Zobrazeno 1 - 10 of 57 pro vyhledávání: '"Ankur Moitra"'
1
Robustly Learning General Mixtures of Gaussians
Autor: Allen Liu, Ankur Moitra
Publikováno v: Journal of the ACM. 70:1-53
This work represents a natural coalescence of two important lines of work — learning mixtures of Gaussians and algorithmic robust statistics. In particular, we give the first provably robust algorithm for learning mixtures of any constant number of
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::e0a587ea69a35030310264a7468d663f
https://doi.org/10.1145/3583680
Zobrazit plný text záznamu
3
A New Approach to Learning Linear Dynamical Systems
Autor: Ainesh Bakshi, Allen Liu, Ankur Moitra, Morris Yau
Linear dynamical systems are the foundational statistical model upon which control theory is built. Both the celebrated Kalman filter and the linear quadratic regulator require knowledge of the system dynamics to provide analytic guarantees. Naturall
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c1397a9fc2309965900a2e8ae3a1565d
Zobrazit plný text záznamu
4
Robust Voting Rules from Algorithmic Robust Statistics
Autor: Allen Liu, Ankur Moitra
Publikováno v: Proceedings of the 2023 Annual ACM-SIAM Symposium on Discrete Algorithms (SODA) ISBN: 9781611977554
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::fbc85303e75a08d1556843fbab671728
https://doi.org/10.1137/1.9781611977554.ch133
Zobrazit plný text záznamu
5
Minimax Rates for Robust Community Detection
Autor: Allen Liu, Ankur Moitra
In this work, we study the problem of community detection in the stochastic block model with adversarial node corruptions. Our main result is an efficient algorithm that can tolerate an $\epsilon$-fraction of corruptions and achieves error $O(\epsilo
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a5f5f83f58c58da11684f50ff30eaf77
http://arxiv.org/abs/2207.11903
Zobrazit plný text záznamu
6
Robustness meets algorithms
Autor: Alistair Stewart, Daniel M. Kane, Ankur Moitra, Gautam Kamath, Ilias Diakonikolas, Jerry Li
Publikováno v: Communications of the ACM, vol 64, iss 5
In every corner of machine learning and statistics, there is a need for estimators that work not just in an idealized model, but even when their assumptions are violated. Unfortunately, in high dimensions, being provably robust and being efficiently
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::933ab5f8df4e23de670400571866b444
https://doi.org/10.1145/3453935
Zobrazit plný text záznamu
8
Kalman Filtering with Adversarial Corruptions
Autor: Sitan Chen, Frederic Koehler, Ankur Moitra, Morris Yau
Here we revisit the classic problem of linear quadratic estimation, i.e. estimating the trajectory of a linear dynamical system from noisy measurements. The celebrated Kalman filter gives an optimal estimator when the measurement noise is Gaussian, b
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0b6becdbc2e21d6b1ea00c847696c596
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje