CMU Locus Lab

optnet

OptNet: Differentiable Optimization as a Layer in Neural Networks

trellisnet

[ICLR'19] Trellis Networks for Sequence Modeling

convex_adversarial

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

smoothing

Provable adversarial robustness at ImageNet scale

pytorch_fft

PyTorch wrapper for FFTs

lcp-physics

A differentiable LCP physics engine in PyTorch.

icnn

Input Convex Neural Networks

mdeq

[NeurIPS'20] Multiscale Deep Equilibrium Models

e2e-model-learning

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

robust_overfitting

DC3

DC3: A Learning Method for Optimization with Hard Constraints

perturbation_learning

Learning perturbation sets for robust machine learning

edge-of-stability

robust-nn-control

Enforcing robust control guarantees within neural network policies

monotone_op_net

Monotone operator equilibrium networks

orthogonal-convolutions

Implementations of orthogonal and semi-orthogonal convolutions in the Fourier domain with applications to adversarial robustness

convmixer-cifar10

Simple CIFAR-10 classification with ConvMixer

stable_dynamics

Companion code to "Learning Stable Deep Dynamics Models" (Manek and Kolter, 2019)

ImpSq

Implicit^2: Implicit model for implicit neural representations

breaking-poisoned-classifier

Code for paper "Poisoned classifiers are not only backdoored, they are fundamentally broken"

intermediate_robustness

mixing

The Mixing method: coordinate descent for low-rank semidefinite programming

sdp_clustering

ase

Analogous Safe-state Exploration (ASE) is an algorithm for provably safe and optimal exploration in MDPs with unknown, stochastic dynamics.

JIIO-DEQ

Efficient joint input optimization and inference with DEQ

uniform-convergence-NeurIPS19

The code for the NeurIPS19 paper and blog on "Uniform convergence may be unable to explain generalization in deep learning".

mixsat

Low-rank semidefinite programming for the MAX2SAT problem

sdp_mrf

lipschitz_mondeq

mugrade