CMU Locus Lab's repositories
trellisnet
[ICLR'19] Trellis Networks for Sequence Modeling
convex_adversarial
A method for training neural networks that are provably robust to adversarial attacks.
pytorch_fft
PyTorch wrapper for FFTs
lcp-physics
A differentiable LCP physics engine in PyTorch.
e2e-model-learning
Task-based end-to-end model learning in stochastic optimization
perturbation_learning
Learning perturbation sets for robust machine learning
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)
breaking-poisoned-classifier
Code for paper "Poisoned classifiers are not only backdoored, they are fundamentally broken"
uniform-convergence-NeurIPS19
The code for the NeurIPS19 paper and blog on "Uniform convergence may be unable to explain generalization in deep learning".