Understanding SVM (and associated kernel machines) through the development of a Matlab toolbox
|
|
- Prosper Andrews
- 5 years ago
- Views:
Transcription
1 Understanding SVM (and associated kernel machines) through the development of a Matlab toolbox Stephane Canu To cite this version: Stephane Canu. Understanding SVM (and associated kernel machines) through the development of a Matlab toolbox. Engineering school. Introduction to Support Vector Machines (SVM), Sao Paulo, 204, pp.33. <cel > HAL Id: cel Submitted on 8 Jun 204 HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.
2 Lecture 8: Multi Class SVM Stéphane Canu Sao Paulo 204 April 0, 204
3 Roadmap Multi Class SVM 3 different strategies for multi class SVM Multi Class SVM by decomposition Multi class SVM Coupling convex hulls
4 3 different strategies for multi class SVM Decomposition approaches one vs all: winner takes all one vs one: max-wins voting pairwise coupling: use probability c SVDD 2 global approach (size c n), formal (different variations) min f H,α 0,ξ IR n 2 with and c f l 2 H + C p l= n c ξ p il i= l=,l y i f yi (x i )+b yi f l (x i )+b l + 2 ξ il ξ il 0 for i =,..., n; l =,..., c; l y i non consistent estimator but practically useful structured outputs 3 A coupling formulation using the convex hulls
5 3 different strategies for multi class SVM Decomposition approaches one vs all: winner takes all one vs one: max-wins voting pairwise coupling: use probability best results c SVDD 2 global approach (size c n), formal (different variations) min f H,α 0,ξ IR n 2 with and c f l 2 H + C p l= n c ξ p il i= l=,l y i f yi (x i )+b yi f l (x i )+b l + 2 ξ il ξ il 0 for i =,..., n; l =,..., c; l y i non consistent estimator but practically useful structured outputs 3 A coupling formulation using the convex hulls
6 Multiclass SVM: complexity issues n training data n = 60, 000 for MNIST c class c = 0 for MNIST problem number of approach discrimination rejection size sub problems vs. all n c n c(c ) vs. c n c SVDD c c - ++ all together n c ++ - coupling CH n + +
7 Roadmap Multi Class SVM 3 different strategies for multi class SVM Multi Class SVM by decomposition Multi class SVM Coupling convex hulls
8 Multi Class SVM by decomposition One-Against-All Methods winner-takes-all strategy One-vs-One: pairwise methods max-wins voting directed acyclic graph (DAG) error-correcting codes post process probabilities Hierarchical binary tree for multi-class SVM mas622j/projects/aisen-project/
9 SVM and probabilities (Platt, 999) The decision function of the SVM is: sign ( f(x)+b ) log IP(Y = x) IP(Y = x) should have (almost) the same sign as f(x)+b log IP(Y = x) IP(Y = x) = a (f(x)+b)+a 2 IP(Y = x) = +exp a(f(x)+b)+a2 max L a,a 2 with L = a et a 2 estimated using maximum likelihood on new data n IP(Y = x i ) y i +( IP(Y = x i )) ( y i) i= and log L = n i= y i log(ip(y = x i ))+( y i )log( IP(Y = x i )) = n i= y i log ( IP(Y= x i ) IP(Y= x i )) + log( IP(Y = xi )) = n i= y ) i( a (f(x i )+b)+a 2 log(+exp a (f(x i )+b)+a 2 ) = n i= y ) i( a z i log(+exp a z i) Newton iterations: a new a old H logl
10 SVM and probabilities (Platt, 999) n max log L = ( y i a ) z i log(+exp a z i ) a IR 2 i= Newton iterations a new a old H logl logl = = n z y i z i expa +exp z a z i n ( yi IP(Y = x i ) ) z i = Z (y p) i= i= H = n i= z i z i IP(Y = x i ) ( IP(Y = x i ) ) = Z WZ Newton iterations a new a old +(Z WZ) Z (y p)
11 SVM and probabilities: practical issues y t = ε + = n + + n ε = n + 2 if y i = if y i = in: X,y, f /out: p 2 t 3 Z 4 loop until convergence p +exp a z 2 W diag ( p( p) ) 3 a new a old +(Z WZ) Z (t p)
12 SVM and probabilities: pairwise coupling From pairwise probabilities IP(c l, c j ) to class probabilities p l = IP(c l x) ( )( ) Q e p e = 0 µ min p ( 0 The global procedure : ) c l IP(c l, c j ) 2 (p l p j ) 2 l= j= (Xa, ya, Xt, yt) split(x, y) 2 (Xl, yl, Xp, yp) split(xa, ya) 3 loop for all pairs (c i, c j ) of classes { IP(cl, c with Q lj = j ) 2 l j i IP(c l, c i ) 2 l = j model i,j train_svm(xl, yl,(c i, c j )) 2 IP(c i, c j ) estimate_proba(xp, yp, model) % Platt estimate 4 p post_process(xt, yt, IP) % Pairwise Coupling Wu, Lin & Weng, 2004, Duan & Keerti, 05
13 SVM and probabilities Some facts SVM is universally consistent (converges towards the Bayes risk) SVM asymptotically implements the bayes rule but theoretically: no consistency towards conditional probabilities (due to the nature of sparsity) to estimate conditional probabilities on an interval (typically[ 2 η, 2 +η]) to sparseness in this interval (all data points have to be support vectors) Bartlett & Tewari, JMLR, 07
14 SVM and probabilities (2/2) An alternative approach g(x) ε (x) IP(Y = x) g(x)+ε + (x) with g(x) = +4 f (x) α 0 non parametric functions ε and ε + have to verify: with a = log 2 and a 2 = 0 g(x)+ε + (x) = exp a( f(x) α0)++a2 g(x) ε (x) = exp a(+f(x)+α0)++a2 Grandvalet et al., 07
15 Roadmap Multi Class SVM 3 different strategies for multi class SVM Multi Class SVM by decomposition Multi class SVM Coupling convex hulls
16 Multi class SVM: the decision function One hyperplane by class f l (x) = w l x+b l l =, c Winner takes all decision function ( D(x) = Argmax w x+b, w2 x+b 2,..., wl x+b l,..., w ) c x+b c l=,c We can revisit the 2 classes case in this setting c (d + ) unknown variables (w l, b l ); l =, c
17 Multi class SVM: the optimization problem The margin in the multidimensional case m = min l y i ( v yi x i a yi v l x i + a l ) = v yi x i + a yi max l y i ( v l x i + a l ) The maximal margin multiclass SVM max m v l,a l with vy i x i + a yi vl x i a l m for i =, n; l =, c; l y i c and 2 v l 2 = l= The multiclass SVM c min w l,b 2 w l 2 l l= with x i (w yi w l )+b yi b l for i =, n; l =, c; l y i
18 Multi class SVM: KKT and dual form: The 3 classes case min w l,b 2 l 3 w l 2 l= with w y i x i + b yi w l x i + b l + for i =, n; l =, 3; l y i min w l,b 2 w w w 3 2 l with w x i + b w2 x i + b 2 + for i such that y i = w x i + b w3 x i + b 3 + for i such that y i = w2 x i + b 2 w x i + b + for i such that y i = 2 w2 x i + b 2 w3 x i + b 3 + for i such that y i = 2 w3 x i + b 3 w x i + b + for i such that y i = 3 w3 x i + b 3 w2 x i + b 2 + for i such that y i = 3 L = 2 ( w 2 + w w 3 2 ) α 2 (X (w w 2 )+b b 2 ) α 3 (X (w w 3 )+b b 3 ) α 2 (X 2(w 2 w )+b 2 b ) α 23 (X 2(w 2 w 3 )+b 2 b 3 ) α 3 (X 3(w 3 w )+b 3 b ) α 32 (X 3(w 3 w 2 )+b 3 b 2 )
19 Multi class SVM: KKT and dual form: The 3 classes case L = 2 w 2 α (XMw+Ab ) with I I 0 w I 0 I w = w 2 IR 3d M = M I = I I 0 w 3 0 I I I 0 I 0 I I a 6d 3d matrix where I the identity matrix and X X X = 0 0 X X X X 3 a 2n 6d matrix with input data X = X X 2 n d X 3
20 Multi class SVM: KKT and dual form: The 3 classes case KKT Stationality conditions = w L = w M X α b L = A α The dual min α IR 2 n 2 α Gα e α with Ab = 0 and 0 α With G = XMM X = X(M I)(M I) X = X(MM I)X = (MM I). XX = (MM I). I K I and M =
21 Multi class SVM and slack variables (2 variants) A slack for all (Vapnik & Blanz, Weston & Watkins 998) c n c min w l,b l,ξ IR cn 2 w l 2 + C ξ il l= i= l=,l y i with wy i x i + b yi wl x i b l ξ il and ξ il 0 for i =, n; l =, c; l y i The dual min α IR 2 n 2 α Gα e α with Ab = 0 and 0 α C Max error, a slack per training data (Cramer and Singer, 200) c n min w l,b l,ξ IR n 2 w l 2 + C ξ i l= i= with (w yi w l ) x i ξ i for i =, n; l =, c; l y i i= and ξ i 0 for i =, n
22 Multi class SVM and Kernels c min f H,α 0,ξ IR cn 2 f l 2 H + C with l= n c ξ il i= l=,l y i f yi (x i )+b yi f l (x i ) b l ξ il n i= and ξ il 0 for i =, n; l =, c; l y i The dual min α IR 2 n 2 α Gα e α with Ab = 0 and 0 α C where G is the multi class kernel matrix
23 Other Multi class SVM Lee, Lin & Wahba, 2004 c λ min f H 2 f l 2 H + n l= c with f l (x) = 0 l= n c (f l (x i )+ c ) + l=,l y i i= x Structured outputs = Cramer and Singer, 200 MSVMpack : A Multi-Class Support Vector Machine Package Fabien Lauer & Yann Guermeur
24 Roadmap Multi Class SVM 3 different strategies for multi class SVM Multi Class SVM by decomposition Multi class SVM Coupling convex hulls
25 One more way to derivate SVM Minimizing the distance between the convex hulls min u v 2 α with u(x) = α i (x i x), v(x) = and {i y i =} {i y i =} α i =, {i y i = } α i =, 0 α i {i y i = } α i (x i x) i =, n
26 The multi class case min α with and c c u l u l 2 l= l = u l (x) = α i,l (x i x), l =, c {i y i =l} α i,l =, 0 α i,l i =, n;l =, c {i y i =l}
27 Bibliography Estimating probabilities Platt, J. (2000). Probabilistic outputs for support vector machines and comparison to regularized likelihood methods. In Advances in large margin classifiers. MIT Press. T. Lin, C.-J. Lin, R.C. Weng, A note on Platt s probabilistic outputs for support vector machines, Mach. Learn. 68 (2007) Multiclass SVM K.-B. Duan & S. Keerthi (2005). "Which Is the Best Multiclass SVM Method? An Empirical Study". T.-F. Wu, C.-J. Lin, R.C. Weng, Probability estimates for multi-class classification by pairwise coupling, JMLR. 5 (2004) K. Crammer & Y. Singer (200). "On the Algorithmic Implementation of Multiclass Kernel-based Vector Machines". JMLR 2: Lee, Y.; Lin, Y.; and Wahba, G. (200). "Multicategory Support Vector Machines". Computing Science and Statistics Stéphane Canu (INSA Rouen - LITIS) April 0, / 25
Dispersion relation results for VCS at JLab
Dispersion relation results for VCS at JLab G. Laveissiere To cite this version: G. Laveissiere. Dispersion relation results for VCS at JLab. Compton Scattering from Low to High Momentum Transfer, Mar
More informationEaster bracelets for years
Easter bracelets for 5700000 years Denis Roegel To cite this version: Denis Roegel. Easter bracelets for 5700000 years. [Research Report] 2014. HAL Id: hal-01009457 https://hal.inria.fr/hal-01009457
More informationMethylation-associated PHOX2B gene silencing is a rare event in human neuroblastoma.
Methylation-associated PHOX2B gene silencing is a rare event in human neuroblastoma. Loïc De Pontual, Delphine Trochet, Franck Bourdeaut, Sophie Thomas, Heather Etchevers, Agnes Chompret, Véronique Minard,
More informationA new simple recursive algorithm for finding prime numbers using Rosser s theorem
A new simple recursive algorithm for finding prime numbers using Rosser s theorem Rédoane Daoudi To cite this version: Rédoane Daoudi. A new simple recursive algorithm for finding prime numbers using Rosser
More informationClassification of high dimensional data: High Dimensional Discriminant Analysis
Classification of high dimensional data: High Dimensional Discriminant Analysis Charles Bouveyron, Stephane Girard, Cordelia Schmid To cite this version: Charles Bouveyron, Stephane Girard, Cordelia Schmid.
More informationSoundness of the System of Semantic Trees for Classical Logic based on Fitting and Smullyan
Soundness of the System of Semantic Trees for Classical Logic based on Fitting and Smullyan Shahid Rahman To cite this version: Shahid Rahman. Soundness of the System of Semantic Trees for Classical Logic
More informationSome explanations about the IWLS algorithm to fit generalized linear models
Some explanations about the IWLS algorithm to fit generalized linear models Christophe Dutang To cite this version: Christophe Dutang. Some explanations about the IWLS algorithm to fit generalized linear
More informationCompleteness of the Tree System for Propositional Classical Logic
Completeness of the Tree System for Propositional Classical Logic Shahid Rahman To cite this version: Shahid Rahman. Completeness of the Tree System for Propositional Classical Logic. Licence. France.
More informationOn size, radius and minimum degree
On size, radius and minimum degree Simon Mukwembi To cite this version: Simon Mukwembi. On size, radius and minimum degree. Discrete Mathematics and Theoretical Computer Science, DMTCS, 2014, Vol. 16 no.
More informationL institution sportive : rêve et illusion
L institution sportive : rêve et illusion Hafsi Bedhioufi, Sida Ayachi, Imen Ben Amar To cite this version: Hafsi Bedhioufi, Sida Ayachi, Imen Ben Amar. L institution sportive : rêve et illusion. Revue
More informationPasserelle entre les arts : la sculpture sonore
Passerelle entre les arts : la sculpture sonore Anaïs Rolez To cite this version: Anaïs Rolez. Passerelle entre les arts : la sculpture sonore. Article destiné à l origine à la Revue de l Institut National
More informationA new approach of the concept of prime number
A new approach of the concept of prime number Jamel Ghannouchi To cite this version: Jamel Ghannouchi. A new approach of the concept of prime number. 4 pages. 24. HAL Id: hal-3943 https://hal.archives-ouvertes.fr/hal-3943
More informationCase report on the article Water nanoelectrolysis: A simple model, Journal of Applied Physics (2017) 122,
Case report on the article Water nanoelectrolysis: A simple model, Journal of Applied Physics (2017) 122, 244902 Juan Olives, Zoubida Hammadi, Roger Morin, Laurent Lapena To cite this version: Juan Olives,
More informationSmart Bolometer: Toward Monolithic Bolometer with Smart Functions
Smart Bolometer: Toward Monolithic Bolometer with Smart Functions Matthieu Denoual, Gilles Allègre, Patrick Attia, Olivier De Sagazan To cite this version: Matthieu Denoual, Gilles Allègre, Patrick Attia,
More informationHook lengths and shifted parts of partitions
Hook lengths and shifted parts of partitions Guo-Niu Han To cite this version: Guo-Niu Han Hook lengths and shifted parts of partitions The Ramanujan Journal, 009, 9 p HAL Id: hal-00395690
More informationAnalysis of Boyer and Moore s MJRTY algorithm
Analysis of Boyer and Moore s MJRTY algorithm Laurent Alonso, Edward M. Reingold To cite this version: Laurent Alonso, Edward M. Reingold. Analysis of Boyer and Moore s MJRTY algorithm. Information Processing
More informationEvolution of the cooperation and consequences of a decrease in plant diversity on the root symbiont diversity
Evolution of the cooperation and consequences of a decrease in plant diversity on the root symbiont diversity Marie Duhamel To cite this version: Marie Duhamel. Evolution of the cooperation and consequences
More informationThomas Lugand. To cite this version: HAL Id: tel
Contribution à la Modélisation et à l Optimisation de la Machine Asynchrone Double Alimentation pour des Applications Hydrauliques de Pompage Turbinage Thomas Lugand To cite this version: Thomas Lugand.
More informationb-chromatic number of cacti
b-chromatic number of cacti Victor Campos, Claudia Linhares Sales, Frédéric Maffray, Ana Silva To cite this version: Victor Campos, Claudia Linhares Sales, Frédéric Maffray, Ana Silva. b-chromatic number
More informationLecture 9: Multi Kernel SVM
Lecture 9: Multi Kernel SVM Stéphane Canu stephane.canu@litislab.eu Sao Paulo 204 April 6, 204 Roadap Tuning the kernel: MKL The ultiple kernel proble Sparse kernel achines for regression: SVR SipleMKL:
More informationLecture 6: Minimum encoding ball and Support vector data description (SVDD)
Lecture 6: Minimum encoding ball and Support vector data description (SVDD) Stéphane Canu stephane.canu@litislab.eu Sao Paulo 2014 May 12, 2014 Plan 1 Support Vector Data Description (SVDD) SVDD, the smallest
More informationLecture 2: Linear SVM in the Dual
Lecture 2: Linear SVM in the Dual Stéphane Canu stephane.canu@litislab.eu São Paulo 2015 July 22, 2015 Road map 1 Linear SVM Optimization in 10 slides Equality constraints Inequality constraints Dual formulation
More informationFORMAL TREATMENT OF RADIATION FIELD FLUCTUATIONS IN VACUUM
FORMAL TREATMENT OF RADIATION FIELD FLUCTUATIONS IN VACUUM Frederic Schuller, Renaud Savalle, Michael Neumann-Spallart To cite this version: Frederic Schuller, Renaud Savalle, Michael Neumann-Spallart.
More informationOn Symmetric Norm Inequalities And Hermitian Block-Matrices
On Symmetric Norm Inequalities And Hermitian lock-matrices Antoine Mhanna To cite this version: Antoine Mhanna On Symmetric Norm Inequalities And Hermitian lock-matrices 015 HAL Id: hal-0131860
More informationCutwidth and degeneracy of graphs
Cutwidth and degeneracy of graphs Benoit Kloeckner To cite this version: Benoit Kloeckner. Cutwidth and degeneracy of graphs. IF_PREPUB. 2009. HAL Id: hal-00408210 https://hal.archives-ouvertes.fr/hal-00408210v1
More informationCan we reduce health inequalities? An analysis of the English strategy ( )
Can we reduce health inequalities? An analysis of the English strategy (1997-2010) Johan P Mackenbach To cite this version: Johan P Mackenbach. Can we reduce health inequalities? An analysis of the English
More informationFrom Unstructured 3D Point Clouds to Structured Knowledge - A Semantics Approach
From Unstructured 3D Point Clouds to Structured Knowledge - A Semantics Approach Christophe Cruz, Helmi Ben Hmida, Frank Boochs, Christophe Nicolle To cite this version: Christophe Cruz, Helmi Ben Hmida,
More informationSolving a quartic equation and certain equations with degree n
Solving a quartic equation and certain equations with degree n Abdeljalil Saghe To cite this version: Abdeljalil Saghe. Solving a quartic equation and certain equations with degree n. EUROPEAN JOURNAL
More informationSolving an integrated Job-Shop problem with human resource constraints
Solving an integrated Job-Shop problem with human resource constraints Olivier Guyon, Pierre Lemaire, Eric Pinson, David Rivreau To cite this version: Olivier Guyon, Pierre Lemaire, Eric Pinson, David
More informationThe Windy Postman Problem on Series-Parallel Graphs
The Windy Postman Problem on Series-Parallel Graphs Francisco Javier Zaragoza Martínez To cite this version: Francisco Javier Zaragoza Martínez. The Windy Postman Problem on Series-Parallel Graphs. Stefan
More informationapproximation results for the Traveling Salesman and related Problems
approximation results for the Traveling Salesman and related Problems Jérôme Monnot To cite this version: Jérôme Monnot. approximation results for the Traveling Salesman and related Problems. Information
More informationVibro-acoustic simulation of a car window
Vibro-acoustic simulation of a car window Christophe Barras To cite this version: Christophe Barras. Vibro-acoustic simulation of a car window. Société Française d Acoustique. Acoustics 12, Apr 12, Nantes,
More informationExact Comparison of Quadratic Irrationals
Exact Comparison of Quadratic Irrationals Phuc Ngo To cite this version: Phuc Ngo. Exact Comparison of Quadratic Irrationals. [Research Report] LIGM. 20. HAL Id: hal-0069762 https://hal.archives-ouvertes.fr/hal-0069762
More informationOn Symmetric Norm Inequalities And Hermitian Block-Matrices
On Symmetric Norm Inequalities And Hermitian lock-matrices Antoine Mhanna To cite this version: Antoine Mhanna On Symmetric Norm Inequalities And Hermitian lock-matrices 016 HAL Id: hal-0131860
More informationOn path partitions of the divisor graph
On path partitions of the divisor graph Paul Melotti, Eric Saias To cite this version: Paul Melotti, Eric Saias On path partitions of the divisor graph 018 HAL Id: hal-0184801 https://halarchives-ouvertesfr/hal-0184801
More informationNorm Inequalities of Positive Semi-Definite Matrices
Norm Inequalities of Positive Semi-Definite Matrices Antoine Mhanna To cite this version: Antoine Mhanna Norm Inequalities of Positive Semi-Definite Matrices 15 HAL Id: hal-11844 https://halinriafr/hal-11844v1
More informationClimbing discrepancy search for flowshop and jobshop scheduling with time-lags
Climbing discrepancy search for flowshop and jobshop scheduling with time-lags Wafa Karoui, Marie-José Huguet, Pierre Lopez, Mohamed Haouari To cite this version: Wafa Karoui, Marie-José Huguet, Pierre
More informationSparse Domain Adaptation in a Good Similarity-Based Projection Space
Sparse Domain Adaptation in a Good Similarity-Based Projection Space Emilie Morvant, Amaury Habrard, Stéphane Ayache To cite this version: Emilie Morvant, Amaury Habrard, Stéphane Ayache. Sparse Domain
More informationRobust minimum encoding ball and Support vector data description (SVDD)
Robust minimum encoding ball and Support vector data description (SVDD) Stéphane Canu stephane.canu@litislab.eu. Meriem El Azamin, Carole Lartizien & Gaëlle Loosli INRIA, Septembre 2014 September 24, 2014
More informationOn Newton-Raphson iteration for multiplicative inverses modulo prime powers
On Newton-Raphson iteration for multiplicative inverses modulo prime powers Jean-Guillaume Dumas To cite this version: Jean-Guillaume Dumas. On Newton-Raphson iteration for multiplicative inverses modulo
More informationEfficient Subquadratic Space Complexity Binary Polynomial Multipliers Based On Block Recombination
Efficient Subquadratic Space Complexity Binary Polynomial Multipliers Based On Block Recombination Murat Cenk, Anwar Hasan, Christophe Negre To cite this version: Murat Cenk, Anwar Hasan, Christophe Negre.
More informationIntroduction to Machine Learning Lecture 13. Mehryar Mohri Courant Institute and Google Research
Introduction to Machine Learning Lecture 13 Mehryar Mohri Courant Institute and Google Research mohri@cims.nyu.edu Multi-Class Classification Mehryar Mohri - Introduction to Machine Learning page 2 Motivation
More informationEntropies and fractal dimensions
Entropies and fractal dimensions Amelia Carolina Sparavigna To cite this version: Amelia Carolina Sparavigna. Entropies and fractal dimensions. Philica, Philica, 2016. HAL Id: hal-01377975
More informationSome tight polynomial-exponential lower bounds for an exponential function
Some tight polynomial-exponential lower bounds for an exponential function Christophe Chesneau To cite this version: Christophe Chesneau. Some tight polynomial-exponential lower bounds for an exponential
More informationFull-order observers for linear systems with unknown inputs
Full-order observers for linear systems with unknown inputs Mohamed Darouach, Michel Zasadzinski, Shi Jie Xu To cite this version: Mohamed Darouach, Michel Zasadzinski, Shi Jie Xu. Full-order observers
More informationFast Computation of Moore-Penrose Inverse Matrices
Fast Computation of Moore-Penrose Inverse Matrices Pierre Courrieu To cite this version: Pierre Courrieu. Fast Computation of Moore-Penrose Inverse Matrices. Neural Information Processing - Letters and
More informationLearning an Adaptive Dictionary Structure for Efficient Image Sparse Coding
Learning an Adaptive Dictionary Structure for Efficient Image Sparse Coding Jérémy Aghaei Mazaheri, Christine Guillemot, Claude Labit To cite this version: Jérémy Aghaei Mazaheri, Christine Guillemot,
More informationThe core of voting games: a partition approach
The core of voting games: a partition approach Aymeric Lardon To cite this version: Aymeric Lardon. The core of voting games: a partition approach. International Game Theory Review, World Scientific Publishing,
More informationA Simple Proof of P versus NP
A Simple Proof of P versus NP Frank Vega To cite this version: Frank Vega. A Simple Proof of P versus NP. 2016. HAL Id: hal-01281254 https://hal.archives-ouvertes.fr/hal-01281254 Submitted
More informationOn the longest path in a recursively partitionable graph
On the longest path in a recursively partitionable graph Julien Bensmail To cite this version: Julien Bensmail. On the longest path in a recursively partitionable graph. 2012. HAL Id:
More informationFinite volume method for nonlinear transmission problems
Finite volume method for nonlinear transmission problems Franck Boyer, Florence Hubert To cite this version: Franck Boyer, Florence Hubert. Finite volume method for nonlinear transmission problems. Proceedings
More informationNon-Bayesian Classifiers Part II: Linear Discriminants and Support Vector Machines
Non-Bayesian Classifiers Part II: Linear Discriminants and Support Vector Machines Selim Aksoy Department of Computer Engineering Bilkent University saksoy@cs.bilkent.edu.tr CS 551, Fall 2018 CS 551, Fall
More informationTwo-step centered spatio-temporal auto-logistic regression model
Two-step centered spatio-temporal auto-logistic regression model Anne Gégout-Petit, Shuxian Li To cite this version: Anne Gégout-Petit, Shuxian Li. Two-step centered spatio-temporal auto-logistic regression
More informationNew estimates for the div-curl-grad operators and elliptic problems with L1-data in the half-space
New estimates for the div-curl-grad operators and elliptic problems with L1-data in the half-space Chérif Amrouche, Huy Hoang Nguyen To cite this version: Chérif Amrouche, Huy Hoang Nguyen. New estimates
More informationStickelberger s congruences for absolute norms of relative discriminants
Stickelberger s congruences for absolute norms of relative discriminants Georges Gras To cite this version: Georges Gras. Stickelberger s congruences for absolute norms of relative discriminants. Journal
More informationNegative results on acyclic improper colorings
Negative results on acyclic improper colorings Pascal Ochem To cite this version: Pascal Ochem. Negative results on acyclic improper colorings. Stefan Felsner. 005 European Conference on Combinatorics,
More informationA remark on a theorem of A. E. Ingham.
A remark on a theorem of A. E. Ingham. K G Bhat, K Ramachandra To cite this version: K G Bhat, K Ramachandra. A remark on a theorem of A. E. Ingham.. Hardy-Ramanujan Journal, Hardy-Ramanujan Society, 2006,
More informationOn Solving Aircraft Conflict Avoidance Using Deterministic Global Optimization (sbb) Codes
On Solving Aircraft Conflict Avoidance Using Deterministic Global Optimization (sbb) Codes Sonia Cafieri, Frédéric Messine, Ahmed Touhami To cite this version: Sonia Cafieri, Frédéric Messine, Ahmed Touhami.
More informationA Slice Based 3-D Schur-Cohn Stability Criterion
A Slice Based 3-D Schur-Cohn Stability Criterion Ioana Serban, Mohamed Najim To cite this version: Ioana Serban, Mohamed Najim. A Slice Based 3-D Schur-Cohn Stability Criterion. ICASSP 007, Apr 007, Honolulu,
More informationSpatial representativeness of an air quality monitoring station. Application to NO2 in urban areas
Spatial representativeness of an air quality monitoring station. Application to NO2 in urban areas Maxime Beauchamp, Laure Malherbe, Laurent Letinois, Chantal De Fouquet To cite this version: Maxime Beauchamp,
More informationA Context free language associated with interval maps
A Context free language associated with interval maps M Archana, V Kannan To cite this version: M Archana, V Kannan. A Context free language associated with interval maps. Discrete Mathematics and Theoretical
More informationFinite element computation of leaky modes in straight and helical elastic waveguides
Finite element computation of leaky modes in straight and helical elastic waveguides Khac-Long Nguyen, Fabien Treyssede, Christophe Hazard, Anne-Sophie Bonnet-Ben Dhia To cite this version: Khac-Long Nguyen,
More informationBasic concepts and models in continuum damage mechanics
Basic concepts and models in continuum damage mechanics Djimedo Kondo, Hélène Welemane, Fabrice Cormery To cite this version: Djimedo Kondo, Hélène Welemane, Fabrice Cormery. Basic concepts and models
More informationConfluence Algebras and Acyclicity of the Koszul Complex
Confluence Algebras and Acyclicity of the Koszul Complex Cyrille Chenavier To cite this version: Cyrille Chenavier. Confluence Algebras and Acyclicity of the Koszul Complex. Algebras and Representation
More informationQuantum efficiency and metastable lifetime measurements in ruby ( Cr 3+ : Al2O3) via lock-in rate-window photothermal radiometry
Quantum efficiency and metastable lifetime measurements in ruby ( Cr 3+ : Al2O3) via lock-in rate-window photothermal radiometry A. Mandelis, Z. Chen, R. Bleiss To cite this version: A. Mandelis, Z. Chen,
More informationDYNAMICAL PROPERTIES OF MONOTONE DENDRITE MAPS
DYNAMICAL PROPERTIES OF MONOTONE DENDRITE MAPS Issam Naghmouchi To cite this version: Issam Naghmouchi. DYNAMICAL PROPERTIES OF MONOTONE DENDRITE MAPS. 2010. HAL Id: hal-00593321 https://hal.archives-ouvertes.fr/hal-00593321v2
More informationBest linear unbiased prediction when error vector is correlated with other random vectors in the model
Best linear unbiased prediction when error vector is correlated with other random vectors in the model L.R. Schaeffer, C.R. Henderson To cite this version: L.R. Schaeffer, C.R. Henderson. Best linear unbiased
More informationSupport Vector Machines for Classification: A Statistical Portrait
Support Vector Machines for Classification: A Statistical Portrait Yoonkyung Lee Department of Statistics The Ohio State University May 27, 2011 The Spring Conference of Korean Statistical Society KAIST,
More informationA Study of the Regular Pentagon with a Classic Geometric Approach
A Study of the Regular Pentagon with a Classic Geometric Approach Amelia Carolina Sparavigna, Mauro Maria Baldi To cite this version: Amelia Carolina Sparavigna, Mauro Maria Baldi. A Study of the Regular
More informationThe Mahler measure of trinomials of height 1
The Mahler measure of trinomials of height 1 Valérie Flammang To cite this version: Valérie Flammang. The Mahler measure of trinomials of height 1. Journal of the Australian Mathematical Society 14 9 pp.1-4.
More informationPolychotomous regression : application to landcover prediction
Polychotomous regression : application to landcover prediction Frédéric Ferraty, Martin Paegelow, Pascal Sarda To cite this version: Frédéric Ferraty, Martin Paegelow, Pascal Sarda. Polychotomous regression
More informationExtended-Kalman-Filter-like observers for continuous time systems with discrete time measurements
Extended-Kalman-Filter-lie observers for continuous time systems with discrete time measurements Vincent Andrieu To cite this version: Vincent Andrieu. Extended-Kalman-Filter-lie observers for continuous
More informationHiggs searches at L3
Higgs searches at L3 D. Teyssier To cite this version: D. Teyssier. Higgs searches at L3. High Energy Physics Conference - HEP-MAD 0, Sep 200, Antananariv, Madagascar. World Scientific, pp.67-72, 2002.
More informationReduced Models (and control) of in-situ decontamination of large water resources
Reduced Models (and control) of in-situ decontamination of large water resources Antoine Rousseau, Alain Rapaport To cite this version: Antoine Rousseau, Alain Rapaport. Reduced Models (and control) of
More informationSparsity Measure and the Detection of Significant Data
Sparsity Measure and the Detection of Significant Data Abdourrahmane Atto, Dominique Pastor, Grégoire Mercier To cite this version: Abdourrahmane Atto, Dominique Pastor, Grégoire Mercier. Sparsity Measure
More informationA CONDITION-BASED MAINTENANCE MODEL FOR AVAILABILITY OPTIMIZATION FOR STOCHASTIC DEGRADING SYSTEMS
A CONDITION-BASED MAINTENANCE MODEL FOR AVAILABILITY OPTIMIZATION FOR STOCHASTIC DEGRADING SYSTEMS Abdelhakim Khatab, Daoud Ait-Kadi, Nidhal Rezg To cite this version: Abdelhakim Khatab, Daoud Ait-Kadi,
More informationTowards an active anechoic room
Towards an active anechoic room Dominique Habault, Philippe Herzog, Emmanuel Friot, Cédric Pinhède To cite this version: Dominique Habault, Philippe Herzog, Emmanuel Friot, Cédric Pinhède. Towards an active
More informationSolution to Sylvester equation associated to linear descriptor systems
Solution to Sylvester equation associated to linear descriptor systems Mohamed Darouach To cite this version: Mohamed Darouach. Solution to Sylvester equation associated to linear descriptor systems. Systems
More informationDissipative Systems Analysis and Control, Theory and Applications: Addendum/Erratum
Dissipative Systems Analysis and Control, Theory and Applications: Addendum/Erratum Bernard Brogliato To cite this version: Bernard Brogliato. Dissipative Systems Analysis and Control, Theory and Applications:
More informationComputation and Experimental Measurements of the Magnetic Fields between Filamentary Circular Coils
Computation and Experimental Measurements of the Magnetic Fields between Filamentary Circular Coils Ao Anele, Y Hamam, L Chassagne, J Linares, Y Alayli, Karim Djouani To cite this version: Ao Anele, Y
More informationQuasi-periodic solutions of the 2D Euler equation
Quasi-periodic solutions of the 2D Euler equation Nicolas Crouseilles, Erwan Faou To cite this version: Nicolas Crouseilles, Erwan Faou. Quasi-periodic solutions of the 2D Euler equation. Asymptotic Analysis,
More informationAnalyzing large-scale spike trains data with spatio-temporal constraints
Analyzing large-scale spike trains data with spatio-temporal constraints Hassan Nasser, Olivier Marre, Selim Kraria, Thierry Viéville, Bruno Cessac To cite this version: Hassan Nasser, Olivier Marre, Selim
More informationAxiom of infinity and construction of N
Axiom of infinity and construction of N F Portal To cite this version: F Portal. Axiom of infinity and construction of N. 2015. HAL Id: hal-01162075 https://hal.archives-ouvertes.fr/hal-01162075 Submitted
More informationLorentz force velocimetry using small-size permanent magnet systems and a multi-degree-of-freedom force/torque sensor
Lorentz force velocimetry using small-size permanent magnet systems and a multi-degree-of-freedom force/torque sensor D Hernández, C Karcher To cite this version: D Hernández, C Karcher. Lorentz force
More informationParallel Repetition of entangled games on the uniform distribution
Parallel Repetition of entangled games on the uniform distribution André Chailloux, Scarpa Giannicola To cite this version: André Chailloux, Scarpa Giannicola. Parallel Repetition of entangled games on
More informationSelf-dual skew codes and factorization of skew polynomials
Self-dual skew codes and factorization of skew polynomials Delphine Boucher, Félix Ulmer To cite this version: Delphine Boucher, Félix Ulmer. Self-dual skew codes and factorization of skew polynomials.
More informationBoundary conditions control in ORCA2
Boundary conditions control in ORCA2 Eugene Kazantsev To cite this version: Eugene Kazantsev. Boundary conditions control in ORCA2. Journée thématique - Que peuvent attendre les modélisateurs de l assimilation?,
More informationOn infinite permutations
On infinite permutations Dmitri G. Fon-Der-Flaass, Anna E. Frid To cite this version: Dmitri G. Fon-Der-Flaass, Anna E. Frid. On infinite permutations. Stefan Felsner. 2005 European Conference on Combinatorics,
More informationMultiple sensor fault detection in heat exchanger system
Multiple sensor fault detection in heat exchanger system Abdel Aïtouche, Didier Maquin, Frédéric Busson To cite this version: Abdel Aïtouche, Didier Maquin, Frédéric Busson. Multiple sensor fault detection
More informationSome approaches to modeling of the effective properties for thermoelastic composites
Some approaches to modeling of the ective properties for thermoelastic composites Anna Nasedkina Andrey Nasedkin Vladimir Remizov To cite this version: Anna Nasedkina Andrey Nasedkin Vladimir Remizov.
More informationA proximal approach to the inversion of ill-conditioned matrices
A proximal approach to the inversion of ill-conditioned matrices Pierre Maréchal, Aude Rondepierre To cite this version: Pierre Maréchal, Aude Rondepierre. A proximal approach to the inversion of ill-conditioned
More informationLow frequency resolvent estimates for long range perturbations of the Euclidean Laplacian
Low frequency resolvent estimates for long range perturbations of the Euclidean Laplacian Jean-Francois Bony, Dietrich Häfner To cite this version: Jean-Francois Bony, Dietrich Häfner. Low frequency resolvent
More informationA Novel Aggregation Method based on Graph Matching for Algebraic MultiGrid Preconditioning of Sparse Linear Systems
A Novel Aggregation Method based on Graph Matching for Algebraic MultiGrid Preconditioning of Sparse Linear Systems Pasqua D Ambra, Alfredo Buttari, Daniela Di Serafino, Salvatore Filippone, Simone Gentile,
More informationThere are infinitely many twin primes 30n+11 and 30n+13, 30n+17 and 30n+19, 30n+29 and 30n+31
There are infinitely many twin primes 30n+11 and 30n+13, 30n+17 and 30n+19, 30n+29 and 30n+31 Sibiri Christian Bandre To cite this version: Sibiri Christian Bandre. There are infinitely many twin primes
More informationThe beam-gas method for luminosity measurement at LHCb
The beam-gas method for luminosity measurement at LHCb P. Hopchev To cite this version: P. Hopchev. The beam-gas method for luminosity measurement at LHCb. XLVth Rencontres de Moriond: Electroweak Interactions
More informationA non-linear simulator written in C for orbital spacecraft rendezvous applications.
A non-linear simulator written in C for orbital spacecraft rendezvous applications. Paulo Ricardo Arantes Gilz To cite this version: Paulo Ricardo Arantes Gilz. A non-linear simulator written in C for
More informationUsing multitable techniques for assessing Phytoplankton Structure and Succession in the Reservoir Marne (Seine Catchment Area, France)
Using multitable techniques for assessing Phytoplankton Structure and Succession in the Reservoir Marne (Seine Catchment Area, France) Frédéric Bertrand, Myriam Maumy, Anne Rolland, Stéphan Jacquet To
More informationSTATISTICAL ENERGY ANALYSIS: CORRELATION BETWEEN DIFFUSE FIELD AND ENERGY EQUIPARTITION
STATISTICAL ENERGY ANALYSIS: CORRELATION BETWEEN DIFFUSE FIELD AND ENERGY EQUIPARTITION Thibault Lafont, Alain Le Bot, Nicolas Totaro To cite this version: Thibault Lafont, Alain Le Bot, Nicolas Totaro.
More informationNumerical Modeling of Eddy Current Nondestructive Evaluation of Ferromagnetic Tubes via an Integral. Equation Approach
Numerical Modeling of Eddy Current Nondestructive Evaluation of Ferromagnetic Tubes via an Integral Equation Approach Anastassios Skarlatos, Grégoire Pichenot, Dominique Lesselier, Marc Lambert, Bernard
More informationFinite Volume for Fusion Simulations
Finite Volume for Fusion Simulations Elise Estibals, Hervé Guillard, Afeintou Sangam To cite this version: Elise Estibals, Hervé Guillard, Afeintou Sangam. Finite Volume for Fusion Simulations. Jorek Meeting
More information