activity
20122023
most citedTheoretically Principled Trade-off between Robustness and Accuracy

921 citations · 1.7k across the 59 of their papers we have counts for

collaborators
Showing math.STShow all

6 papers · 1 filter

math.ST2020★ 4 cited

When does the Tukey median work?

Banghua Zhu, Jiantao Jiao, Jacob Steinhardt

We analyze the performance of the Tukey median estimator under total variation (TV) distance corruptions. Previous results show that under Huber's additive corruption model, the br…

math.ST2019★ 26 cited

Generalized Resilience and Robust Statistics

Banghua Zhu, Jiantao Jiao, Jacob Steinhardt

Robust statistics traditionally focuses on outliers, or perturbations in total variation distance. However, a dataset could be corrupted in many other ways, such as systematic meas…

math.ST2017★ 16 cited

Optimal rates of entropy estimation over Lipschitz balls

Yanjun Han, Jiantao Jiao, Tsachy Weissman +1

We consider the problem of minimax estimation of the entropy of a density over Lipschitz balls. Dropping the usual assumption that the density is bounded away from zero, we obtain…

math.ST2017★ 18 cited

On Estimation of -Norms in Gaussian White Noise Models

Yanjun Han, Jiantao Jiao, Rajarshi Mukherjee

We provide a complete picture of asymptotically minimax estimation of -norms (for any ) of the mean in Gaussian white noise model over Nikolskii-Besov spaces. In this…

math.ST2017★ 4 cited

Bias Correction with Jackknife, Bootstrap, and Taylor Series

Jiantao Jiao, Yanjun Han

We analyze bias correction methods using jackknife, bootstrap, and Taylor series. We focus on the binomial model, and consider the problem of bias correction for estimating ,…

math.ST2017★ 32 cited

Minimax Estimation of the Distance

Jiantao Jiao, Yanjun Han, Tsachy Weissman

We consider the problem of estimating the distance between two discrete probability measures and from empirical data in a nonasymptotic and large alphabet setting. Wh…