Publications related to Differentiable function

Learning Ridge Functions With Randomized Sampling In High Dimensions

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

GeneNetWeaver: In silico benchmark generation and performance profiling of network inference methods

Dario Floreano, Daniel Marbach, Thomas Schaffter

Motivation: Over the last decade, numerous methods have been developed for inference of regulatory networks from gene expression data. However, accurate and systematic evaluation of these methods is hampered by the difficulty of constructing adequate bench ...

Oxford University Press2011

An optimal first-order solver for the TV-$L_1$ optical flow problem

Pierre Vandergheynst, Gilles Puy, Emmanuel D'Angelo

In this study, we address the problem of computing efficiently a dense optical flow between two images under a total variation (TV) regularization and an

L_1

norm data fidelity constraint using a variational method. We build upon Nesterov's framework for ...

2010

Additive Envelopes of Continuous Functions

Thomas Alois Weber

We present an iterative method for constructing additive envelopes of continuous functions on a compact set, with contact at a specified point. For elements of a class of submodular functions we provide closed-form expressions for such additive envelopes. ...

2010

GeneNetWeaver 3.0: realistic benchmark generation and performance profiling of network inference methods

Dario Floreano, Daniel Marbach, Thomas Schaffter

Numerous methods have been developed for inference of gene regulatory networks from expression data, however, their strengths and weaknesses remain poorly understood. Accurate and systematic evaluation of these methods is hampered by the difficulty of cons ...

2010

Dynamic network loading: a differentiable model that derives link state distributions

Michel Bierlaire, Gunnar Flötteröd, Carolina Osorio Pizano

We present a dynamic network loading model that yields queue length distributions, accounts for spillbacks, and maintains a differentiable mapping from the dynamic demand on the dynamic queue lengths. The approach builds upon an existing stationary queuein ...

2010

Obfuscation for Cryptographic Purposes

Martijn Stam

Loosely speaking, an obfuscation O of a function f should satisfy two requirements: firstly, using O, it should be possible to evaluate f; secondly, O should not reveal anything about f that cannot be learnt from oracle access to f alone. Several definitio ...

Springer Verlag2010

Delayed Multiattribute Product Differentiation

Thomas Alois Weber

We develop a two-stage model for versioning products with respect to both vertical and horizontal attributes. At first, a firm positions its top-quality “flagship” product in a market with an imperfectly known distribution of tastes and reservation prices. ...

2008

Approximation des moments par l'utilisation de la théorie des fonctions analytiques

Khalid Ohmiti

In this thesis, I define and explain the notion of punctual analytical uniform development (DUAP) versus moments or cumulants approximation of punctual uniforms analyticals 's class statistics. Hence, I derive "truncated" DUAP's version for numerical compu ...

EPFL2007

A New Learning Method for Piecewise Linear Regression

Giancarlo Ferrari Trecate

A new connectionist model for the solution of piecewise lin- ear regression problems is introduced; it is able to reconstruct both con- tinuous and non continuous real valued mappings starting from a finite set of possibly noisy samples. The approximating ...

Springer-Verlag, Heidelberg2002

Differentiable function

Graph Chatbot

Chat with Graph Search

Learning Ridge Functions With Randomized Sampling In High Dimensions

GeneNetWeaver: In silico benchmark generation and performance profiling of network inference methods

An optimal first-order solver for the TV-$L_1$ optical flow problem

Additive Envelopes of Continuous Functions

GeneNetWeaver 3.0: realistic benchmark generation and performance profiling of network inference methods

Dynamic network loading: a differentiable model that derives link state distributions

Obfuscation for Cryptographic Purposes

Delayed Multiattribute Product Differentiation

Approximation des moments par l'utilisation de la théorie des fonctions analytiques

A New Learning Method for Piecewise Linear Regression

Delayed Multiattribute Product Differentiation

Approximation des moments par l'utilisation de la théorie des fonctions analytiques

An optimal first-order solver for the TV-$L_1$ optical flow problem

Additive Envelopes of Continuous Functions

Learning Ridge Functions With Randomized Sampling In High Dimensions

Dynamic network loading: a differentiable model that derives link state distributions

GeneNetWeaver: In silico benchmark generation and performance profiling of network inference methods

Obfuscation for Cryptographic Purposes

GeneNetWeaver 3.0: realistic benchmark generation and performance profiling of network inference methods

A New Learning Method for Piecewise Linear Regression