optml-group / bip Goto Github PK
View Code? Open in Web Editor NEW[NeurIPS22] "Advancing Model Pruning via Bi-level Optimization" by Yihua Zhang*, Yuguang Yao*, Parikshit Ram, Pu Zhao, Tianlong Chen, Mingyi Hong, Yanzhi Wang, and Sijia Liu
[NeurIPS22] "Advancing Model Pruning via Bi-level Optimization" by Yihua Zhang*, Yuguang Yao*, Parikshit Ram, Pu Zhao, Tianlong Chen, Mingyi Hong, Yanzhi Wang, and Sijia Liu
Hi authors,
Congrats on the nice work. However I am confused with several lines in your code in
Line 340 in c51fc35
Here from l.340-342 it seems that the three lines of code will not change the value of "mask" as flatten is not an in-place operation?
Thanks
Dear Authors,
In Line 97 (bilevel.py), it calculates the implicit gradient using the following code:
implicit_gradient = -args.lr2 * mask_grad_vec * param_grad_vec
Here, mask_grad_vec consists of non-zero mask gradients, and zero weight gradients, because of the pruning mode.
However, in the paper Algorithm A1 Bip, Line 5, the multiplication involves the gradient of weights ∇θ tr(m * θ), rather than that of a mask.
Can you help me understand this or is this possibly a bug?
Best
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.