Multiple Functional Regression with both Discrete and Continuous Covariates

Kadri, Hachem; Preux, Philippe; Duflos, Emmanuel; Canu, Stéphane

doi:10.1007/978-3-7908-2736-1_29

Cited by 6 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our proposed ComboKR model is an adaptation of an approach that has sometimes been referred to as generalised kernel dependency estimation (KDE) [24] or input output kernel regression (IOKR) [25, 26].…”

Section: Methodsmentioning

confidence: 99%

“…This is especially difficult prediction task, since practically each output – a surface – in any such data set is sampled in part or fully from different sets of concentrations than the others, and therefore the dose-combination response matrices are not directly comparable. To solve the problem, we consider adapting an approach that has sometimes been referred to as generalised kernel dependency estimation (KDE) [24] or input output kernel regression (IOKR) [25, 26].…”

Section: Overview Of Combokrmentioning

confidence: 99%

See 1 more Smart Citation

Predicting drug combination response surfaces

Huusari,

Wang,

Szedmak

et al. 2024

Preprint

View full text Add to dashboard Cite

Prediction of drug combination responses is a research question of growing importance for cancer and other complex diseases. Current machine learning approaches generally consider predicting either drug combination synergy summaries or single combination dose-response values, which fail to appropriately model the continuous nature of the underlying dose-response combination surface and can lead to inconsistencies when a synergy score or a dose-response matrix is reconstructed from separate predictions. We propose a structured prediction method, comboKR, that directly predicts the drug combination response surface for a drug combination. The method is based on a powerful input-output kernel regression technique and functional modeling of the response surface. As an important part of our approach, we develop a novel normalisation between response surfaces that standardizes the heterogeneous experimental designs used to measure the dose-responses, and thus allows training the method with data measured in different laboratories. Our experiments on two predictive scenarios highlight the suitability of the proposed approach especially in the traditionally challenging setting of predicting combination responses for new drugs not available in the training data.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Overview Of Combokrmentioning

confidence: 99%

Predicting drug combination response surfaces

Huusari,

Wang,

Szedmak

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…In this framework of multiple kernel‐learning problem, people find an optimal convex combination

boldK = \sum_{j = 1}^{m} β_{j} K_{j}, β_{j} \geq 0, \sum_{j = 1}^{m} β_{j} = 1,

of m given kernels K 1 , …, K m . Efficient and scalable methods to find such optimal weights were studied intensively in pieces of literature such as and references therein.…”

Section: Learning Theory Basics For Regressionmentioning

confidence: 99%

Chemical machine learning with kernels: The impact of loss functions

Nguyen

Lin

et al. 2019

Int J of Quantum Chemistry

View full text Add to dashboard Cite

Machine learning promises to accelerate materials discovery by allowing computational efficient property predictions from a small number of reference calculations. As a result, the literature has spent a considerable effort in designing representations that capture basic physical properties. Our work focuses on the less‐studied learning formulations in this context in order to exploit inner structures in the prediction errors. In particular, we propose to directly optimize basic loss functions of the prediction error metrics typically used in the literature, such as the mean absolute error or the worst case error. In some instances, a proper choice of the loss function can directly reduce reasonably the prediction performance in the desired metric, albeit at the cost of additional computations during training. To support this claim, we describe the statistical learning theoretic foundations, and provide supporting numerical evidence with the prediction of atomization energies for a database of small organic molecules.

show abstract

“…Predictive models for functional data generally adapts the idea of standard linear models and the functional principal component analysis (FPCA) is commonly used for better estimation of the parameter functions of such models [8], [9]. Functional linear models (FLM) [10], [11] frequently appear in FDA methods and in FLM, the inner product between functional covariate and an coefficient function is used to estimate the effect of functional covariates on response. But in many situations only a few out of many functional covariates are actually useful in predicting the response [12] or multicollinearity of the covariates makes the model inconsistent in model estimation [13].…”

Section: Introductionmentioning

confidence: 99%

Functional Classwise Principal Component Analysis: A Novel Classification Framework

Chatterjee¹,

Mazumder²,

Das³

2021

Preprint

View full text Add to dashboard Cite

In recent times, functional data analysis (FDA) has been successfully applied in the field of high dimensional data classification. In this paper, we present a novel classification framework using functional data and classwise Principal Component Analysis (PCA). Our proposed method can be used in high dimensional time series data which typically suffers from small sample size problem. Our method extracts a piece wise linear functional feature space and is particularly suitable for hard classification problems. The proposed framework converts time series data into functional data and uses classwise functional PCA for feature extraction followed by classification using a Bayesian linear classifier. We demonstrate the efficacy of our proposed method by applying it to both synthetic data sets and real time series data from diverse fields including but not limited to neuroscience, food science, medical sciences and chemometrics.

show abstract

Multiple Functional Regression with both Discrete and Continuous Covariates

Cited by 6 publications

References 18 publications

Predicting drug combination response surfaces

Predicting drug combination response surfaces

Chemical machine learning with kernels: The impact of loss functions

Functional Classwise Principal Component Analysis: A Novel Classification Framework

Contact Info

Product

Resources

About