37 citations · 45 across the 5 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2020★ 7 cited
Regret minimization in stochastic non-convex learning via a proximal-gradient approach
Nadav Hallak, Panayotis Mertikopoulos, Volkan Cevher
Motivated by applications in machine learning and operations research, we study regret minimization with stochastic first-order oracle feedback in online constrained, and possibly…
cs.LG2020★ 1 cited
Efficient Proximal Mapping of the 1-path-norm of Shallow Networks
Fabian Latorre, Paul Rolland, Nadav Hallak +1
We demonstrate two new important properties of the 1-path-norm of shallow neural networks. First, despite its non-smoothness and non-convexity it allows a closed form proximal oper…