sungyoon-lee

bcp

[NeurIPS 2020] Lipschitz-Certifiable Training with a Tight Outer Bound | BCP (Box Constraint Propagation) | ⚡💪🛡️

colt

Convex Layerwise Adversarial Training (COLT)

convex_adversarial

A method for training neural networks that are provably robust to adversarial attacks.

hippylib

An Extensible Software Framework for Large-Scale Inverse Problems

LossLandscapeMatters

[NeurIPS 2021] Towards Better Understanding of Training Certifiably Robust Models against Adversarial Examples | ⛰️⚠️

PyHessian

PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks

releasing-research-code

Tips for releasing research code in Machine Learning (with official NeurIPS 2020 recommendations)

sungyoon-lee

sungyoon-lee.github.io

SVC

sungyoon-lee/bcp

[NeurIPS 2020] Lipschitz-Certifiable Training with a Tight Outer Bound | BCP (Box Constraint Propagation) | ⚡💪🛡️

sungyoon-lee/LossLandscapeMatters

[NeurIPS 2021] Towards Better Understanding of Training Certifiably Robust Models against Adversarial Examples | ⛰️⚠️

sungyoon-lee/SVC

sungyoon-lee/colt

Convex Layerwise Adversarial Training (COLT)

sungyoon-lee/convex_adversarial

A method for training neural networks that are provably robust to adversarial attacks.

sungyoon-lee/hippylib

An Extensible Software Framework for Large-Scale Inverse Problems

sungyoon-lee/PyHessian

PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks

sungyoon-lee/releasing-research-code

Tips for releasing research code in Machine Learning (with official NeurIPS 2020 recommendations)

sungyoon-lee/sungyoon-lee

sungyoon-lee/sungyoon-lee.github.io

sungyoon-lee/universal