FALCONN (FAst Lookups of Cosine and Other Nearest Neighbors) is a C++ library with a Python wrapper for similarity search over high-dimensional data. It supports cosine similarity and the Euclidean distance. The main ingredient of FALCONN is a Locality-Sensitive Hashing family for cosine similarity that is: Optimal in theory, Fast in practice.
Keywords for this software
References in zbMATH (referenced in 12 articles )
Showing results 1 to 12 of 12.
- Davoodi, Arash Gholami; Chang, Sean; Yoo, Hyun Gon; Baweja, Anubhav; Mongia, Mihir; Mohimani, Hosein: ForestDSH: a universal hash design for discrete probability distributions (2021)
- Gerace, Federica; Loureiro, Bruno; Krzakala, Florent; Mézard, Marc; Zdeborová, Lenka: Generalisation error in learning with random features and the hidden manifold model (2021)
- Kirshanova, Elena; Laarhoven, Thijs: Lower bounds on lattice sieving and information set decoding (2021)
- Li, Yuliang; Wang, Jianguo; Pullman, Benjamin; Bandeira, Nuno; Papakonstantinou, Yannis: Index-based, high-dimensional, cosine threshold querying with optimality guarantees (2021)
- Żogała-Siudem, Barbara; Jaroszewicz, Szymon: Fast stepwise regression based on multidimensional indexes (2021)
- Chen, Lijie: On the hardness of approximate and exact (bichromatic) maximum inner product (2020)
- Anagnostopoulos, Evangelos; Emiris, Ioannis Z.; Psarros, Ioannis: Randomized embeddings with slack and high-dimensional approximate nearest neighbor (2018)
- Chandrasekaran, Karthekeyan; Dadush, Daniel; Gandikota, Venkata; Grigorescu, Elena: Lattice-based locality sensitive hashing is optimal (2018)
- Chen, Lijie: On the hardness of approximate and exact (bichromatic) maximum inner product (2018)
- Laarhoven, Thijs: Graph-based time-space trade-offs for approximate near neighbors (2018)
- Rachkovskij, D. A.: Index structures for fast similarity search for real-valued vectors. I (2018)
- Laarhoven, Thijs: Hypercube LSH for approximate near neighbors (2017)