Publications related to Epidemic Learning: Boosting Decentralized Learning with Randomized Communication

On the performance of random reshuffling in stochastic learning

Ali H. Sayed, Stefan Vlaski, Bicheng Ying, Kun Yuan

In empirical risk optimization, it has been observed that gradient descent implementations that rely on random reshuffling of the data achieve better performance than implementations that rely on sampling the data randomly and independently of each other. ...

2017

MATHICSE Technical Report : Multilevel weighted least squares polynomial approximation

Fabio Nobile

Weighted least squares polynomial approximation uses random samples to determine projections of functions onto spaces of polynomials. It has been shown that, using an optimal distribution of sample locations, the number of samples required to achieve quasi ...

MATHICSE2017

Multilevel weighted least squares polynomial approximation

Fabio Nobile

Weighted least squares polynomial approximation uses random samples to determine projections of functions onto spaces of polynomials. It has been shown that, using an optimal distribution of sample locations, the number of samples required to achieve quasi ...

2017

Compressive Spectral Clustering

Pierre Vandergheynst, Rémi Gribonval, Gilles Puy, Nicolas Tremblay

Spectral clustering has become a popular technique due to its high performance in many contexts. It comprises three main steps: create a similarity graph between N objects to cluster, compute the first k eigenvectors of its Laplacian matrix to define a fea ...

2016

Attributing Aliasing Artifacts in Dirty Intensity Fields to their Parent Source

Matthieu Martin Jean-André Simeoni

Estimating intensity fields of stochastic phenomenons is of crucial interest in many scientific applications. Typical experimental setups involve an acquisition system, that subsequently filters and samples the probed intensity field. This equivalently def ...

2016

Inference for binomial probability based on dependent Bernoulli random variables with applications to meta-analysis and group level studies

Stephan Morgenthaler

We study bias arising as a result of nonlinear transformations of random variables in random or mixed effects models and its effect on inference in group-level studies or in meta-analysis. The findings are illustrated on the example of overdispersed binomi ...

Wiley-Blackwell2016

Random sampling of bandlimited signals on graphs

Pierre Vandergheynst, Rémi Gribonval, Gilles Puy, Nicolas Tremblay

We study the problem of sampling

k

-bandlimited signals on graphs. We propose two sampling strategies that consist in selecting a small subset of nodes at random. The first strategy is non-adaptive, \ie, independent of the graph structure, and its perform ...

2015

Too much success for recent groundbreaking epigenetic experiments

Gregory Francis

An article reporting statistical evidence for epigenetic transfer of learned behavior has important implications, if true. With random sampling, real effects do not always result in rejection of the null hypothesis, but the reported experiments were unifor ...

Genetics Society of America2014

Learning Ridge Functions With Randomized Sampling In High Dimensions

Volkan Cevher, Hemant Tyagi

We study the problem of learning ridge functions of the form f(x) = g(aT x), x ∈ ℝd, from random samples. Assuming g to be a twice continuously differentiable function, we leverage techniques from low rank matrix recovery literature to derive a uniform app ...

IEEE2012

Network Design via Core Detouring for Problems Without a Core

Thomas Rothvoss

Some of the currently best-known approximation algorithms for network design are based on random sampling. One of the key steps of such algorithms is connecting a set of source nodes to a random subset of them. In a recent work [Eisenbrand,Grandoni,Rothvo\ ...

Springer2010

Epidemic Learning: Boosting Decentralized Learning with Randomized Communication

Graph Chatbot

Chat with Graph Search

On the performance of random reshuffling in stochastic learning

MATHICSE Technical Report : Multilevel weighted least squares polynomial approximation

Multilevel weighted least squares polynomial approximation

Compressive Spectral Clustering

Attributing Aliasing Artifacts in Dirty Intensity Fields to their Parent Source

Inference for binomial probability based on dependent Bernoulli random variables with applications to meta-analysis and group level studies

Random sampling of bandlimited signals on graphs

Too much success for recent groundbreaking epigenetic experiments

Learning Ridge Functions With Randomized Sampling In High Dimensions

Network Design via Core Detouring for Problems Without a Core

Multilevel weighted least squares polynomial approximation

On the performance of random reshuffling in stochastic learning

MATHICSE Technical Report : Multilevel weighted least squares polynomial approximation

Too much success for recent groundbreaking epigenetic experiments

Attributing Aliasing Artifacts in Dirty Intensity Fields to their Parent Source

Compressive Spectral Clustering

Inference for binomial probability based on dependent Bernoulli random variables with applications to meta-analysis and group level studies

Random sampling of bandlimited signals on graphs

Learning Ridge Functions With Randomized Sampling In High Dimensions

Network Design via Core Detouring for Problems Without a Core