Publications related to When crowding of crowding leads to uncrowding

Neural Tanget Kernel: Convergence and Generalization in Neural Networks

At initialization, artificial neural networks (ANNs) are equivalent to Gaussian processes in the infinite-width limit [12, 9], thus connecting them to kernel methods. We prove that the evolution of an ANN during training can also be described by a kernel: ...

NEURAL INFORMATION PROCESSING SYSTEMS (NIPS)2018

Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression

Nicolas Henri Bernard Flammarion, Aymeric Daphnis Kévin Dieuleveut

We consider the optimization of a quadratic objective function whose gradients are only accessible through a stochastic oracle that returns the gradient at any given point plus a zero-mean finite variance random error. We present the first algorithm that a ...

2017

The effect of overall stimulus configuration on crowding

Michael Herzog, Maya Roinishvili, Mattew Pachai

The standard framework to study vision is typically hierarchical and feedforward, which facilitates deconstructing complex mechanisms into smaller, more tractable problems. However, this framework can fail when elements are presented in context, as they ar ...

2017

ALS Scheme using Extent-based Constraints for the Analysis of Chemical Reaction Systems

Dominique Bonvin, Julien Léo Billeter, Michael Amrhein

Multivariate curve resolution via alternating least squares (ALS) is used to resolve the concentration profiles C and the pure component spectra E of S species from the multivariate absorbance data A, assuming the bilinear model ...

2016

The recursive Hessian sketch for adaptive filtering

Martin Vetterli, Robin Scheibler

We introduce in this paper the recursive Hessian sketch, a new adaptive filtering algorithm based on sketching the same exponentially weighted least squares problem solved by the recursive least squares algorithm. The algorithm maintains a number of sketch ...

Ieee2016

Predicting Individual Scores From Resting State fMRI Using Partial Least Squares Regression

Dimitri Nestor Alice Van De Ville, Stephan Morgenthaler, Thomas William Arthur Bolton, Maria Giulia Preti, Djalel Eddine Meskaldji

An important question in neuroscience is to reveal the relationship between individual performance and brain activity. This could be achieved by applying model regression techniques, in which functional connectivity derived from resting-state functional ma ...

Ieee2016

Towards More Accurate and Efficient Beamformed Radio Interferometry Imaging

Matthieu Martin Jean-André Simeoni

The Square Kilometre Array (SKA) will form the largest radio telescope ever built, generating on the order of one terabyte of data per second. To reduce the data flow sent to the central processor, hierarchical designs have been proposed: the data is prima ...

2015

From averaging to acceleration, there is only a step-size

Nicolas Henri Bernard Flammarion

We consider the optimization of a quadratic objective function whose gradients are only accessible through a stochastic oracle that returns the gradient at any given point plus a zero-mean finite variance random error. We present the first algorithm that a ...

2015

Adaptive polynomial approximation by means of random discrete least squares

Giovanni Migliorati

We address adaptive multivariate polynomial approximation by means of the discrete least-squares method with random evaluations, to approximate in the L2 probability sense a smooth function depending on a random variable distributed according to a given pr ...

Springer2015

A New Identity for the Least-square Solution of Overdetermined Set of Linear Equations

Afsaneh Asaei, Mohammadjavad Taghizadeh, Saeid Haghighatshoar

In this paper, we prove a new identity for the least-square solution of an over-determined set of linear equation

Ax=b

, where

A

is an

m\times n

full-rank matrix,

b

is a column-vector of dimension

m

, and

m

(the number of equations) is larger tha ...

2015

When crowding of crowding leads to uncrowding

Graph Chatbot

Chat with Graph Search

Neural Tanget Kernel: Convergence and Generalization in Neural Networks

Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression

The effect of overall stimulus configuration on crowding

ALS Scheme using Extent-based Constraints for the Analysis of Chemical Reaction Systems

The recursive Hessian sketch for adaptive filtering

Predicting Individual Scores From Resting State fMRI Using Partial Least Squares Regression

Towards More Accurate and Efficient Beamformed Radio Interferometry Imaging

From averaging to acceleration, there is only a step-size

Adaptive polynomial approximation by means of random discrete least squares

A New Identity for the Least-square Solution of Overdetermined Set of Linear Equations

The effect of overall stimulus configuration on crowding

Neural Tanget Kernel: Convergence and Generalization in Neural Networks

Adaptive polynomial approximation by means of random discrete least squares

Towards More Accurate and Efficient Beamformed Radio Interferometry Imaging

From averaging to acceleration, there is only a step-size

A New Identity for the Least-square Solution of Overdetermined Set of Linear Equations

ALS Scheme using Extent-based Constraints for the Analysis of Chemical Reaction Systems

The recursive Hessian sketch for adaptive filtering

Predicting Individual Scores From Resting State fMRI Using Partial Least Squares Regression

Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression