We prove an extension of McDiarmid's inequality for metric spaces with unbounded
diameter. To this end, we introduce the notion of the\em subgaussian diameter, which is a …

We informally call a stochastic process learnable if it admits a generalization error
approaching zero in probability for any concept class with finite VC-dimension (IID …

Many networks grow by adding successive cohorts–layers of nodes. Often, the nodes in
each layer are selected independently of each other, but from a distribution that can depend …

We introduce the speculate-correct method to derive error bounds for local classifiers. Using
it, we show that k-nearest neighbor classifiers, in spite of their famously fractured decision …

This paper presents a series of PAC error bounds for k-nearest neighbors classifiers, with O
(n− r 2r+ 1) expected range in the difference between error bound and actual error rate, for …

We tackle some fundamental problems in probability theory on corrupted random processes
on the integer line. We analyze when a biased random walk is expected to reach its …

We tackle some fundamental problems in probability theory on corrupted random processes
on the integer line. We analyze when a biased random walk is expected to reach its …

Error bounds based on worst likely assignments use permutation tests to validate classifiers.
Worst likely assignments can produce effective bounds even for data sets with 100 or fewer …