23 open source projects by locuslab

A differentiable LCP physics engine in PyTorch.

[ICLR 2020] A repository for extremely fast adversarial training using FGSM

Input Convex Neural Networks

Provable adversarial robustness at ImageNet scale

[NeurIPS'20] Multiscale Deep Equilibrium Models

Task-based end-to-end model learning in stochastic optimization

Learning perturbation sets for robust machine learning

A fast and differentiable QP solver for PyTorch.

A fast and differentiable model predictive control (MPC) solver for PyTorch.

[ICLR'19] Trellis Networks for Sequence Modeling

[NeurIPS'19] Deep Equilibrium Models

OptNet: Differentiable Optimization as a Layer in Neural Networks

Bridging deep learning and logical reasoning using a differentiable satisfiability solver.

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

PyTorch wrapper for FFTs

Sequence modeling benchmarks and temporal convolutional networks

The Limited Multi-Label Projection Layer

A Newton ADMM based solver for Cone programming.

dreaml: dynamic reactive machine learning

Code for "Gradient descent GAN optimization is locally stable"

[ICML'20] Multi Steepest Descent (MSD) for robustness against the union of multiple perturbation models.