Mendelson, Shahar - Department of Mathematics, Technion, Israel Institute of Technology

• Analyse fonctionnelle/Functional Analysis Reconstruction and subgaussian processes
• On the Geometry of random {-1, 1}-polytopes S. Mendelson A. Pajor M. Rudelson
• Obtaining fast error rates in nonconvex situations Shahar Mendelson
• On Weakly Bounded Empirical Processes Shahar Mendelson
• Optimal Sample-Based Estimates of the Expectation of the Empirical Minimizer
• 1-regularized linear regression: Persistence and oracle inequalities5
• Discrepancy, Chaining and Subgaussian Processes Shahar Mendelson
• Empirical Processes and random projections B. Klartag1
• On the Limitations of Embedding Methods Shahar Mendelson
• On the Geometry of random {-1, 1}-polytopes S. Mendelson A. Pajor M. Rudelson
• Remarks on the Geometry of Coordinate Projections in Rn
• Journal of Machine Learning Research v (2002) pages Submitted 11/01; Published 10/02 Rademacher and Gaussian Complexities
• On singular values of matrices with independent S. Mendelson A. Pajor
• Empirical Minimization Peter L. Bartlett
• Analyse fonctionnelle/Functional Analysis Reconstruction and subgaussian processes
• The Shattering dimension of sets of linear functionals Shahar Mendelson
• Submitted to the Annals of Statistics REGULARIZATION IN KERNEL LEARNING
• Sharper lower bounds on the performance of the Empirical Risk Minimization Algorithm
• A subgaussian embedding theorem Shahar MENDELSON1
• On generic chaining and the smallest singular value of random matrices with heavy tails
• Empirical processes with a bounded 1 diameter Shahar Mendelson
• Majorizing measures and proportional subsets of bounded orthonormal systems
• Ellipsoid Approximation Using Random Vectors S. Mendelson and A. Pajor
• Local Rademacher Complexities Peter L. Bartlett
• Lipschitz representations of subsets of the cube Shahar Mendelson
• Local Rademacher Complexities Empirical Minimization
• A remark on non-exact oracle inequalities with applications to high-dimensional data analysis
• Embedding with a Lipschitz function Shahar Mendelson
• arXiv:math.ST/0608665v127Aug2006 Uniform uncertainty principle for Bernoulli
• Lower bounds for the empirical minimization Shahar Mendelson
• Reconstruction and subgaussian operators in Asymptotic Geometric Analysis
• On the optimality of the empirical risk minimization procedure for the Convex Aggregation problem
• Subspaces and orthogonal decompositions generated by bounded orthogonal systems
• In this thesis we investigate various mathematical aspects of learning in neural net-During a learning process a network is exposed and responds to various inputs. Then,
• Submitted to the Bernoulli On the optimality of the aggregate with
• Geometric parameters in Learning Theory Shahar Mendelson
• Gaussian averages of interpolated bodies and applications to approximate reconstruction