Search Results for author:
Found 4 papers, 0 papers with code
Privately Estimating a Gaussian: Efficient, Robust and Optimal
We prove a new lower bound on differentially private covariance estimation to show that the dependence on the condition number $\kappa$ in the above sample bound is also tight.
Near-optimal fitting of ellipsoids to random points
6031-6036, 2013] conjecture that the ellipsoid fitting problem transitions from feasible to infeasible as the number of points $n$ increases, with a sharp threshold at $n \sim d^2/4$.
Optimal Regularization Can Mitigate Double Descent
Recent empirical and theoretical studies have shown that many learning algorithms -- from linear regression to neural networks -- can have test performance that is non-monotonic in quantities such the sample size and model size.
A Fast Spectral Algorithm for Mean Estimation with Sub-Gaussian Rates
The goal is to design an efficient estimator that attains the optimal sub-gaussian error bound, only assuming that the random vector has bounded mean and covariance.
