Campuses:

Robustness

Tuesday, June 18, 2019 - 2:00pm - 2:50pm
John Duchi (Stanford University)
A common goal in statistics and machine learning is to learn models that can perform well against distributional shifts, such as latent heterogeneous subpopulations, unknown covariate shifts, or unmodeled temporal effects. We develop and analyze a distributionally robust stochastic optimization (DRO) framework that learns a model that provides good performance against perturbations to the data-generating distribution. We give a convex optimization formulation for the problem, providing several convergence guarantees.
Wednesday, April 13, 2016 - 9:00am - 10:00am
Srinivasa Salapaka (University of Illinois at Urbana-Champaign)
Many techniques for nanoscale investigation, even though developed in different areas which do not have anything in common in terms of motivation or objectives, pose problems that are remarkably similar. Many of these problems involve regulation or estimation of certain physical variables under constraints and various uncertainties. In many cases existing solutions are area specific, static or open-loop, which are often inadequate or costly.
Monday, September 28, 2015 - 9:00am - 10:00am
Munther Dahleh (Massachusetts Institute of Technology)
Robust interconnections have been the subject of study by the control community for several decades. Substantial progress has been made in the context of both stability and performance robustness for various types of interconnections. Typical problems addressed in the literature involved interconnections with simple topologies but with more complex components (dynamic, sometimes with high dimensions).
Wednesday, August 5, 2009 - 10:00am - 10:20am
Christopher Bemis (Whitebox Advisors)


href=/2008-2009/MM8.5-14.09/activities/Bemis-Christopher/portfolio_fig1_wl.jpg>

Friday, November 20, 2015 - 12:00pm - 12:15pm
German Enciso (University of California)
It has recently been shown that structural conditions on the reaction network, rather than a ‘fine-tuning’ of system parameters, often suffice to impart ‘absolute concentration robustness’ on a wide class of biologically relevant, deterministically modeled mass-action systems [Shinar and Feinberg, Science, 2010].
Tuesday, March 27, 2012 - 3:30pm - 4:15pm
Constantine Caramanis (The University of Texas at Austin)
In this talk we revisit (high dimensional) sparse regression -- the topic of much recent study and attention. Unlike the standard setting where covariates (the sensing matrix entries) are assumed to be known perfectly and the output (the response variables) free of persistent errors/corruption, real world applications may be plagued by both.
Wednesday, August 6, 2008 - 11:40am - 12:00pm


src=/2007-2008/MM8.6-15.08/activities/Wu-Chai/prob6.jpg>

Tuesday, March 4, 2008 - 2:50pm - 3:30pm
Markus Kollmann (Humboldt-Universität)
Any signalling network must be able to extract weak signals from a noisy
environment and be robust against background perturbations, such as
stochastic fluctuations in protein levels or variations in temperature and
ambient stimulation. Our aim is to elucidate how these tasks have been
solved in the evolutionary design of the chemotaxis pathway in E. coli, one
of the best studied models for signal transduction. Combining
fluorescence-based experimental analyses of spatial and temporal dynamics of
Subscribe to RSS - Robustness