Семинар HDI Lab: Alexey Kroshnin (IITP RAS, HSE University), Robust k-means clustering in metric spaces
13 апреля 2021 г. в 18:00 состоится очередной семинар международной лаборатории стохастических алгоритмов и анализа многомерных данных. С докладом "Robust k-means clustering in metric spaces" выступит Алексей Крошнин (IITP RAS, HSE University).
Аннотация: In this talk we consider robust median of means based algorithms for the k-means clustering problem in a metric space. The main results are non-asymptotic excess distortion bounds that hold under the two bounded moments assumption in a general separable metric space. In the case of Hilbert space our bounds have the sub-Gaussian form depending on the probability mass of the lightest cluster of an optimal quantizer. In a special case of clustering in R^d we prove matching (up to constant factors) non-asymptotic upper and lower bounds on the excess distortion, which depend on the probability mass of the lightest cluster and on the variance. The talk is based on a joint work with Yegor Klochkov and Nikita Zhivotovskiy https://arxiv.org/abs/2002.02339.
Ссылка на семинар: https://us02web.zoom.us/j/9252879297
Следите за обновлениями семинара в Telegram!