Langevin dynamics based algorithm e-TH$\epsilon$O POULA for stochastic optimization problems with discontinuous stochastic gradient

Dong-Young Lim, Ariel Neufeld, Sotirios Sabanis +1

We introduce a new Langevin dynamics based algorithm, called e-TH$\epsilon$O POULA, to solve optimization problems with discontinuous stochastic gradients which naturally appear…