A new "herding" algorithm is proposed which directly converts observed moments into a sequence of pseudo-samples. The pseudosamples respect the moment constraints and ma...
A parametric version of herding is formulated. The nonlinear mapping between consecutive time slices is learned by a form of self-supervised training. The resulting dynamical syst...
In many dynamic matching applications—especially high-stakes ones—the competitive ratios of prior-free online algorithms are unacceptably poor. The algorithm should take distr...
John P. Dickerson, Ariel D. Procaccia, Tuomas Sand...
We derive continuous-time batch and online versions of the recently introduced efficient O(N2 ) training algorithm of Atiya and Parlos [2000] for fully recurrent networks. A mathem...
We study the weight dynamics of the floating-gate pFET synapse and the effects of the pFET's gate and drain voltages on these dynamics. We show that we can derive a weight upd...