10.9k citations
- Centre National de la Recherche ScientifiqueFR655 papers
- University of California, BerkeleyUS568 papers
- University of MichiganUS554 papers
- Brookhaven National LaboratoryUS526 papers
- University of WashingtonUS484 papers
- Stony Brook UniversityUS483 papers
- University of ChicagoUS466 papers
- Iowa State UniversityUS457 papers
- McGill UniversityCA454 papers
- University of ArizonaUS454 papers
- University of ManchesterGB453 papers
- Université Paris CitéFR448 papers
5 papers · 2 filters
Near-Optimal Density Estimation in Near-Linear Time Using Variable-Width Histograms
Siu-On Chan, Ilias Diakonikolas, Rocco A. Servedio +1
Let be an unknown and arbitrary probability distribution over . We consider the problem of {\em density estimation}, in which a learning algorithm is given i.i.d. draws…
Notes on using Determinantal Point Processes for Clustering with Applications to Text Clustering
Apoorv Agarwal, Anna Choromanska, Krzysztof Choromanski
In this paper, we compare three initialization schemes for the KMEANS clustering algorithm: 1) random initialization (KMEANSRAND), 2) KMEANS++, and 3) KMEANSD++. Both KMEANSRAND an…
Scalable Nonlinear Learning with Adaptive Polynomial Expansions
Alekh Agarwal, Alina Beygelzimer, Daniel Hsu +2
Can we effectively learn a nonlinear representation in time comparable to linear learning? We describe a new algorithm that explicitly and adaptively expands higher-order interacti…
The Large Margin Mechanism for Differentially Private Maximization
Kamalika Chaudhuri, Daniel Hsu, Shuang Song
A basic problem in the design of privacy-preserving algorithms is the private maximization problem: the goal is to pick an item from a universe that (approximately) maximizes a dat…
Preventing False Discovery in Interactive Data Analysis is Hard
Moritz Hardt, Jonathan Ullman
We show that, under a standard hardness assumption, there is no computationally efficient algorithm that given samples from an unknown distribution can give valid answers to $n…