The author defends e-means as a superior, drop-in replacement for Lloyd's algorithm that uses scaling laws to automatically tune hyperparameters and escape local minima faster. Critics argue the method relies on known techniques like exponential moving averages and mini-batches without sufficient novelty or rigorous comparison against well-tuned baselines like scikit-learn's implementation.
81 readable replies · Supporting reply 1 · Supporting reply 2 · Supporting reply 3 · Supporting reply 4facebookresearch
faiss
C++2017–2026
facebookresearch / faiss
faiss
A library for efficient similarity search and clustering of dense vectors.
45Distinct people
53Mentions
1Explicit recommenders
41.6KGitHub stars
What to know before exploring
What it is
A library for efficient similarity search and clustering of dense vectors.
GitHub
Where it is used
No documented product use was verified in the last source check.
What people are saying
This tutorial is very complex. Here's how to get free semantic search with much less complexity: 1. Install sentence-transformers [1] 2. Initialize the MiniLM model - `model =…
vikp used a recommendation phrase. One indexed comment matches. This is a phrase match, not a verdict.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
- spotify/annoy · linked in 4 of the same discussions
- searchivarius/nmslib · linked in 2 of the same discussions
Mentioned in the same Hacker News threads. That is not proof they are substitutes.
This week on Hacker News
Nov 8–Nov 15 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/15/2026, 8:03:49 PM UTC.
Mentions over time
HN mentions by year53 dated mentions
Observed mentions: 2017-03-02 20:35:13 UTC to 2026-04-10 23:12:49 UTC.
* An incomplete calendar period is marked with an outlined bar. Its count is not directly comparable with a full period.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| 2017 | 2017-01-01 00:00:00 UTC | 2018-01-01 00:00:00 UTC | 2 | 1 | 1 |
| 2018 | 2018-01-01 00:00:00 UTC | 2019-01-01 00:00:00 UTC | 3 | 0 | 3 |
| 2019 | 2019-01-01 00:00:00 UTC | 2020-01-01 00:00:00 UTC | 5 | 0 | 5 |
| 2020 | 2020-01-01 00:00:00 UTC | 2021-01-01 00:00:00 UTC | 1 | 0 | 1 |
| 2021 | 2021-01-01 00:00:00 UTC | 2022-01-01 00:00:00 UTC | 8 | 1 | 7 |
| 2022 | 2022-01-01 00:00:00 UTC | 2023-01-01 00:00:00 UTC | 3 | 0 | 3 |
| 2023 | 2023-01-01 00:00:00 UTC | 2024-01-01 00:00:00 UTC | 20 | 1 | 19 |
| 2024 | 2024-01-01 00:00:00 UTC | 2025-01-01 00:00:00 UTC | 8 | 1 | 7 |
| 2025 | 2025-01-01 00:00:00 UTC | 2026-01-01 00:00:00 UTC | 1 | 0 | 1 |
| 2026 (partial) | 2026-01-01 00:00:00 UTC | 2027-01-01 00:00:00 UTC | 2 | 2 | 0 |
What Hacker News says
3 sourcesKIkilotaras·Feb 27, 2018
> After the faces are located, they’re matched against a set of candidates (which I would guess is an enumeration if all your Nth order friends [who don’t opt out of this], to reduce computational complexity.
Face recognition is usually done by first transforming the face into vector space and than looking for the closest vector from known, e.g. openface[1] (which is based on google 2015 paper "FaceNet: A Unified Embedding for Face Recognition and Clustering"). Facebook itself opensourced[2] a library for efficient search of nearest neighbors in such spaces.
It doesn't seem likely that generating set of Nth order friends (which grow very quickly with N) would be better than just having a global set or a split of global set by some characteristics (e.g. gender, race).
[1] https://cmusatyalab.github.io/openface/
[2] https://github.com/faceb
Read the rest
Various approaches based on LSH (locality sensitive hashing) and random projections.
But "the best" really depends on your data profile, as the generic problem formulation, for completely generic vectors, is too… generic. See also the curse of dimensionality [0].
In practical terms, if you're looking for an actual implementation to use, here's a benchmark of some state-of-the-art implementations for high-dimensional vector search: http://radimrehurek.com/2013/12/performance-shootout-of-near... and also the updated https://github.com/erikbern/ann-benchmarks.
In particular, for something good AND open source:
- Leonid Boytsov's NMSLIB [1]
- Erik Bernhardsson's Annoy [2]
- Facebook's FAISS [3]
For a commercial engine focused more on practical use (index management, transactions, versioning, support), see ScaleText [4] (disclaimer: our produc
Read the rest
> During the inference time, we first represent user input as a vector using query encoder; then iterate over all available products and compute the metric between the query vector and each of them; finally, sort the results. Depending on the stock size, the metric computation part could take a while. Fortunately, this process can be easily parallelized.
An alternative is to precompute a search index over the item vectors if the dataset of items is very large and you’re OK with running an approximate search to trade a bit of recall for performance, using algorithms provided by libraries like the following.
Nmslib: https://github.com/searchivarius/nmslib
Faiss (Facebook): https://github.com/facebookresearch/faiss
Annoy (Spotify): https://github.com/spotify/annoy
In Building Cross-Lingual End-to-End Product Search with Tensorflow