All Projects → MaestroGraph → sparse-hyper

MaestroGraph / sparse-hyper

Licence: MIT License
Code for the paper "Learning sparse transformations through backpropagation"

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to sparse-hyper

NMFADMM
A sparsity aware implementation of "Alternating Direction Method of Multipliers for Non-Negative Matrix Factorization with the Beta-Divergence" (ICASSP 2014).
Stars: ✭ 39 (-9.3%)
Mutual labels:  sparse-matrix
dbcsr
DBCSR: Distributed Block Compressed Sparse Row matrix library
Stars: ✭ 65 (+51.16%)
Mutual labels:  sparse-matrix
SpM
Sparse modeling tool for analytical continuation of imaginary-time Green's function
Stars: ✭ 16 (-62.79%)
Mutual labels:  sparse-modeling
grblas
Python wrapper around GraphBLAS
Stars: ✭ 22 (-48.84%)
Mutual labels:  sparse-matrix
sympiler
Sympiler is a Code Generator for Transforming Sparse Matrix Codes
Stars: ✭ 32 (-25.58%)
Mutual labels:  sparse-matrix
sparse
Sparse matrix formats for linear algebra supporting scientific and machine learning applications
Stars: ✭ 136 (+216.28%)
Mutual labels:  sparse-matrix
gardenia
GARDENIA: Graph Analytics Repository for Designing Efficient Next-generation Accelerators
Stars: ✭ 22 (-48.84%)
Mutual labels:  sparse-matrix
L0Learn
Efficient Algorithms for L0 Regularized Learning
Stars: ✭ 74 (+72.09%)
Mutual labels:  sparse-modeling
AsFem
A Simple Finite Element Method program (AsFem)
Stars: ✭ 108 (+151.16%)
Mutual labels:  sparse-matrix
RcppML
Rcpp Machine Learning: Fast robust NMF, divisive clustering, and more
Stars: ✭ 52 (+20.93%)
Mutual labels:  sparse-matrix
spm-image
Sparse modeling and Compressive sensing in Python
Stars: ✭ 93 (+116.28%)
Mutual labels:  sparse-modeling
eigen
Owl's OCaml Interface to Eigen3 C++ Library
Stars: ✭ 30 (-30.23%)
Mutual labels:  sparse-matrix
Eigen Git Mirror
THIS MIRROR IS DEPRECATED -- New url: https://gitlab.com/libeigen/eigen
Stars: ✭ 1,659 (+3758.14%)
Mutual labels:  sparse-matrix
coolpuppy
A versatile tool to perform pile-up analysis on Hi-C data in .cool format.
Stars: ✭ 42 (-2.33%)
Mutual labels:  sparse-matrix
monolish
monolish: MONOlithic LInear equation Solvers for Highly-parallel architecture
Stars: ✭ 166 (+286.05%)
Mutual labels:  sparse-matrix
sparse dot
Python wrapper for Intel Math Kernel Library (MKL) matrix multiplication
Stars: ✭ 38 (-11.63%)
Mutual labels:  sparse-matrix

Sparse, adaptive hyperlayers

This is the codebase that accompanies the paper Learning sparse transformations through brackpropagation. Follow the link for the paper and an annotated slidedeck.

Disclaimer

We are still cleaning up the code, but it should now be relatively readable. Make sure you have PyTorch 1.0 installed and start by running experiments/identity.py, which runs the identity experiment:

 python experiments/identity.py -F

The -F flag sets all values of the matrix to 1, which makes learning a little easier.

Feel free to ask me for help by making an issue, or sending an email.

The archive branch contains a snapshot of the code at the time the preprint went up.

Dependencies (probably incomplete)

  • Numpy
  • Matplotlib
  • Pytorch 0.4
  • torchvision
  • tensorboardX
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].