4 papers
Pinet: Optimizing hard-constrained neural networks with orthogonal projection layers
Panagiotis D. Grontas, Antonio Terpin, Efe C. Balta +2
We introduce an output layer for neural networks that ensures satisfaction of convex constraints. Our approach, net, leverages operator splitting for rapid and reliable project…
Contractivity and linear convergence in bilinear saddle-point problems: An operator-theoretic approach
Colin Dirren, Mattia Bianchi, Panagiotis D. Grontas +2
We study the convex-concave bilinear saddle-point problem , where both, only one, or none of the functions and are strongly convex, a…
Optimizing Social Network Interventions via Hypergradient-Based Recommender System Design
Marino Kühne, Panagiotis D. Grontas, Giulia De Pasquale +3
Although social networks have expanded the range of ideas and information accessible to users, they are also criticized for amplifying the polarization of user opinions. Given the…
Operator Splitting for Convex Constrained Markov Decision Processes
Panagiotis D. Grontas, Anastasios Tsiamis, John Lygeros
We consider finite Markov decision processes (MDPs) with convex constraints and known dynamics. In principle, this problem is amenable to off-the-shelf convex optimization solvers,…