Coder Social home page Coder Social logo

optml-group / bip Goto Github PK

View Code? Open in Web Editor NEW
141.0 141.0 39.0 1.12 MB

[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

Python 100.00%

bip's People

Contributors

normaluhr avatar

Stargazers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Watchers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Forkers

maigone zaku-zaku shoplazas e-kiss-me molierflower mistyr0se herpacker moonysunny billionerd monsterdove windb3ll paramedick spicyguml xupercoin vamoko awekling nicolesherwood 0x8235 hay-man gileadr donkkaseu ntt720 masemxiao staccats d3p10y luluchou fskeo tufo830 s8xy breaklien tutuna iam20cm guspan-tanadi ambigev jincan333 asatheesh6561 arjunroyihrpa cpi12 giodalmas

bip's Issues

a bug?

Hi authors,

Congrats on the nice work. However I am confused with several lines in your code in

BiP/utils/model.py

Line 340 in c51fc35

flat_out = mask.flatten()
.
image

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

Question about calculating implicit gradients?

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

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo 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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.