#  Probabilitas Seminar: Jason Klusowski 

 



####  calendar\_today Date and Time 

 **February 21, 2025** 

 10:30AM - 11:30AM EST 

####  pin\_drop Location 

 **Science Center 316**  



 

 



 

 The Probabilitas Seminar series focuses on high-dimensional problems that combine statistics, probability, information theory, computer science, and other related fields. The upcoming seminar takes place on Friday, February 21, from 10:30-11:30am EST. The talk will be hybrid, both in-person in Science Center 316 and on Zoom (please contact the department for Zoom information). This week's guest will be Jason Klusowski of Princeton University's Department of Operations Research and Financial Engineering.

 **Statistical-computational Trade-offs for Recursive Adaptive Partitioning Estimators**

 Recursive adaptive partitioning estimators, like decision trees and their ensembles, are effective for high-dimensional regression but usually rely on greedy training, which can become stuck at suboptimal solutions. We study this phenomenon in estimating sparse regression functions over binary features, showing that when the true function satisfies a certain structural property—Abbe et al. (2022)’s Merged Staircase Property (MSP)—greedy training achieves low estimation error with only a logarithmic number of samples in the feature count. In contrast, when MSP is absent, estimation becomes exponentially more difficult. Interestingly, this dichotomy between efficient and inefficient estimation resembles the behavior of two-layer neural networks trained with SGD in the mean-field regime. Meanwhile, ERM-trained recursive adaptive partitioning estimators achieve low estimation error with logarithmically many samples, regardless of MSP, revealing a fundamental statistical-computational trade-off for greedy training.



 

 



 

 

 Share on:- [     Facebook ](#)
- [     Twitter ](#)
- [     Linkedin ](#)
 


 Save: [ Add to calendar calendar\_today ](https://statistics.fas.harvard.edu/node/1627286/event-feed.ics)  Copy link link