Zoltán Szabó [on Bitbucket, GitHub, mloss, Matlab Central]
 Adaptive lineartime nonparametric hypothesis tests:

Twosample tests:

Adaptivity: features & kernel parameters are chosen to optimize power. The power of the tests matches quadratictime tests. The returned features indicate why the two distributions differ.

Applications: NLP (distinguishing articles from two categories), computer vision (differentiating positive and negative emotions).

Independence tests:

Applications: song  year of release, video  caption dependency testing.

Goodnessoffit tests:

Application: analysis of crime data.
 Information Theoretical Estimators (ITE) Toolbox:
 Several estimators for entropy, mutual information, divergence, association measure, cross quantity, distribution kernels; in Python, Matlab.

KMC (Kernel Hamiltonian Monte Carlo):
 A gradientfree adaptive MCMC algorithm based on Hamiltonian Monte Carlo (HMC). On target densities where classical HMC is not an option due to intractable gradients, KMC adaptively learns the target's gradient structure from the sample path, by fitting an exponential family model in a Reproducing Kernel Hilbert Space.

LLLVM (Locally Linear Latent Variable Model):
 A probabilistic model for nonlinear manifold discovery that describes a joint distribution over observations, their manifold coordinates and locally linear maps conditioned on a set of neighbourhood relationships; 'Bayesian LLE'.

KernelEP (Kernel based justintime Expectation Propagation):
 A fast, online algorithm for nonparametric learning of EP message updates.

OSDL [Online GroupStructured Dictionary Learning (rar/zip/tar)]:
 Structuredsparse dictionary learning method which (i) is online, (ii) allows overlapping group structures with (iii) nonconvex groupstructure inducing regularization, and (iv) handles incomplete observations.