lchizat/2022-wide-linear-NN lchizat/2022-wide-linear-NN

  • Stars
    star
    1
  • Language
    Jupyter Notebook
  • Created about 2 years ago
  • Updated about 2 years ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
lchizat/2022-wide-linear-NN
github

lchizat

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Dynamics of infinitely wide linear neural nets

More Repositories

1

optimal-transport

Optimal transport and generalizations
Jupyter Notebook
52
star
2

2020-implicit-bias-wide-2NN

Code for the paper: "Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss" (Chizat and Bach)
Julia
7
star
3

2020_implicitbias_blog

Code for the figure of the "implicit bias" blog post
Jupyter Notebook
6
star
4

2019-sparse-optim-measures

Source code for the paper "Sparse Optimization on Measures with Over-parameterized Gradient Descent"
Julia
5
star
5

illustrations

Julia
2
star
6

2021-measures-PGM

Code for the paper "Convergence Rates of Gradient Methods for Convex Optimization in the Space of Measures"
Jupyter Notebook
2
star
7

2022-mean-field-langevin-rate

Code for the paper "Mean-Field Langevin Dynamics : exponential convergence and annealing"
1
star
8

2021-exp-ICM

Jupyter Notebook
1
star