2016 - 2017

2017 Jan 26

Seminar: Edgar Dobriban

12:00pm to 1:00pm

Location: 

Science Center Rm. 705

ePCA: Exponential family PCA

Many applications, such as photon-limited imaging and genomics, involve large datasets with entries from exponential family distributions. It is of interest to estimate the covariance structure and principal components of the noiseless distribution. Principal Component Analysis (PCA), the standard method for this setting, can be inefficient for non-Gaussian noise. In this talk we present ePCA, a methodology for PCA on exponential family distributions. ePCA involves the eigendecomposition of a new covariance matrix estimator, constructed in a...

Read more about Seminar: Edgar Dobriban
2016 Nov 01

STAT 300: Keith Chan

12:00pm to 1:00pm

Location: 

Science Center Rm. 705
"Robust Optimal Estimation of Asymptotic Covariance Matrix in Non-stationary Multi-dimensional Time Series" by Keith Chan
2016 Nov 15

STAT 300: Edo Airoldi

12:00pm to 1:00pm

Location: 

Science Center Rm. 705
Model-assisted design of experiments on networks
2016 Sep 29

Pickard Award Lecture and Reception: Nicholas Horton

4:00pm to 6:00pm

Location: 

Science Center Hall A

Click here to watch the 2016 Pickard Award Lecture, featuring Professor Nicholas Horton.

We are pleased to announce that Professor Nicholas Horton of Amherst College has been chosen as the 2016 Pickard Lecturer. Congratulations! For those who may not know about the award, you can learn more about it at https://statistics.fas.harvard.edu/dempster-award...

Read more about Pickard Award Lecture and Reception: Nicholas Horton
2016 Dec 06

STAT 300: Shihao Yang

12:00pm to 1:00pm

Location: 

Science Center Rm. 705
Sequential Hypothesis Testing for Time Series
2017 Feb 01

Seminar: Lucas Janson

12:00pm to 1:00pm

Location: 

Science Center Rm. 705

Model-free knockoffs: high-dimensional variable selection that controls the false discovery rate

Many contemporary large-scale applications involve building interpretable models linking a large set of potential covariates to a response in a nonlinear fashion, such as when the response is binary. Although this modeling problem has been extensively studied, it remains unclear how to effectively control the fraction of false discoveries even in high-dimensional logistic regression, not to mention general high-dimensional nonlinear models. To address such a practical problem, we...

Read more about Seminar: Lucas Janson
2017 Mar 28

STAT 300: Robin Gong

12:00pm to 1:00pm

Location: 

Science Center Rm. 705
An SMC approach to set-valued posterior inference
2016 Oct 11

STAT 300: Yang Chen

12:00pm to 1:00pm

Location: 

Science Center Rm. 705
Bayesian Hierarchical Hidden Markov Models for Single-Molecule Data

Pages