Comments (3)
Based on the theorem in our paper, the performance of CLUB is based on the quality of the variational approximation q_theta(y|x). Since the dimension of the sample (x,y) is changed, the variational approximation q_\theta(y|x) is supposed to be changed to have a better estimation. My suggestion is to reduce the hidden_size of q_\theta(y|x) for a better approximation to data samples with lower dimensions.
from club.
@erow InfoNCE不是互信息最大化的近似估计吗?为什么和CLUB比较?
from club.
@erow InfoNCE不是互信息最大化的近似估计吗?为什么和CLUB比较?
目的都是为了估计互信息,只是有的方法是最大化求MI的下界,有的是最小化求MI的上界。
from club.
Related Issues (20)
- DA experiments : CIFAR and STL
- The mi_minimization.ipynb
- About the logvar prediction HOT 10
- Equation issue in mi_minimization.ipynb HOT 2
- The symmetric problem about the CLUB MI estimator? HOT 1
- About the computation of loglikeli HOT 1
- Query about Example Training HOT 3
- Hi, thanks for the good work. I have a general question: according to your code, the positive term in the pytorch version minors a term of logvar but in ther tensorflow version it doesn't. Does it remain any tips in this two versions? And I also encounter a problem in MI minimization that the MI in the earlier training epoches is always <0, is it resonable and any tips to slove it? HOT 2
- Understanding question - what value to take of the estimator while evaluating? HOT 1
- 您好,请问CLUB和vLUB HOT 2
- How to train CLUBForCategorical? Can you provide an example? Thanks a lot! HOT 1
- I want to apppy the mutual imformation to learn the disentangled latent codes. But if there are four latent codes, how to minimize the objective I(X1; X2; X3; X4)? HOT 2
- 关于两个tensor的互信息 HOT 1
- CLUBForCategorical estimating p(y|x) , why not pass logits through a softmax activation? HOT 1
- Questions about the bound HOT 3
- Negative Mutual Information Values in Feature Decoupling with MI Minimization HOT 1
- The loss training log-likelihood when (x, y) is absolutely independent HOT 4
- confused about logvar HOT 2
- 您好!论文中的公式6是不是存在一些错误呀 HOT 12
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 club.