Code

The github pages contain more information for each individual project. If you are interested in code that is currently not on github, please send me an email.

Datasets

The following repositories contain new test sets for CIFAR-10 and ImageNet. They also provide code for working with and assembling these test sets.

Adversarial Robustness

Together with the MadryLab, I have worked on the following baseline implementation for adversarial robustness:

Nearest neighbor

FALCONN is a fast implementation of locality-sensitive hashing (LSH) for cosine similarity. The code was developed in collaboration with Ilya Razenshteyn.

Structured sparsity

When working with structure beyond sparsity, the the algorithmic core is often to projection onto a structured sparse set. The following github repositories contain code for various projection operators:

The algorithm underlying the graph sparsity code is a fast implementation of the Goemans-Williamson scheme for prize-collecting Steiner forest (PCSF) problems. Aleksander Lenail from the Fraenkel Lab at MIT is maintaining a version of the above PCSF code for applications in computational biology.

Distribution learning

The following repository contains code for differentially private distribution learning: github.