Sparsity as Sorcery (Next Two Weeks at the Statistics Seminar)
Attention conservation notice: Only of interest if you (1)
care about high-dimensional statistics and (2) will be in Pittsburgh over the
next two weeks.
I am not sure how our distinguished speakers would feel at being called
sorcerers, but since one of them is using sparsity to read minds, and the other
to infer causation from correlation, it is hard to think of a more appropriate
- Bin Yu, "Sparse Modeling: Unified Theory and Movie Reconstruction Based on
- Abstract: Information technology has enabled the collection of
massive amounts of data in science, engineering, social science, finance and
beyond. Statistics is the science of data and indispensable for extracting
useful information from high-dimensional data. After broad successes of
statistical machine learning on prediction through regularization,
interpretability is gaining attention and sparsity is used as its proxy. With
the virtues of both regularization and sparsity, L1 penalized Least Squares
(e.g. Lasso) has been intensively studied by researchers from statistics,
applied mathematics, and signal processing. Lasso is a special case of sparse
modeling and has also been the focus on compressive sensing lately.
- In this talk, I would like to cover both theory and practice of Lasso and
its extensions. First, I will present an insightful unified analysis of
M-estimation with decomposable penalties under sparse high dimensional
statistical models. Second, I will present collaborative research with the
Gallant Neuroscience Lab at Berkeley on understanding human visual pathway. In
particular, I will show how we use non-linear sparse models (SPAM) to improve
encoding and decoding results for the visual cortex area V1, and I will explain
how Lasso and ridge methods enter our movie reconstruction algorithm from fMRI
brain signals (dubbed by TIME Magazine as "mind-reading computers" and selected
as one of its 50 Best Inventions of 2011).
- Time and place: 4--5 pm on Monday, 2 April 2012, in Scaife Hall 125
- Peter Bühlmann, "Predicting Causal Effects in High-Dimensional Settings"
- Abstract: Understanding cause-effect relationships between
variables is of great interest in many fields of science. An ambitious but
highly desirable goal is to infer causal effects from observational data
obtained by observing a system of interest without subjecting it to
interventions. This would allow to circumvent severe experimental constraints
or to substantially lower experimental costs. Our main motivation to study this
goal comes from applications in biology.
- We present recent progress for prediction of causal effects with direct
implications on designing new intervention experiments, particularly for
high-dimensional, sparse settings with thousands of variables but based on only
a few dozens of observations. We highlight exciting possibilities and
fundamental limitations. In view of the latter, statistical modeling needs to
be complemented with experimental validations: we discuss this in the context
of molecular biology for yeast (Saccharomyces cerevisiae) and the
model plant Arabidopsis thaliana.
- Time and place: 4--5 pm on Wednesday, 11 April 2012, in Scaife Hall 125
As always, the talks are free and open to the public; hecklers will, however, be turned into newts.
Enigmas of Chance;
Minds, Brains, Neurons
Posted at March 29, 2012 13:10 | permanent link