[fnord123]

http://www.frankmcsherry.org/assets/COST.pdf

[frankmcsherry]

It's a bit different, right, because that paper presents better algorithms on the same datasets as the work it cites.

[fnord123]

Yes it's different. Another part of Benchmarklandia is where researchers make custom algorithms for the same dataset. Benchmarks targeting MNIST is a great example. :)