Michael Shoemate

Many of the notebooks use features that are not available in OpenDP, like filtering. I've opened individual issues for ports that are not blocked.

From @ctcovington https://tworavens.slack.com/archives/CRNSFC508/p1588104720021900?thread_ts=1588095160.013400&cid=CRNSFC508 Mechanisms ---------- - Exponential - McSherry & Talwar (2007) https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/mdviadp.pdf - Gaussian - Dwork & Roth (2014) https://www.cis.upenn.edu/~aaroth/Papers/privacybook.pdf - Geometric - Ghosh, Roughgarden, & Sundararajan (2012) https://theory.stanford.edu/~tim/papers/priv.pdf...

Exponential [1] Gaussian [2] Geometric [3][4] Laplace [5] DPCount [3] DPHistogram [3][4] DPMean [5] DPSum [5] DPVariance [6] [1] F. McSherry and K. Talwar, "Mechanism Design via Differential Privacy," 48th...

Usually I'd just say "go for it!", but we have a pretty long backlog of PR's right now, and clippy fixes usually cause conflicts. In order to avoid rebase conflicts...

@andrewvyrros Any objections to adding clippy to the CI?

Two minor nits to get the ball rolling: 1. Could you please remove the .pdf file? I think it would be best to keep binary files out of the repo....

Now that we have filtering (the lib calls it subsetting), this notebook should now be ready to port.

e75b1eb was meant to reference #113, not #103

Two potential routes here. Route 1: Do special-casing in mechanisms. If `privacy_definition.strict_parameter_checks` are off, infinite epsilon disables noise addition. Route 2: Introduce an intermediate filter level with one of these...

Specifically a proof for `make_find_bin`, which should be an application of the row-by-row proof. Only necessary to prove that membership in the input atom domain implies membership in the output...