 2024). [pdf]

V. Hyvönen, E. Jääsaari, T. Roos. A Multilabel Classification Framework for Approximate Nearest Neighbor Search. Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS 2022). [pdf]

T. Silander, J. Leppä-aho, E. Jääsaari, T. Roos. Quotient normalized maximum likelihood criterion for learning Bayesian network structures. Proceedings of the 21st International Conference on Artificial Intelligence and Statistics (AISTATS 2018). [pdf]

E. Jääsaari, J. Leppä-aho, T. Silander, T. Roos. Minimax optimal Bayes mixtures for memoryless sources over large alphabets. Proceedings of the 29th International Conference on Algorithmic Learning Theory (ALT 2018). [pdf]