Robust Linear Regression: Optimal Rates in Polynomial Time

We obtain robust and computationally efficient estimators for learning several linear models that achieve statistically optimal convergence rate under minimal distributional assumptions. Concretely, we assume our data is drawn from a $k$-hypercontractive distribution and an $ε$-fraction is adversarially corrupted. We then describe an estimator that converges to the optimal least-squares minimiz…

Paper

Similar papers

© 2026 NYSGPT2525 LLC