We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Plotting a learner's average performance against the number of training samples results in a learning curve. Studying such curves on one or more data sets is a way to get to a better understanding of the generalization properties of this learner. The behavior of learning curves is, however, not very well understood and can display (for most researchers) quite unexpected behavior. Our work introduces the formal notion of \emph{risk monotonicity}, which asks the risk to not deteriorate with increasing training set sizes in expectation over the training samples. We then present the surprising result that various standard learners, specifically those that minimize the empirical risk, can act \emph{non}monotonically irrespective of the training sample size. We provide a theoretical underpinning for specific instantiations from classification, regression, and density estimation. Altogether, the proposed monotonicity notion opens up a whole new direction of research.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1907.05476")
get_code_for_paper("1907.05476")
have("1907.05476")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1907.05476.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1907.05476)
Connect an agent — have() is free.