4 problems

In real-valued statistical learning, the $gamma$-fat-shattering dimension controls learnability and uniform convergence only up to a possible factor of $2$ in the scale. Phil Long'…

In binary classification, let $d$ denote the relevant complexity parameter and let $n$ be the sample size. The one-inclusion graph approach gives an in-expectation PAC error bound…

Let the risk function and empirical risk arise from a sparse, possibly non-convex M-estimation problem, with sparsity constraint represented by an $_ell_0$ restriction. Uniform con…

Uniform periodic approximation conjecture. For each $c\in(0,1]$ and almost all $\alpha$, the limit $F(c)$ exists and