SDS Seminar Series – Dr. Purna Sarkar
Mar
29
2024
Mar
29
2024
Description
The Spring 2024 SDS Seminar Series continues on March 29th from 2:00 p.m. to 3:00 p.m. with Dr. Purna Sarkar (Statistics and Data Sciences, University of Texas at Austin). This event is in-person.
Title: Some New Results for Streaming Principal Component Analysis
Abstract: Streaming PCA, also known as Oja's algorithm, with roots going back to 1949, has attracted much attention in Statistics and Computer Science in the last decade. In this talk, I will discuss two of our works that consider this problem under slight departures from the setup considered widely in the literature.
Our first work looks at data streams generated from a Markov chain. While streaming PCA is typically analyzed under the IID data model, in many applications like distributed optimization, data points are sampled from a Markov chain and, therefore, are dependent. The naive approach of dropping data leads to a suboptimal rate. We use a novel linearization argument to remove the logarithmic dependence on the number of samples n.
Typically, the analysis of Oja's algorithm assumes that the effective rank of the covariance matrix is much smaller than n. Our second work examines online sparse PCA, where the effective rank is comparable to n. This differs from previously studied settings because the Oja vector does not concentrate on the true population eigenvector. Here, we show that a simple thresholding yields a consistent estimate of the population eigenvector. Both are joint works with Syamantak Kumar.
Location
Peter O’Donnell Jr. Building (POB) 2.302
Share
Other Events in This Series
Apr
3
2026
SDS Seminar Series – Leo Duan, University of Florida
Bayesian Distance-to-Set Models: from Latent Variable to Latent Projection
2:00 pm – 3:00 pm • In Person
Speaker(s): Leo Duan
Apr
17
2026
SDS Seminar Series – Rina Foygel Barber, University of Chicago
False Detection Rate Control in Time Series Coincidence Detection
2:00 pm – 3:00 pm • In Person
Speaker(s): Rina Foygel Barber
Sep
11
2026
SDS Seminar Series – Shuangjie Zhang, University of Texas at Austin
Structure Learning for Directed Trees with Zero-Inflated Compositional Nodes
2:00 pm – 3:00 pm • In Person
Speaker(s): Shuangjie Zhang
Sep
18
2026
SDS Seminar Series – Arhit Chakrabarti, University of Texas at Austin
Graphical Dirichlet Process for Clustering Non-Exchangeable Grouped Data
2:00 pm • In Person
Speaker(s): Arhit Chakrabarti
Sep
25
2026
SDS Seminar Series – Chad Hazlett, University of California, Los Angeles
The Synthetic Confounder: What Pre-Treatment Outcomes Can and Cannot Buy in Longitudinal Causal Inference
2:00 pm – 3:00 pm • In Person
Speaker(s): Chad Hazlett
Oct
2
2026
SDS Seminar Series – Giovanni Toto, University of Texas at Austin
Condition matrix completion for polypharmacy medication information
2:00 pm – 3:00 pm
Speaker(s): Giovanni Toto
Oct
9
2026
SDS Seminar Series – Anirban Bairagi University of Texas at Austin
TBA
2:00 pm – 3:00 pm
Speaker(s): Anirban Bairagi
Oct
16
2026
SDS Seminar Series – Adam Klivans, University of Texas at Austin
TBA
2:00 pm – 3:00 pm
Speaker(s): Adam Klivans
Oct
23
2026
SDS Seminar Series – Casey Breen, University of Texas at Austin
TBD
2:00 pm – 3:00 pm • In Person
Speaker(s): Casey Breen
Oct
30
2026
SDS Seminar Series – Sanjay Shakkottai, University of Texas at Austin
TBA
2:00 pm – 3:00 pm
Speaker(s): Sanjay Shakkottai