Search Results for author:
Found 5 papers, 1 papers with code
Consistency of semi-supervised learning, stochastic tug-of-war games, and the p-Laplacian
In this paper we give a broad overview of the intersection of partial differential equations (PDEs) and graph-based semi-supervised learning.
Asymptotically optimal strategies for online prediction with history-dependent experts
The prediction problem is played (in part) over a discrete graph called the $d$ dimensional de Bruijn graph, where $d$ is the number of days of history used by the experts.
Online Prediction With History-Dependent Experts: The General Case
We consider the problem with history-dependent experts, in which each expert uses the previous $d$ days of history of the market in making their predictions.
A PDE Approach to the Prediction of a Binary Sequence with Advice from Two History-Dependent Experts
Compared to other recent applications of partial differential equations to prediction, ours has a new element: there are two timescales, since the recent history changes at every step whereas regret accumulates more slowly.
Prediction with Expert Advice: a PDE Perspective
Focusing on an appropriate continuum limit and using methods from optimal control, we characterize the value of the game as the viscosity solution of a certain nonlinear partial differential equation.
