Publication

MOSES: A Streaming Algorithm for Linear Dimensionality Reduction

Related publications (29)

Autoencoders reloaded

In Bourlard and Kamp (Biol Cybern 59(4):291-294, 1998), it was theoretically proven that autoencoders (AE) with single hidden layer (previously called "auto-associative multilayer perceptrons") were, in the best case, implementing singular value decomposit ...

SPRINGER2022

Genuinely distributed Byzantine machine learning

Rachid Guerraoui, El Mahdi El Mhamdi, Le Nguyen Hoang, Sébastien Louis Alexandre Rouault, Arsany Hany Abdelmessih Guirguis

Machine learning (ML) solutions are nowadays distributed, according to the so-called server/worker architecture. One server holds the model parameters while several workers train the model. Clearly, such architecture is prone to various types of component ...

2022

High-dimensional optimization under nonconvex excluded volume constraints

Antonio Sclocchi

We consider high-dimensional random optimization problems where the dynamical variables are subjected to nonconvex excluded volume constraints. We focus on the case in which the cost function is a simple quadratic cost and the excluded volume constraints a ...

AMER PHYSICAL SOC2022

Subspace clustering in high-dimensions: Phase transitions & Statistical-to-Computational gap

Florent Gérard Krzakala, Lenka Zdeborová, Bruno Loureiro, Luca Pesce, Bruno Loureiro

A simple model to study subspace clustering is the high-dimensional k -Gaussian mixture model where the cluster means are sparse vectors. Here we provide an exact asymptotic characterization of the statistically optimal reconstruction error in this model i ...

2022

Dalton: Learned Partitioning for Distributed Data Streams

Anastasia Ailamaki, Ioannis Mytilinis, Eleni Zapridou

To sustain the input rate of high-throughput streams, modern stream processing systems rely on parallel execution. However, skewed data yield imbalanced load assignments and create stragglers that hinder scalability. Deciding on a static partitioning for a ...

2022

Non-intrusive double-greedy parametric model reduction by interpolation of frequency-domain rational surrogates

Fabio Nobile, Davide Pradovera

We propose a model order reduction approach for non-intrusive surrogate modeling of parametric dynamical systems. The reduced model over the whole parameter space is built by combining surrogates in frequency only, built at few selected values of the param ...

2021

A Real-time Synchrophasor Data Compression Method Using Singular Value Decomposition

Mario Paolone

The proliferation of phasor measurement units (PMUs) presents new challenges in archiving and processing large amounts of synchrophasor data which necessitates advanced data compression methods. This paper proposes a singular value decomposition (SVD)-base ...

2021

Landscape and training regimes in deep learning

Mario Geiger, Matthieu Wyart, Leonardo Petrini

Deep learning algorithms are responsible for a technological revolution in a variety oftasks including image recognition or Go playing. Yet, why they work is not understood.Ultimately, they manage to classify data lying in high dimension – a feat generical ...

2021

Measuring and modeling the motor system with machine learning

Mackenzie Mathis, Alexander Mathis, Alessandro Marin Vargas

The utility of machine learning in understanding the motor system is promising a revolution in how to collect, measure, and analyze data. The field of movement science already elegantly incorporates theory and engineering principles to guide experimental w ...

2021