Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Mingda Qiao

Properly learning decision trees in almost polynomial time


Sep 01, 2021
Guy Blanc, Jane Lange, Mingda Qiao, Li-Yang Tan

* 21 pages, to appear in FOCS 2021 

  Access Paper or Ask Questions

Decision tree heuristics can fail, even in the smoothed setting


Jul 02, 2021
Guy Blanc, Jane Lange, Mingda Qiao, Li-Yang Tan

* To appear in RANDOM 2021 

  Access Paper or Ask Questions

Exponential Weights Algorithms for Selective Learning


Jun 29, 2021
Mingda Qiao, Gregory Valiant

* To appear in COLT 2021 

  Access Paper or Ask Questions

Stronger Calibration Lower Bounds via Sidestepping


Dec 07, 2020
Mingda Qiao, Gregory Valiant


  Access Paper or Ask Questions

A Theory of Selective Prediction


Feb 27, 2019
Mingda Qiao, Gregory Valiant


  Access Paper or Ask Questions

On Generalization Error Bounds of Noisy Gradient Methods for Non-Convex Learning


Feb 02, 2019
Jian Li, Xuanyuan Luo, Mingda Qiao


  Access Paper or Ask Questions

Do Outliers Ruin Collaboration?


May 12, 2018
Mingda Qiao

* Accepted to ICML 2018 

  Access Paper or Ask Questions

Learning Discrete Distributions from Untrusted Batches


Nov 22, 2017
Mingda Qiao, Gregory Valiant


  Access Paper or Ask Questions

Nearly Optimal Sampling Algorithms for Combinatorial Pure Exploration


Jun 04, 2017
Lijie Chen, Anupam Gupta, Jian Li, Mingda Qiao, Ruosong Wang

* Accepted to COLT 2017 

  Access Paper or Ask Questions

Towards Instance Optimal Bounds for Best Arm Identification


May 24, 2017
Lijie Chen, Jian Li, Mingda Qiao

* Accepted to COLT 2017 

  Access Paper or Ask Questions

Practical Algorithms for Best-K Identification in Multi-Armed Bandits


May 19, 2017
Haotian Jiang, Jian Li, Mingda Qiao


  Access Paper or Ask Questions

Nearly Instance Optimal Sample Complexity Bounds for Top-k Arm Selection


Feb 13, 2017
Lijie Chen, Jian Li, Mingda Qiao

* Accepted by AISTATS 2017 

  Access Paper or Ask Questions