29 citations · 33 across the 3 of their papers we have counts for
4 papers
Asymptotically optimal strategies for online prediction with history-dependent experts
Jeff Calder, Nadejda Drenska
We establish sharp asymptotically optimal strategies for the problem of online prediction with history dependent experts. The prediction problem is played (in part) over a discrete…
Rates of Convergence for Laplacian Semi-Supervised Learning with Low Labeling Rates
Jeff Calder, Dejan Slepčev, Matthew Thorpe
We study graph-based Laplacian semi-supervised learning at low labeling rates. Laplacian learning uses harmonic extension on a graph to propagate labels. At very low label rates, L…
Poisson Learning: Graph Based Semi-Supervised Learning At Very Low Label Rates
Jeff Calder, Brendan Cook, Matthew Thorpe +1
We propose a new framework, called Poisson learning, for graph based semi-supervised learning at very low label rates. Poisson learning is motivated by the need to address the dege…
Improved spectral convergence rates for graph Laplacians on epsilon-graphs and k-NN graphs
Jeff Calder, Nicolas Garcia Trillos
In this paper we improve the spectral convergence rates for graph-based approximations of Laplace-Beltrami operators constructed from random data. We utilize regularity of the cont…