Search Results for author:
Found 5 papers, 2 papers with code
Optimal Sketching Bounds for Sparse Linear Regression
For this problem, under the $\ell_2$ norm, we observe an upper bound of $O(k \log (d)/\varepsilon + k\log(k/\varepsilon)/\varepsilon^2)$ rows, showing that sparse recovery is strictly easier to sketch than sparse regression.
Coresets for Classification -- Simplified and Strengthened
It also does not depend on the specific loss function, so a single coreset can be used in multiple training scenarios.
Designing Transportable Experiments
To reduce the variance of our estimator, we design a covariate balance condition (Target Balance) between the treatment and control groups based on the target population.
Methodology
Efficient Second-Order Shape-Constrained Function Fitting
We give an algorithm to compute a one-dimensional shape-constrained function that best fits given data in weighted-$L_{\infty}$ norm.
Agnostic Estimation of Mean and Covariance
We consider the problem of estimating the mean and covariance of a distribution from iid samples in $\mathbb{R}^n$, in the presence of an $\eta$ fraction of malicious noise; this is in contrast to much recent work where the noise itself is assumed to be from a distribution of known type.
