rose-stl-lab / gradient-flow-symmetry Goto Github PK
View Code? Open in Web Editor NEW[ICLR 2023] Symmetries, flat minima, and the conserved quantities of gradient flow
Home Page: https://arxiv.org/abs/2210.17216
[ICLR 2023] Symmetries, flat minima, and the conserved quantities of gradient flow
Home Page: https://arxiv.org/abs/2210.17216
I have been going through the ensemble_CIFAR.ipynb code and I noticed what appears to be a discrepancy in the usage of the H data while computing self.pi_g_H and gH. This has left me a bit confused.
In the calculation of self.pi_g_H, the code uses the following data assignment: x, y = cif2.batch_get(-ga.in_features*ga.num_g, len(cif2.data)). However, in the calculation of gH, the code uses a different assignment: x, y = cif2.batch_get(-num+last, last).
I would like to understand the reasoning behind using different data for these computations. Could you please provide some clarification on why distinct data assignments are used in these two cases?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ 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. ๐๐๐
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 โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.