A
A. Cristiano I. Malossi
Researcher at IBM
Publications - 32
Citations - 798
A. Cristiano I. Malossi is an academic researcher from IBM. The author has contributed to research in topics: Network topology & Artificial neural network. The author has an hindex of 11, co-authored 31 publications receiving 619 citations. Previous affiliations of A. Cristiano I. Malossi include École Polytechnique Fédérale de Lausanne & Polytechnic University of Milan.
Papers
More filters
Posted Content
BAGAN: Data Augmentation with Balancing GAN
TL;DR: This work proposes balancing GAN (BAGAN) as an augmentation tool to restore balance in imbalanced datasets and compares the proposed methodology with state-of-the-art GANs and demonstrates that BAGAN generates images of superior quality when trained with an imbalanced dataset.
Proceedings ArticleDOI
An extreme-scale implicit solver for complex PDEs: highly heterogeneous flow in earth's mantle
Johann Rudi,A. Cristiano I. Malossi,Tobin Isaac,Georg Stadler,Michael Gurnis,Peter Staar,Yves Ineichen,Costas Bekas,Alessandro Curioni,Omar Ghattas +9 more
TL;DR: This work demonstrates that---contrary to conventional wisdom---algorithmically optimal implicit solvers can be designed that scale out to 1.5 million cores for severely nonlinear, ill-conditioned, heterogeneous, and anisotropic PDEs.
Proceedings ArticleDOI
The transprecision computing paradigm: Concept, design, and applications
A. Cristiano I. Malossi,Michael Schaffner,Anca Molnos,Luca Gammaitoni,Giuseppe Tagliavini,Andrew Emerson,Andrés E. Tomás,Dimitrios S. Nikolopoulos,Eric Flamand,Norbert Wehn +9 more
TL;DR: The driving motivations, roadmap, and expected impact of the European project OPRECOMP are presented, which aims at demolishing the ultra-conservative “precise” computing abstraction, replacing it with a more flexible and efficient one, namely transprecision computing.
Journal ArticleDOI
A two-level time step technique for the partitioned solution of one-dimensional arterial networks
TL;DR: Since the modeling of blood flow in compliant vessels is tackled using explicit finite element methods, the coupling problem is formulated using a two-level time stepping technique, and two approaches are considered to solve the associated nonlinear interface problem.
Journal ArticleDOI
Algorithms for the partitioned solution of weakly coupled fluid models for cardiovascular flows
TL;DR: In this article, a robust iterative strategy to partition the solution of the Navier-Stokes equations in a 3D domain, into non overlapping 3D subdomains, which communicate through the exchange of averaged/integrated quantities across the interfaces.