activity
20122024
most citedOutput Range Analysis for Deep Neural Networks

75 citations · 261 across the 31 of their papers we have counts for

collaborators
Showing 2021Show all

6 papers · 1 filter

math.OC2021★ 4 cited

An Abstract Model for Branch and Cut

Aleksandr M. Kazachkov, Pierre Le Bodic, Sriram Sankaranarayanan

Branch and cut is the dominant paradigm for solving a wide range of mathematical programming problems -- linear or nonlinear -- combining efficient search (via branch and bound) an…

math.OC2021

The Cut-and-Play Algorithm: Computing Nash Equilibria via Outer Approximations

Margarida Carvalho, Gabriele Dragotto, Andrea Lodi +1

We introduce Cut-and-Play, a practically-efficient algorithm for computing Nash equilibria in simultaneous non-cooperative games where players decide via nonconvex and possibly unb…

cs.LG2021★ 7 cited

Local Repair of Neural Networks Using Optimization

Keyvan Majd, Siyu Zhou, Heni Ben Amor +2

In this paper, we propose a framework to repair a pre-trained feed-forward neural network (NN) to satisfy a set of properties. We formulate the properties as a set of predicates th…

cs.LG2021

Static analysis of ReLU neural networks with tropical polyhedra

Eric Goubault, Sébastien Palumby, Sylvie Putot +2

This paper studies the problem of range analysis for feedforward neural networks, which is a basic primitive for applications such as robustness of neural networks, compliance to s…

cs.RO2021

Predictive Runtime Monitoring for Mobile Robots using Logic-Based Bayesian Intent Inference

Hansol Yoon, Sriram Sankaranarayanan

We propose a predictive runtime monitoring framework that forecasts the distribution of future positions of mobile robots in order to detect and avoid impending property violations…

math.OC2021★ 21 cited

Fairness over time in dynamic resource allocation with an application in Healthcare

Andrea Lodi, Philippe Olivier, Gilles Pesant +1

Decision making problems are typically concerned with maximizing efficiency. In contrast, we address problems where there are multiple stakeholders and a centralized decision maker…