11 papers
Presenting a proof of the Kannan-Lovasz-Simonovits conjecture
Pierre Bizeul, Boaz Klartag, Joseph Lehec
Together with Bourgain's slicing problem and the variance conjecture, the Kannan-Lovász-Simonovits (KLS) conjecture has been a driving force for mathematical developments in high d…
Optimal MM* bounds for convex bodies
Pierre Bizeul
Let be a convex body in isotropic position. We prove the optimal mean-width estimate \[ M^*(K)\leq C\sqrt{n\log n}. \] The main new ingredient is a geometric inequal…
Minimum Norm Interpolation via the Local Theory of Banach Spaces: The Role of -Uniform Convexity
Gil Kur, Pierre Bizeul
The minimum-norm interpolator (MNI) framework has recently attracted considerable attention as a tool for understanding generalization in overparameterized models, such as neural n…
Distances between non-symmetric convex bodies: optimal bounds up to polylog
Pierre Bizeul, Boaz Klartag
In this paper we determine, up to polylogarithmic factors, the diameter of the Banach--Mazur compactum of -dimensional convex bodies without symmetry assumptions. We prove that…
Entropy and Learning of Lipschitz Functions under Log-Concave Measures
Pierre Bizeul, Boaz Klartag
We study regression of -Lipschitz functions under a log-concave measure on . We focus on the high-dimensional regime where the sample size is subexponentia…
Polynomial Approximation in of the Double Exponential via Complex Analysis
Pierre Bizeul, Boaz Klartag
We study the polynomial approximation problem in where . We show that for any absolutely continuous function , $$ \sum_{k=1}^{\infty} \log^2(…
The slicing conjecture via small ball estimates
Pierre Bizeul
Bourgain's slicing conjecture was recently resolved by Joseph Lehec and Bo'az Klartag. We present an alternative proof by establishing small ball probability estimates for isotropi…
On the Log-Sobolev Constant of Log-Concave Vectors
Pierre Bizeul
It is well known that if a random vector satisfies a log-Sobolev inequality, all of its marginals have subgaussian tails. In the spirit of the KLS conjecture, we investigate whethe…
On measures strongly log-concave on a subspace
Pierre Bizeul
In this work we study the concentration properties of log-concave measures that are curved only on a subspace of directions. Proofs uses an adapted version of the stochastic locali…
Entropy and Information jump for log-concave vectors
Pierre Bizeul
We extend the result of Ball and Nguyen on the jump of entropy under convolution for logconcave random vectors. We show that the result holds for any pair of vectors (not necessari…
Positive solutions for large random linear systems
Pierre Bizeul, Jamal Najim
Consider a large linear system where is a matrix with independent real standard Gaussian entries, is a vector of ones and with unkn…