SDS Seminar Series – Po-Ling Loh, University of Cambridge

art by Peter Olexa
Event starts on this day

Mar

28

2025

Event starts at this time 2:00 pm – 3:00 pm
In Person (view details)
Featured Speaker(s): Po-Ling Loh
Cost: Free
Differentially Private M-estimation via Noisy Optimization

Description

The Spring 2025 SDS Seminar Series continues on March 28th from 2:00 p.m. to 3:00 p.m. with Dr. Poh-Ling Loh (Professor, Department of Pure Mathematics and Mathematical Statistics, University of Cambridge). This event is in-person in the Avaya Room (POB 2.302).    

Title: Differentially Private M-estimation via Noisy Optimization

Abstract: We present a noisy composite gradient descent algorithm for differentially private statistical estimation in high dimensions. We begin by providing general rates of convergence for the parameter error of successive iterates under assumptions of local restricted strong convexity and local restricted smoothness. Our analysis is local, in that it ensures a linear rate of convergence when the initial iterate lies within a constant-radius region of the true parameter. At each iterate, multivariate Gaussian noise is added to the gradient in order to guarantee that the output satisfies Gaussian differential privacy. We then derive consequences of our theory for linear regression and mean estimation. Motivated by M-estimators used in robust statistics, we study loss functions which downweight the contribution of individual data points in such a way that the sensitivity of function gradients is guaranteed to be bounded, even without the usual assumption that our data lie in a bounded domain. We prove that the objective functions thus obtained indeed satisfy the restricted convexity and restricted smoothness conditions required for our general theory. We will also discuss the benefits of acceleration in optimization procedures, specifically a private version of the Frank-Wolfe algorithm, and its consequences for statistical estimation.

This is based on joint work with Marco Avella-Medina, Casey Bradshaw, Zheng Liu, and Laurentiu Marchis.

Location

POB 2.302

Share


Audience

Other Events in This Series

Sep

8

2023

Seminar Series

SDS Seminar Series – Dr. Emily Roberts

A Causal Inference Approach for Surrogate Marker Evaluation with Mixed Models

2:00 pm – 3:00 pm In Person

Speaker(s): Emily Roberts

Sep

15

2023

Seminar Series

SDS Seminar Series – Dr. Dimitris Korobilis

Monitoring Multicountry Macroeconomic Risk

2:00 pm – 3:00 pm Virtual

Speaker(s): Dimitris Korobilis

Sep

22

2023

Seminar Series

SDS Seminar Series – Dr. Will Fithian

Estimating the False Discovery Rate of Model Selection

2:00 pm – 3:00 pm In Person

Speaker(s): Will Fithian

Sep

29

2023

Seminar Series

SDS Seminar Series – Dr. David Moriarty

A Data Science Journey in Business

2:00 pm – 3:00 pm In Person

Speaker(s): David Moriarty

Oct

6

2023

Seminar Series

SDS Seminar Series – Dr. Amanda Ellis

Navigating the Future of Statistics Education: Leveraging ChatGPT's Advantages and Overcoming Challenges

2:00 pm – 3:00 pm Virtual

Speaker(s): Amanda Ellis

Oct

20

2023

Seminar Series

SDS Seminar Series – Dr. Amy Zhang

Bisimulation and Reinforcement Learning

2:00 pm – 3:00 pm Virtual

Speaker(s): Amy Zhang

Oct

27

2023

Seminar Series

SDS Seminar Series – Dr. Marcelo Medeiros

Global Inflation Forecasting: Benefits from Machine Learning Methods

2:00 pm – 3:00 pm Virtual

Speaker(s): Marcelo Medeiros

Nov

3

2023

Seminar Series

SDS Seminar Series - Dr. Steve Yadlowsky

Choosing a Proxy Metric from Past Experiments

2:00 pm – 3:00 pm Virtual

Speaker(s): Steve Yadlowsky

Nov

10

2023

Seminar Series

SDS Seminar Series – Drew Herren

Statistical Aspects of SHAP: Functional ANOVA for Model Interpretation

2:00 pm – 3:00 pm In Person

Speaker(s): Drew Herren

Dec

1

2023

Seminar Series

SDS Seminar Series – Dr. Dave Zhao

High-Dimensional Nonparametric Empirical Bayes Problems in Genomics

2:00 pm – 3:00 pm In Person

Speaker(s): Dave Zhao