Search results for "Linear Model"

Implicit differentiation for fast hyperparameter selection in non-smooth convex learning

2022

International audience; Finding the optimal hyperparameters of a model can be cast as a bilevel optimization problem, typically solved using zero-order techniques. In this work we study first-order methods when the inner optimization problem is convex but non-smooth. We show that the forward-mode differentiation of proximal gradient descent and proximal coordinate descent yield sequences of Jacobians converging toward the exact Jacobian. Using implicit differentiation, we show it is possible to leverage the non-smoothness of the inner problem to speed up the computation. Finally, we provide a bound on the error made on the hypergradient when the inner optimization problem is solved approxim…

Uneven economic burden of non-communicable diseases among Indian households: A comparative analysis

2021

Background Non-communicable diseases (NCDs) are the leading global cause of death and disproportionately concentrate among those living in low-income and middle-income countries. However, its economic impact on households remains less well known in the Indian context. This study aims to assess the economic impact of NCDs in terms of out-of-pocket expenditure (OOPE) and its catastrophic impact on NCDs affected households in India. Materials and methods Data were collected from the 75th round of the National Sample Survey Office, Government of India, conducted in the year 2017–18. This is the latest round of data available on health, which constitutes a sample of 113,823 households. The coll…

Aggregation ofArgulus coregoni(Crustacea: Branchiura) on rainbow trout (Oncorhynchus mykiss): a consequence of host susceptibility or exposure?

2005

By sampling individual rainbow trout,Oncorhynchus mykiss, at a fish farm we showed thatArgulus coregoniwere aggregated within their host population. The relative significance of susceptibility and exposure generating the observed pattern was tested using experimental infections. We examined, whether rainbow trout developed protective resistance mechanisms against the louse following a challenge infection and if there was variation between individual trout in their susceptibility toA. coregonimetanauplii. Fish were exposed to 20A. coregonifor 5, 25, 50, 85 or 120 min and the numbers attaching recorded. Three weeks later, developing argulids were removed and the experiment repeated with a sta…

Simultaneous determination of four 5-hydroxy polymethoxyflavones by reversed-phase high performance liquid chromatography with electrochemical detect…

2009

Accumulating evidence has suggested the potential health-promoting effects of 5-hydroxy polymethoxyflavones (5-OH-PMFs) naturally existing in citrus genus. However, research efforts are hampered by the lack of reliable and sensitive methods for their determination in plant materials and biological samples. Using reversed-phase high performance liquid chromatography (HPLC) equipped with electrochemical (EC) detection, we have developed a fast and highly sensitive method for quantification of four 5-OH-PMFs, namely 5-hydroxy-6,7,8,3',4'-pentamethoxyflavone, 5-hydroxy-3,6,7,8,3',4'-hexamethoxyflavone, 5-hydroxy-6,7,4'-trimethoxyflavone, and 5-hydroxy-6,7,8,4'-tetramethoxyflavone. The method wa…

Numerical investigation of optical heartbeats with external driving forces

2010

The role of harmonic and random external forces in a phenomenological nonlinear model of optical heartbeats is investigated. External forces trigger damped oscillations at the natural frequency of the system and higher harmonics. The numerical results are compared with experimental ones.

Capillary electrophoresis–inductively coupled plasma-mass spectrometry hyphenation for the determination at the nanogram scale of metal affinities an…

2012

Abstract A screening strategy based on hyphenated capillary electrophoresis and inductively coupled plasma mass spectrometry (CE–ICP-MS) was developed to classify phosphorylated ligands according to their europium(III) binding affinity in a hydro-organic medium (sodium formate, pH 3.7, H2O/MeOH 90:10, v/v). Taking advantage of the high sensibility of ICP-MS for detecting phosphorus, this method enabled to assess the affinity of a variety of phosphorylated compounds, including phosphine oxides, thiophosphines, phosphonates, and phosphinates, in less than 1 h and using less than 5 ng of substance. By varying the total europium concentration, complexation constants could be determined accordin…

Predictors and mediators of differences in soft drinks consumption according to gender and plans of further education among Norwegian secondary-schoo…

2013

AbstractObjectiveTo explore mediators of gender and educational differences in sugar-sweetened soft drinks consumption (SDC) and whether gender and level of future education moderate the associations of accessibility, modelling, attitudes and preferences with SDC.DesignA cross-sectional school-based survey within the Fruits and Vegetables Makes the Marks (FVMM) project from 2005.SettingThe questionnaires were completed by the pupils in the classroom guided by a trained project worker during one class session. The questionnaire included questions on SDC (times/week), the potential mediators and moderators. Multilevel linear regression models were used to calculate the mediating and moderatin…

2014

Introduction: Many studies examine gene expression data that has been obtained under the influence of multiple factors, such as genetic background, environmental conditions, or exposure to diseases. The interplay of multiple factors may lead to effect modification and confounding. Higher order linear regression models can account for these effects. We present a new methodology for linear model selection and apply it to microarray data of bone marrow-derived macrophages. This experiment investigates the influence of three variable factors: the genetic background of the mice from which the macrophages were obtained, Yersinia enterocolitica infection (two strains, and a mock control),and treat…

A Widrow–Hoff Learning Rule for a Generalization of the Linear Auto-associator

1996

Abstract A generalization of the linear auto-associator that allows for differential importance and nonindependence of both the stimuli and the units has been described previously by Abdi (1988). This model was shown to implement the general linear model of multivariate statistics. In this note, a proof is given that the Widrow–Hoff learning rule can be similarly generalized and that the weight matrix will converge to a generalized pseudo-inverse when the learning parameter is properly chosen. The value of the learning parameter is shown to be dependent only upon the (generalized) eigenvalues of the weight matrix and not upon the eigenvectors themselves. This proof provides a unified framew…

Inventory record inaccuracy in supply chains: the role of workers' behavior

2014

Purpose – The purpose of this paper is to explore the effect of inventory record inaccuracy due to behavioral aspects of workers on the order and inventory variance amplification. Design/methodology/approach – The authors adopt a continuous-time analytical approach to describe the effect of inbound throughput on the inventory and order variance amplification due to the workload pressure and arousal of workers. The model is numerically solved through simulation and results are analyzed with statistical general linear model. Findings – Inventory management policies that usually dampen variance amplification are not effective when inaccuracy is generated due to workers’ behavioral aspects. Sp…