Publications associées à Test de Wald

Machine Learning Security in Industry: A Quantitative Survey

Despite the large body of academic work on machine learning security, little is known about the occurrence of attacks on machine learning systems in the wild. In this paper, we report on a quantitative study with 139 industrial practitioners. We analyze at ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2023

Incremental Learning in Diagonal Linear Networks

Raphaël Jean Berthier

Diagonal linear networks (DLNs) are a toy simplification of artificial neural networks; they consist in a quadratic reparametrization of linear regression inducing a sparse implicit regularization. In this paper, we describe the trajectory of the gradient ...

Microtome Publishing2023

A note on universal inference

Anthony Christopher Davison, Timmy Rong Tian Tse

Universal inference enables the construction of confidence intervals and tests without regularity conditions by splitting the data into two parts and appealing to Markov's inequality. Previous investigations have shown that the cost of this generality is a ...

WILEY2022

Experimental characterisation of textile compaction response: A benchmark exercise

Véronique Michaud, Baris Çaglar, Christophe Lopez

This paper reports the results of an international benchmark exercise on the measurement of fibre bed compaction behaviour. The aim was to identify aspects of the test method critical to obtain reliable results and to arrive at a recommended test procedure ...

2021

NovelT2Mapping for Evaluating Cervical Cancer Features by Providing QuantitativeT2Maps and Synthetic Morphologic Images: A Preliminary Study

Tobias Kober, Tom Hilbert, Yong Zhang, Meng Yang, Jie Liu

Background The application value of T(2)mapping in evaluating cervical cancer (CC) features remains unclear. Purpose To investigate the role of T(2)values in evaluating CC classification, grade, and lymphovascular space invasion (LVSI) in comparison to app ...

WILEY2020

On long time behavior of solutions to nonlinear dispersive equations

Stefano Francesco Burzio

In part I, we address the issue of existence of solutions for Cauchy problems involving nonlinear hyperbolic equations for initial data in Sobolev spaces with scaling subcritical regularity. In particular, we analyse nonlinear estimates for null-forms in t ...

EPFL2020

Learning new physics from a machine

Raffaele Tito D'Agnolo, Andrea Wulzer

We propose using neural networks to detect data departures from a given reference model, with no prior bias on the nature of the new physics responsible for the discrepancy. The virtues of neural networks as unbiased function approximants make them particu ...

American Physical Society2019

The detection of two-component mixture alternatives : Theory and methods

Daria Rukina

In this thesis, we deal with one of the facets of the statistical detection problem. We study a particular type of alternative, the mixture model. We consider testing where the null hypothesis corresponds to the absence of a signal, represented by some kno ...

EPFL2018

MAGIC observations of the February 2014 flare of 1ES 1011+496 and ensuing constraint of the EBL density

Thomas Günther Bretz

Context. During February-March 2014, the MAGIC telescopes observed the high-frequency peaked BL Lac 1ES 1011 + 496 (z = 0.212) in flaring state at very-high energy (VHE, E > 100 GeV). The flux reached a level of more than ten times higher than any previous ...

Edp Sciences S A2016

Comparing connectomes across subjects and populations at different scales

Jean-Philippe Thiran, Stephan Morgenthaler, Alessandra Griffa, Elda Fischi Gomez, Patric Hagmann, Djalel Eddine Meskaldji

Brain connectivity can be represented by a network that enables the comparison of the different patterns of struc- tural and functional connectivity among individuals. In the literature, two levels ofstatistical analysis have been con- sidered in comparing ...

2013