Comments (1)
We have not extensively trying out per-layer lr/momentum. In YF, we want to demonstrate momentum is related the range of curvatures of all variables. That is the reason why we decide to use single lr/momentum. I am not sure in a general setting what would happen if there is multiple momentum. If the Hessian can be closely approximated by a diagonal block matrix, multiple momentum might also work I think. On the other hand, it might also be possible the Hessian can not be properly approximated by diagonal block matrix, then it might violate our analysis on analyzing the range of curvature. We do not have direct empirical evidence on this question :).
from yellowfin_pytorch.
Related Issues (17)
- NaN and AssertionError HOT 21
- The nonzero count in grad_sparsity fails if grad is zero
- Different variance in publication and implementation HOT 1
- illegal memory access HOT 2
- too many things are kept as state
- Learning Rate Decay HOT 2
- LR keeps growing instead of shrinking HOT 11
- Python3 changes for word_language_model HOT 1
- 'YFOptimizer' object has no attribute '_h_min' when calling optimizer.state_dict()
- Bad performance on large vision models HOT 3
- Does not work with pytorch 0.4 HOT 2
- AttributeError: 'YFOptimizer' object has no attribute '_state_checkpoint' HOT 3
- YF doesn't work for the cv task HOT 4
- gradient clipping doesn't work with dict params HOT 2
- Assertion Error: assert root.size == 1 HOT 1
- Feature Request: Implement state_dict() / load_state_dict() HOT 2
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 yellowfin_pytorch.