Comments (10)
Open questions
-
what is a good sparsity regularizer for the task? Sparse Sep? l1 is too brittle w.r.t. the coeff and the pruning is too restrictive. Maybe we need to use evolutionary algo to do the pruning? Somehow we need to consider "bringing back" pruned components...
-
how should we do training? one loss or many losses (with many optimizers)?
-
what is the number of constraints for n > 2?
-
what can we say from the general theory of differentiable games?
-
how does MuZero solve the problem of learning decoder + model?no details in the paper -
can we solve the equation analytically somehow and see the number of fixed points (use Mathematica's Solve[...]?) -- should work as it's a fractional-polynomial equation
-
how can we make the training distributed so that we can use multi-start to battle non-convexity?
-
what does general theory says about it all (Polyak/Nesterov/Boyd/...)? -- write Polyak?
from causality-disentanglement-rl.
Some exercises from Gerstner's lectures:
https://lcnwww.epfl.ch/gerstner/VideoLecturesANN-Gerstner.html -> Week 3
Exercise 1: Sol_Lecture7.pdf
from causality-disentanglement-rl.
Johanni: small networks have local minima
Sergei: check if GANs break on 2 dimensions
Sergei: trying 5 and 3 for a start
Johanni: first, try 5 and then high-dimensional representation for observations
from causality-disentanglement-rl.
Johanni: GANs' loss is split so that D does not make G worse ("consensus algorithm instead of a battle")
Sergei: 3 optimizers (disentanglement, model fit, non-degeneracy)
Look at Goodfellow's talks with functional analysis -- why do we freeze G?
https://www.youtube.com/watch?v=HGYYEUSm-0Q
from causality-disentanglement-rl.
Spiking networks -- built-in discreteness instead of l1
[nb from skype]
from causality-disentanglement-rl.
- Try GAN with combined loss https://github.com/sergeivolodin/gans-playground . makes things worse
- Try math in |XAX^{-1}|_0 -> min s.t. X non degenerate . NP-hard
- Try all the loss splitting options in the optimizer and try more hyperparams
from causality-disentanglement-rl.
Splitting might be bad for efficiency.
https://discourse.julialang.org/t/a-hacky-guide-to-using-automatic-differentiation-in-nested-optimization-problems/39123/6
Goal for the week: understand what the problem is (formulate concisely and solve / send to ppl)
from causality-disentanglement-rl.
Related: https://en.wikipedia.org/wiki/Sparse_dictionary_learning
from causality-disentanglement-rl.
l1 projection + masking works ~ok in a toy setting (not the synth. experiment)
adapt? https://en.wikipedia.org/wiki/Matching_pursuit
Binary search for params in sparsity https://www.cs.virginia.edu/~bjc8c/class/cs6501-f18/papers/bhattacharya16sparsesep.pdf
from causality-disentanglement-rl.
Works with an observation model estimated separately, see the report
from causality-disentanglement-rl.
Related Issues (8)
- Train a stock agent on transformed representation to a full return HOT 2
- Fix memory leak HOT 14
- Add a button to KeyChest environment
- Use visualization from the notebook in tensorboard and sacred
- Create and run hyperparameter study HOT 1
- Add a diagram of networks/losses/optimizers into README
- Add checkpoints
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 causality-disentanglement-rl.