- PhD thesis presentation Statistical Learning Theory
- Motivation Contributions Fast learning rates for plug-in classifiers under
- JOURNAL OF LATEX CLASS FILES, VOL. ?, NO. ?, ?? 1 Context-Dependent Kernels for Object
- The Annals of Statistics 2007, Vol. 35, No. 2, 608633
- TH`ESE DE DOCTORAT DE L'UNIVERSITE PARIS VI Specialite : Mathematiques
- Metric Entropy and Gaussian Bandits S. Grunewalder
- Transductive Segmentation of Textured Meshes Anne-Laure Chauve, Jean-Philippe Pons, Jean-Yves Audibert, and
- Minimax policies for adversarial and stochastic bandits Jean-Yves Audibert
- Vanishing point detection for road detection Jean-Yves Audibert
- Algorithms for Infinitely Many-Armed Bandits Department of Statistics -University of Michigan
- Algorithms for Infinitely Many-Armed Bandit (Supplementary file)
- Semantic Lattices for Multiple Annotation of Images Anne-Marie Tousch
- Toward Manifold-Adaptive Learning Amir massoud Farahmand Csaba Szepesvari
- Graph-Cut Transducers for Relevance Feedback in Content Based Image Hichem Sahbi
- Tuning bandit algorithms in stochastic environments
- Use of variance estimation in the multi-armed bandit problem
- Fast learning rates in statistical inference through aggregation
- Radon space and Adaboost for Pose Estimation Patrick Etyngier1
- From Graphs to Manifolds Weak and Strong Pointwise Consistency of Graph Laplacians
- Semantic hierarchies for image annotation : a survey Anne-Marie Touscha,b
- Context McAllester's pioneering work The different PAC-Bayes bounds Main ideas in Chap.1 Application to linear least squares PAC-Bayesian bounds
- No fast exponential deviation inequalities for the progressive mixture rule
- Graph Laplacian for Interactive Image Retrieval1
- Variance estimates and exploration function in multi-armed bandit
- Fast interactive segmentation using color and textural information
- Diffeomorphic Matching and Image Jean-Yves Audibert
- AUDIBERT Jean-Yves born in 1976, French nationality
- APPRENTISSAGE STATISTIQUE (ENS 2010 2011)
- Apprentissage statistique 1 Exercice 1 (VC-dimension pour des frontires coniques)
- Apprentissage statistique 1 Correction de l'exercice 1
- Exercice 1 (Vitesse de convergence de l'algorithme des k-p.p.v.) On considre le problme de la rgression aux moindres carrs. L'espace des entres est
- Correction de l'exercice 1 1. Prendre des lments de la forme [k1
- Classement de caract`eres manuscrits 1 Presentation des donnees
- Apprentissage statistique 1 k + et k/n 0.
- Exercice 1 (algorithme par partition) Dans cet exercice, nous considrons que l'espace des entres est [0; 8[ et l'espace des sorties
- Correction de l'exercice 1 ^f0(x) = 0, 4 pour tout x [0; 8[.
- Ecole des Ponts ParisTech -Universit Marne-La-Valle 2010-2011 Machine Learning et Applications
- Compromis exploration-exploitation et theorie des jeux
- Exercice 1 (Prdiction squentielle) Considrons le problme de prdiction squentielle suivant : les valeurs prdire sont notes
- Habilitation diriger des recherches de l'Universit Paris-Est
- Manifold Learning using Robust Graph Laplacian for Interactive Image Search Hichem Sahbi
- Empirical Bernstein Stopping Volodymyr Mnih mnih@cs.ualberta.ca
- TIP-05166-2009, ACCEPTED 1 General road detection from a single image
- Regret Bounds for Gaussian Process Bandit Problems Steffen Grunewalder Jean-Yves Audibert Manfred Opper John Shawe-Taylor
- The Annals of Statistics 2009, Vol. 37, No. 4, 15911646
- Exploration-exploitation trade-off using variance estimates in multi-armed bandits
- Ecole des Ponts ParisTech 2009-2010 Machine Learning et Applications
- Context-Dependent Kernel Design for Object Matching and Recognition Hichem Sahbi
- Exercice 1 (l'implmentation d'AdaBoost) Notons par -1 et +1 les classes d'un problme de classification binaire. Soient Z1 =
- Transductive segmentation Olivier Duchenne1
- Known results New results Risk bounds for linear regression
- Best Arm Identification in Multi-Armed Bandits Jean-Yves Audibert
- Best Arm Identification in Multi-Armed Bandits Jean-Yves Audibert
- Ecole des Ponts ParisTech -Universit Marne-La-Valle 2010-2011 Machine Learning et Applications
- 1 Bandit View on Noisy Optimization Jean-Yves Audibert audibert@certis.enpc.fr
- Intrinsic Dimensionality Estimation of Submanifolds in Rd Matthias Hein mh@tuebingen.mpg.de
- Proof of the optimality of the empirical star J.-Y. Audibert
- Exercice 1 (Prdiction avec experts pondrs par des poids exponentiels) On se place dans le cadre de la prdiction squentielle avec K experts. Soit (yt)t1 une
- Ecole des Ponts ParisTech 2009-2010 Machine Learning et Applications
- Variants of known results New results Risk bounds for linear regression
- Graph-Cut Transducers for Relevance Feedback in Content
- Progressive mixture rules are deviation suboptimal Jean-Yves Audibert
- Fast learning rates in statistical inference through aggregation
- 1 Proof of Theorem 1 The first assertion is a direct consequence of Lemma 3.3 and Corollary 4.1 of [2]. The second
- Apprentissage statistique 1 Exercice 1 (sur l'algorithme des k plus proches voisins)
- Segmentation by transduction Olivier Duchenne
- Correction de l'exercice 1 1) Ewe-Y f(X) = pe + (1 -p)e-.
- TIP-05187-2009, ACCEPTED 1 Detecting Abandoned Objects with a Moving
- Journal of Machine Learning Research 11 (2010) 2785-2836 Submitted 7/09; Revised 6/10; Published 10/10 Regret Bounds and Minimax Policies under Partial Monitoring
- Some links between min-cuts, optimal spanning forests and watersheds
- AGGREGATED ESTIMATORS AND EMPIRICAL COMPLEXITY FOR LEAST SQUARE REGRESSION
- A randomized online learning algorithm for better variance control
- Some links between extremum spanning forests, watersheds and min-cuts
- Bandit game Parameters available to the forecaster
- Fast learning rates for plug-in classifiers under the margin condition
- Submitted to the Annals of Statistics ROBUST LINEAR LEAST SQUARES REGRESSION
- Data-driven Crowd Analysis in Videos Mikel Rodriguez1,4
- Density-aware person detection and tracking in crowds Mikel Rodriguez1,4
- Semantic hierarchies for image annotation: A survey Anne-Marie Tousch a,b
- Minimax Policies for Combinatorial Prediction Games Jean-Yves Audibert
- Deviations of stochastic bandit regret Antoine Salomon1
- Exercice 1 (Prdiction avec experts pondrs par des poids exponentiels) On se place dans le cadre de la prdiction squentielle avec K experts. Soit (yt)t1 une
- Exercice 1 ("Anytime policy") Nous nous plaons dans le cadre de la prdiction squentielle avec avis d'experts : les obser-
