Comments (6)
We did some rough benchmarking in an earlier version of megaman here: https://github.com/mmp2/megaman/tree/1c8e9010d5e03e8e0c257885209e866ad30771c5/benchmarks
Ultimately, however, when the data set becomes larger than say 100,000 points Spectral Embedding vastly out-scales the other methods. Since our data sets were all significantly larger than 100K we dedicated most of the time to benchmarking and evaluating Spectral Embedding as in the JMLR paper.
from megaman.
from megaman.
Sorry--my explanation wasn't clear.
I'm using megaman for dimensionality reduction, prior to clustering.
I'm looking at the tutorial notebook, which provides an ordered list of how well the algorithms scale from best to worst, but I was hoping for more detailed benchmarks on the embedding algorithms. Where can I find those?
Thank you,
Andrew
from megaman.
Somehow I managed to completely miss the folder clearly marked "Benchmarks".
Very helpful, thank you.
from megaman.
You didn't miss the folder, that's from an old commit -- it doesn't exist in live anymore :)
If you're interested, it would be fantastic to do a more formal benchmarking of the methods!
from megaman.
I'll put this on my to-do list, but unfortunately it's cluttered with so many other things already.
from megaman.
Related Issues (20)
- No operator available that can perform this conversion
- Modified LLE? HOT 8
- Initialization for k_means_clustering
- Any easy way to apply learned mapping on different set of points? HOT 2
- perfomance improvements for ltsa HOT 1
- Cyflann - ValueError: Buffer dtype mismatch, expected 'double' but got 'float' HOT 3
- errors when running "make test" HOT 2
- cannot import megaman.geometry HOT 2
- errors in OSX and Ubuntu, when `from megaman.embedding import SpectralEmbedding` HOT 1
- errors in OSX and Ubuntu when `from megaman.geometry import Geometry` HOT 2
- different results with the same input HOT 2
- how to choose parameters for megaman HOT 1
- Example for performing Riemannian relaxation? HOT 3
- Manifold dimension in rmetric computation
- can it be used on Windows? HOT 1
- Conda package: broken or missing pyflann dependency HOT 1
- flann/flann.hpp: No such file or directory HOT 3
- When the manifold dim is lower than embedding dim
- Make test failed with ERROR: Failure: ImportError (No module named _check_build HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from megaman.