Publications (51)
Modified empirical CLT's under only pre-Gaussian conditions
Shahar Mendelson, Joel Zinn
A remark on the diameter of random sections of convex bodies
Shahar Mendelson
A probabilistic approach to the geometry of the \ell_p^n-ball
Franck Barthe, Olivier Guedon, Shahar Mendelson +1
On the geometry of polytopes generated by heavy-tailed random vectors
Olivier Guédon, Felix Krahmer, Christian Kümmerle +2
Bounding the smallest singular value of a random matrix without concentration
Vladimir Koltchinskii, Shahar Mendelson
Reconstruction and subgaussian operators
Shahar Mendelson, Alain Pajor, Nicole Tomczak-Jaegermann
Minimax rate of convergence and the performance of ERM in phase recovery
Guillaume Lecué, Shahar Mendelson
On generic chaining and the smallest singular value of random matrices with heavy tails
Shahar Mendelson, Grigoris Paouris
Majorizing measures and proportional subsets of bounded orthonormal systems
Olivier Guedon, Shahar Mendelson, Alain Pajor +1
On the geometry of random polytopes
Shahar Mendelson
Improved bounds for sparse recovery from subsampled random convolutions
Shahar Mendelson, Holger Rauhut, Rachel Ward
Necessary moment conditions for exact reconstruction via basis pursuit
Guillaume Lecué, Shahar Mendelson
On the optimality of the aggregate with exponential weights for low temperatures
Guillaume Lecué, Shahar Mendelson
Learning subgaussian classes : Upper and minimax bounds
Guillaume Lecué, Shahar Mendelson
On aggregation for heavy-tailed classes
Shahar Mendelson
Sparse recovery under weak moment assumptions
Guillaume Lecué, Shahar Mendelson
Sharper lower bounds on the performance of the empirical risk minimization algorithm
Guillaume Lecué, Shahar Mendelson
Concentration of the spectral norm of ErdÅs-Rényi random graphs
Gábor Lugosi, Shahar Mendelson, Nikita Zhivotovskiy
On multiplier processes under weak moment assumptions
Shahar Mendelson
General nonexact oracle inequalities for classes with a subexponential envelope
Guillaume Lecué, Shahar Mendelson
Robust one-bit compressed sensing with partial circulant matrices
Sjoerd Dirksen, Shahar Mendelson
Dvoretzky type theorems for subgaussian coordinate projections
Shahar Mendelson
Uniform uncertainty principle for Bernoulli and subgaussian ensembles
Shahar Mendelson, Alain Pajor, Nicole Tomczak-Jaegermann
Empirical processes with bounded Ï_1 diameter
Shahar Mendelson
On weakly bounded empirical processes
Shahar Mendelson
Non-Gaussian Hyperplane Tessellations and Robust One-Bit Compressed Sensing
Sjoerd Dirksen, Shahar Mendelson
Upper bounds on product and multiplier empirical processes
Shahar Mendelson
Robust covariance estimation under $L_4-L_2$ norm equivalence
Shahar Mendelson, Nikita Zhivotovskiy
Learning without Concentration for General Loss Functions
Shahar Mendelson
Stable recovery and the coordinate small-ball behaviour of random vectors
Shahar Mendelson, Grigoris Paouris
Generalized Dual Sudakov Minoration via Dimension Reduction - A Program
Shahar Mendelson, Emanuel Milman, Grigoris Paouris
Regularization, sparse recovery, and median-of-means tournaments
Gábor Lugosi, Shahar Mendelson
`local' vs. `global' parameters -- breaking the gaussian complexity barrier
Shahar Mendelson
Column normalization of a random measurement matrix
Shahar Mendelson
Risk minimization by median-of-means tournaments
Gabor Lugosi, Shahar Mendelson
Suprema of Chaos Processes and the Restricted Isometry Property
Felix Krahmer, Shahar Mendelson, Holger Rauhut
An optimal unrestricted learning procedure
Shahar Mendelson
Sub-Gaussian estimators of the mean of a random vector
Gábor Lugosi, Shahar Mendelson
Near-optimal mean estimators with respect to general norms
Gábor Lugosi, Shahar Mendelson
Approximating the covariance ellipsoid
Shahar Mendelson
Discrepancy, chaining and subgaussian processes
Shahar Mendelson
Discussion of "2004 IMS Medallion Lecture: Local Rademacher complexities and oracle inequalities in risk minimization" by V. Koltchinskii
Peter L. Bartlett, Shahar Mendelson
Mean estimation and regression under heavy-tailed distributions--a survey
Gabor Lugosi, Shahar Mendelson
A remark on "Robust machine learning by median-of-means"
Gabor Lugosi, Shahar Mendelson
Regularization in kernel learning
Shahar Mendelson, Joseph Neeman
The shattering dimension of sets of linear functionals
Shahar Mendelson, Gideon Schechtman
Regularization and the small-ball method II: complexity dependent error rates
Guillaume Lecué, Shahar Mendelson
Learning without Concentration
Shahar Mendelson
Local Rademacher complexities
Peter L. Bartlett, Olivier Bousquet, Shahar Mendelson
Performance of empirical risk minimization in linear aggregation
Guillaume Lecué, Shahar Mendelson
Regularization and the small-ball method I: sparse recovery
Guillaume Lecué, Shahar Mendelson