#  The Boston Area Differential Privacy Seminar Series Kicked Off 

 





February 08, 2021

 

 

- [ Blog ](/news-categories/blog)
 
 

 

 The Boston-area DP seminar series kicked off last week. As a reminder, you can get updates about the seminar series by joining [this google group](https://urldefense.proofpoint.com/v2/url?u=https-3A__groups.google.com_g_bostondataprivacy&d=DwMFaQ&c=WO-RGvefibhHBZq3fL85hQ&r=z5rNifhWcGlmk5wTbFoujwunXeqWMX9z0dOuQ_Lp5XY&m=mtrJruRk2YpI89gXBsuw6zixKqDLvJzpK5HsfP5bj_k&s=-Y81LLEW1v2DTYunbW2cOr3VUdzuT_N8AfTfOUUAy9M&e=) and checking [this calendar](https://urldefense.proofpoint.com/v2/url?u=https-3A__calendar.google.com_calendar_u_0-3Fcid-3DZmN2MDBuNGd2MjdwazY0M2E4OXEwNDVqajRAZ3JvdXAuY2FsZW5kYXIuZ29vZ2xlLmNvbQ&d=DwMFaQ&c=WO-RGvefibhHBZq3fL85hQ&r=z5rNifhWcGlmk5wTbFoujwunXeqWMX9z0dOuQ_Lp5XY&m=mtrJruRk2YpI89gXBsuw6zixKqDLvJzpK5HsfP5bj_k&s=2lMRToqQzJgwhvZi3QSxKKDuRYD5j0YJKunp-_dnux4&e=).

 **Past Speaker, 2/5:** Vikrant Singhal  
**Title:** Private Mean Estimation of Heavy-Tailed Distributions  
**Abstract:**  We give new upper and lower bounds on the minimax sample complexity of differentially private mean estimation of distributions with bounded $k$-th moments. Roughly speaking, in the univariate case, we show that $$n = \\Theta\\left(\\frac{1}{\\alpha^2} + \\frac{1}{\\alpha^{\\frac{k}{k-1}}\\varepsilon}\\right)$$ samples are necessary and sufficient to estimate the mean to $\\alpha$-accuracy under $\\varepsilon$-differential privacy, or any of its common relaxations. This result demonstrates a qualitatively different behavior compared to estimation absent privacy constraints, for which the sample complexity is identical for all $k \\geq 2$. We also give algorithms for the multivariate setting whose sample complexity is a factor of $O(d)$ larger than the univariate case.

 **----------------Upcoming Speakers:**

 **2/12: Ruobin Gong "Towards Good Statistical Inference from Differentially Private Data"**

 **2/19: Lijie Chen "On Distributed Differential Privacy and Counting Distinct Elements"**





 

 

 



 

 

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