In this thesis, we explore techniques for addressing the communication bottleneck in data-parallel distributed training of deep learning models. We investigate algorithms that either reduce the size of the messages that are exchanged between workers, or th ...
Metal-based Laser Powder Bed Fusion (LPBF) has made fabricating intricate components easier. Yet, assessing part quality is inefficient, relying on costly Computed Tomography (CT) scans or time-consuming destructive tests. Also, intermittent inspection of ...
In this article, we study the problem of Byzantine fault-tolerance in a federated optimization setting, where there is a group of agents communicating with a centralized coordinator. We allow up to f Byzantine-faulty agents, which may not follow a prescr ...
The problem of Byzantine resilience in distributed machine learning, a.k.a., Byzantine machine learning, consists in designing distributed algorithms that can train an accurate model despite the presence of Byzantine nodes, i.e., nodes with corrupt data or ...
Machine learning models trained with passive sensor data from mobile devices can be used to perform various inferences pertaining to activity recognition, context awareness, and health and well-being. Prior work has improved inference performance through t ...
Machine learning (ML) models for molecules and materials commonly rely on a decomposition of the global target quantity into local, atom-centered contributions. This approach is convenient from a computational perspective, enabling large-scale ML-driven si ...
Parliament dynamics might seem erratic at times. Predicting future voting patterns could support policy design based on the simulation of voting scenarios. The availability of open data on legislative activities and machine learning tools might enable such ...
Non-convex constrained optimization problems have become a powerful framework for modeling a wide range of machine learning problems, with applications in k-means clustering, large- scale semidefinite programs (SDPs), and various other tasks. As the perfor ...
Epilepsy is one of the most prevalent brain disorders that disrupts the lives of millions worldwide. For patients with drug-resistant seizures, there exist implantable devices capable of monitoring neural activity, promptly triggering neurostimulation to r ...
Organocatalysis has evolved significantly over the last decades, becoming a pillar of synthetic chemistry, but traditional theoretical approaches based on quantum mechanical computations to investigate reaction mechanisms and provide rationalizations of ca ...
