Find Research Labs maintains this page using public sources. The faculty member, lab, and university have not claimed or approved this listing. Listing a lab does not indicate endorsement, partnership, or a recruiting opportunity.
How can algorithms be designed with provable efficiency and robustness for large-scale learning, online decision-making, and control? The group researches the design and analysis of algorithms for machine learning and optimization, including adaptive gradient methods like AdaGrad and first sublinear-time algorithms for convex optimization. Researchers develop and analyze projection-free and fast semidefinite programming solvers and online Newton-style methods to obtain logarithmic regret guarantees for online convex optimization. Work also introduces nonstochastic control theory linking optimization and control, with implementations and theoretical analysis to enable provable performance.
Research focus
What this lab works on
optimizationonline learningadaptive gradientsprojection-free methodscontrol theory
Selected work
Publications
Publication highlights are being curated.
Use the official faculty profile or website for the complete publication record.
People
Current and previous researchers
Alumni details have not been added.
See the official lab website for its alumni record. The lab can claim this profile to add previous researchers and their destinations.
Data provenance
Sources
This profile is curated by Find Research Labs from the public sources below. Listing information may change; consult the official sources for current details. Recruiting availability is unconfirmed.
