Wang Changxu DelightRun
DelightRun
/ l2sqr_functions.cpp
Created
September 2, 2021 09:19
— forked from matsui528/l2sqr_functions.cpp
Runtime evaluation for squared Euclidean distances with SSE, AVX, AVX512 implementations
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #include <iostream> | |
| #include <random> | |
| #include <chrono> | |
| #include <x86intrin.h> | |
| #include <cassert> | |
| // Runtime evaluation for squared Eucliden distance functions | |
| // - fvec_L2_sqr_ref: naive reference impl from Faiss | |
| // - fvec_L2_sqr_sse: SSE impl from Faiss | |
| // - fvec_L2_sqr_avx: AVX impl from Faiss |
DelightRun
/ intdim_mle.py
Created
January 26, 2019 08:49
— forked from mehdidc/intdim_mle.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| """ | |
| Implementation of 'Maximum Likelihood Estimation of Intrinsic Dimension' by Elizaveta Levina and Peter J. Bickel | |
| how to use | |
| ---------- | |
| The goal is to estimate intrinsic dimensionality of data, the estimation of dimensionality is scale dependent | |
| (depending on how much you zoom into the data distribution you can find different dimesionality), so they | |
| propose to average it over different scales, the interval of the scales [k1, k2] are the only parameters of the algorithm. |