80 citations
- Stanford UniversityUS2 papers
- The University of Texas at AustinUS2 papers
- University of VirginiaUS2 papers
- EURECOMFR1 paper
- Finland UniversityFI1 paper
- Hongik UniversityKR1 paper
- Hunan Institute of Science and TechnologyCN1 paper
- IBM Research - Thomas J. Watson Research CenterUS1 paper
- IBM (United States)US1 paper
- Institut des Sciences de l'Information et de leurs InteractionsFR1 paper
- Institute for Infocomm ResearchSG1 paper
- Laboratoire Informatique d'AvignonFR1 paper
5 papers
Keep It Simple: Fault Tolerance Evaluation of Federated Learning with Unreliable Clients
Victoria Huang, Shaleeza Sohail, Michael Mayo +4
Federated learning (FL), as an emerging artificial intelligence (AI) approach, enables decentralized model training across multiple devices without exposing their local training da…
On the Benefit of Nonlinear Control for Robust Logarithmic Growth: Coin Flipping Games as a Demonstration Case
Anton V. Proskurnikov, B. Ross Barmish
The takeoff point for this paper is the voluminous body of literature addressing recursive betting games with expected logarithmic growth of wealth being the performance criterion.…
I4U Submission to NIST SRE 2018: Leveraging from a Decade of Shared Experiences
Kong Aik Lee, Ville Hautamaki, Tomi Kinnunen +43
The I4U consortium was established to facilitate a joint entry to NIST speaker recognition evaluations (SRE). The latest edition of such joint submission was in SRE 2018, in which…
Tolerating Soft Errors in Processor Cores Using CLEAR (Cross-Layer Exploration for Architecting Resilience)
Eric Cheng, Shahrzad Mirkhani, Lukasz G. Szafaryn +8
We present CLEAR (Cross-Layer Exploration for Architecting Resilience), a first of its kind framework which overcomes a major challenge in the design of digital systems that are re…
CLEAR: Cross-Layer Exploration for Architecting Resilience - Combining Hardware and Software Techniques to Tolerate Soft Errors in Processor Cores
Eric Cheng, Shahrzad Mirkhani, Lukasz G. Szafaryn +8
We present a first of its kind framework which overcomes a major challenge in the design of digital systems that are resilient to reliability failures: achieve desired resilience t…