Comments (2)
Hi, @pengfzhou thanks for openning this issue to share your idea, I appreciate it! If I understand correctly, your method is equivalent to back-propagation because you also need extra memory to store intermediate configurations, wrong?
Actually, the default method for obtaining single solution in GenericTensorNetworks
is not backpropagation, it is an algebra called ConfigSampler
: https://queracomputing.github.io/GenericTensorNetworks.jl/dev/ref/#GenericTensorNetworks.ConfigSampler
The SingleConfigMax(; bounded=true)
calls the back-propagation method, it can take the advantage of tropical GEMM: https://queracomputing.github.io/GenericTensorNetworks.jl/dev/performancetips/#GEMM-for-Tropical-numbers. It is slightly faster in general, while being more memory inefficient. The following is a benchmark in our paper
where Fig (d), Single MIS (P1+S1, CPU) and Single MIS (T+bounding, CPU) shows the differences.
Here, bounding is another word of saying back-propagation.
The paper is coming out soon!
from generictensornetworks.jl.
Check our paper: https://arxiv.org/abs/2205.03718
from generictensornetworks.jl.
Related Issues (16)
- Estimate memory HOT 1
- Graph problems todo list
- Rename UnWeighted HOT 1
- Laser method for generic matrix multiplication HOT 2
- Best n configurations HOT 1
- Notes on polishing documentation HOT 3
- Register HOT 54
- don't call it a vector if it's not a vector
- TagBot trigger issue HOT 24
- Plots HOT 3
- Speed up finite field algebra matrix multiplication
- Type Variables declared but not used HOT 1
- GenericTensorNetworks crashes without throwing any error messages HOT 3
- Sampling the configurations at finite temperature HOT 1
- Change Spinglass APIs
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 generictensornetworks.jl.