Publication

Online Resource Inference in Network Utility Maximization Problems

Related publications (29)

Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances

Wulfram Gerstner, Clément Hongler, Johanni Michael Brea, Francesco Spadaro, Berfin Simsek, Arthur Jacot

We study how permutation symmetries in overparameterized multi-layer neural networks generate `symmetry-induced' critical points. Assuming a network with

L

layers of minimal widths

r_1^*, \ldots, r_{L-1}^*

reaches a zero-loss minimum at $ r_1^*! \c ...

2021

Social Learning Under Inferential Attacks

Ali H. Sayed, Virginia Bordignon, Stefan Vlaski, Konstantinos Ntemos

A common assumption in the social learning literature is that agents exchange information in an unselfish manner. In this work, we consider the scenario where a subset of agents aims at driving the network beliefs to the wrong hypothesis. The adversaries a ...

IEEE2021

Linking trajectory data collected with a swarm of drones to the underlying urban network for macroscopic traffic parameter estimation

Nikolaos Geroliminis, Emmanouil Barmpounakis

Recently, an open-data initiative was announced with one of the most complete datasets to study urban congestion. The pNEUMA dataset consists of more than half a million trajectories in heterogeneous traffic. In order to utilize the dataset for macroscopic ...

2020

Annealing and Replica-Symmetry in Deep Boltzmann Machines

Emanuele Mingione, Diego Alberici

In this paper we study the properties of the quenched pressure of a multi-layer spin-glass model (a deep Boltzmann Machine in artificial intelligence jargon) whose pairwise interactions are allowed between spins lying in adjacent layers and not inside the ...

SPRINGER2020

WatchNet plus plus : efficient and accurate depth-based network for detecting people attacks and intrusion

Jean-Marc Odobez, Olivier Canévet, Michael Villamizar

We present an efficient and accurate people detection approach based on deep learning to detect people attacks and intrusion in video surveillance scenarios Unlike other approaches using background segmentation and pre-processing techniques, which are not ...

2020

Estimating network travel time reliability with network partitioning

Nikolaos Geroliminis, Mohammadreza Saeedmanesh

Network travel time reliability can be represented by a relationship between network space-mean travel time and the standard deviation of network travel time. The primary objective of this paper is to improve estimation of the network travel time reliabili ...

PERGAMON-ELSEVIER SCIENCE LTD2020

Containergy-A Container-Based Energy and Performance Profiling Tool for Next Generation Workloads

David Atienza Alonso, Marina Zapater Sancho, Arman Iranfar, Wellington Silva De Souza

Run-time profiling of software applications is key to energy efficiency. Even the most optimized hardware combined to an optimally designed software may become inefficient if operated poorly. Moreover, the diversification of modern computing platforms and ...

2020

Lupulus: A Flexible Hardware Accelerator For Neural Networks

Andreas Peter Burg, Alexios Konstantinos Balatsoukas Stimming, Robert Giterman, Andreas Toftegaard Kristensen

Neural networks have become indispensable for a wide range of applications, but they suffer from high computational- and memory-requirements, requiring optimizations from the algorithmic description of the network to the hardware implementation. Moreover, ...

IEEE2020

Vision based pixel-level bridge structural damage detection using a link ASPP network

Wenlong Deng

Structural Health Monitoring (SHM) has greatly benefited from computer vision. Recently, deep learning approaches are widely used to accurately estimate the state of deterioration of infrastructure. In this work, we focus on the problem of bridge surface s ...

2020

Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances

Wulfram Gerstner, Clément Hongler, Johanni Michael Brea, Francesco Spadaro, Berfin Simsek, Arthur Jacot

We study how permutation symmetries in overparameterized multi-layer neural networks generate `symmetry-induced' critical points. Assuming a network with

L

layers of minimal widths

r_1^*, \ldots, r_{L-1}^*

reaches a zero-loss minimum at $ r_1^*! \c ...

2021