Search Results for author: Martin Aumüller

Found 8 papers, 4 papers with code

DEANN: Speeding up Kernel-Density Estimation using Approximate Nearest Neighbor Search

no code implementations6 Jul 2021 Matti Karppa, Martin Aumüller, Rasmus Pagh

We present an algorithm called Density Estimation from Approximate Nearest Neighbors (DEANN) where we apply Approximate Nearest Neighbor (ANN) algorithms as a black box subroutine to compute an unbiased KDE.

Density Estimation

Sampling a Near Neighbor in High Dimensions -- Who is the Fairest of Them All?

1 code implementation26 Jan 2021 Martin Aumüller, Sariel Har-Peled, Sepideh Mahabadi, Rasmus Pagh, Francesco Silvestri

Given a set of points $S$ and a radius parameter $r>0$, the $r$-near neighbor ($r$-NN) problem asks for a data structure that, given any query point $q$, returns a point $p$ within distance at most $r$ from $q$.


Differentially Private Sketches for Jaccard Similarity Estimation

no code implementations18 Aug 2020 Martin Aumüller, Anders Bourgeat, Jana Schmurr

This paper describes two locally-differential private algorithms for releasing user vectors such that the Jaccard similarity between these vectors can be efficiently estimated.

The Role of Local Intrinsic Dimensionality in Benchmarking Nearest Neighbor Search

no code implementations17 Jul 2019 Martin Aumüller, Matteo Ceccarello

This paper reconsiders common benchmarking approaches to nearest neighbor search.

PUFFINN: Parameterless and Universally Fast FInding of Nearest Neighbors

2 code implementations28 Jun 2019 Martin Aumüller, Tobias Christiani, Rasmus Pagh, Michael Vesterli

We describe a novel synthetic data set that is difficult to solve for almost all existing nearest neighbor search approaches, and for which PUFFINN significantly outperform previous methods.

Data Structures and Algorithms Computational Geometry

Fair Near Neighbor Search: Independent Range Sampling in High Dimensions

1 code implementation5 Jun 2019 Martin Aumüller, Rasmus Pagh, Francesco Silvestri

There are several variants of the similarity search problem, and one of the most relevant is the $r$-near neighbor ($r$-NN) problem: given a radius $r>0$ and a set of points $S$, construct a data structure that, for any given query point $q$, returns a point $p$ within distance at most $r$ from $q$.


ANN-Benchmarks: A Benchmarking Tool for Approximate Nearest Neighbor Algorithms

2 code implementations15 Jul 2018 Martin Aumüller, Erik Bernhardsson, Alexander Faithfull

This paper describes ANN-Benchmarks, a tool for evaluating the performance of in-memory approximate nearest neighbor algorithms.

Cannot find the paper you are looking for? You can Submit a new open access paper.