Comments (3)
As far as I've understood, the first two steps pertain to the training of the autoencoding components (embedding, recovery) in terms of their ability to encode into latent space and learning temporal dependencies. Thus some sort of pre-training (Chapter 4.1 in the original paper)
What remains unclear to me is why the g_loss_s is included as is in the train_supervisor function, but the generator_loss_supervised is multiplied by 0.1 in the train_embedder function and by 100 in train_generator (while taking the square root). Any insights on this?
Agree on the change of the g_loss_s (and this should also be valid for generator_loss_supervised I guess).
from ydata-synthetic.
I believe that all hyperparameters are purely empirically identified parameters that seem to perform well on the datasets used by the authors. The relative weight (0.1 or 100*sqrt) may be used to balance the individual loss components. g_loss_s is added to two cross entropy components (G_loss_U and G_loss_Ue) for the generator loss, as opposed to the embedding loss. Different magnitudes of the loss components may require different scaling of g_loss_s. At least this is my intuition...Hope this helps!
from ydata-synthetic.
Thanks! Good point on the cross entropy...I guess I'll leave it at intuition for now.
from ydata-synthetic.
Related Issues (20)
- Generating long sequences - GAN mode collapse HOT 6
- AttributeError: 'tuple' object has no attribute 'betas' HOT 4
- [FEAT] make this library available for Python 3.9
- Dependency Dashboard
- [BUG] HOT 2
- [BUG] Google Colab link on README.md links to a broken page. HOT 1
- Stock dataset is not available in Google Colab HOT 5
- Question : What should .save actually save?I mean I thought that save the previous state like loss...#Time-GAN
- [BUG] HOT 1
- [FEAT] return losses of TimeGAN training
- [BUG] Python 3.8 error HOT 3
- [BUG] Unable to install version 1.0.0 with streamlit HOT 8
- [BUG] (help) Some errors in streamlit web app HOT 1
- [BUG] Failure to Import TimeGAN HOT 7
- [FEAT] support for Tensorflow 2.12 HOT 1
- Are there any new models for time series that can be used[FEAT]
- Error while generating synthetic data from CGAN HOT 3
- [BUG] Is training data be sent across the network to compute the syntactic data? HOT 1
- [SUGGESTION] - Replace comments to clear the confusion HOT 1
- Issues install on MacOS HOT 5
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 ydata-synthetic.