Bringing Statistical Thinking in Distributed Optimization. Vignettes from statistical inference over Networks
Prof. Gesualdo Scutari
Purdue University, West Lafayette
IN, USA
DEIB - Seminar Room "N. Schiavoni" (Bld. 20)
July 17th, 2023
2.15 pm
Contacts:
Alessandro Falsone
Maria Prandini
Research Line:
Control systems
Purdue University, West Lafayette
IN, USA
DEIB - Seminar Room "N. Schiavoni" (Bld. 20)
July 17th, 2023
2.15 pm
Contacts:
Alessandro Falsone
Maria Prandini
Research Line:
Control systems
Sommario
On July 17th, 2023 at 2.15 pm Gesualdo Scutari, Professor with the School of Industrial Engineering and Electrical and Computer Engineering at Purdue University, IN, USA, will hold a seminar on "Bringing Statistical Thinking in Distributed Optimization. Vignettes from statistical inference over Networks" in DEIB Seminar Room (Building 20).
There is growing interest in solving large-scale statistical machine learning problems over decentralized networks, where data are distributed across the nodes of the network and no centralized coordination is present (we termed these systems "mesh" networks).
Modern massive datasets create a fundamental problem at the intersection of the computational and statistical sciences: how to provide guarantees on the quality of statistical inference given bounds on computational resources, such as time and communication efforts. While statistical-computation trade-offs have been largely explored in the centralized setting, our understanding over mesh networks is limited: (i) distributed schemes, designed and performing well in the classical low-dimensional regime, can break down in the high-dimensional case; and (ii) existing convergence studies may fail to predict algorithmic behaviors; some are in fact confuted by experiments. This is mainly due to the fact that the majority of distributed algorithms have been designed and studied only from the optimization perspective, lacking the statistical dimension. This talk will discuss some vignettes from high-dimensional statistical inference suggesting new analyses (and designs) aiming at bringing statistical thinking in distributed optimization.
Gesualdo Scutari is a Professor with the School of Industrial Engineering and Electrical and Computer Engineering at Purdue University, West Lafayette, IN, USA, and he is a Purdue Faculty Scholar. His research interests include optimization, equilibrium programming, and their applications to signal processing and machine learning. Among others, he was a recipient of the 2013 NSF CAREER Award, the 2015 IEEE Signal Processing Society Young Author Best Paper Award, and the 2020 IEEE Signal Processing Society Best Paper Award.
He serves as an IEEE Signal Processing Distinguish Lecturer (2023-2024). He served on the editorial broad of several IEEE journals and he is currently an Associate Editor of SIAM Journal on Optimization. He is IEEE Fellow.
There is growing interest in solving large-scale statistical machine learning problems over decentralized networks, where data are distributed across the nodes of the network and no centralized coordination is present (we termed these systems "mesh" networks).
Modern massive datasets create a fundamental problem at the intersection of the computational and statistical sciences: how to provide guarantees on the quality of statistical inference given bounds on computational resources, such as time and communication efforts. While statistical-computation trade-offs have been largely explored in the centralized setting, our understanding over mesh networks is limited: (i) distributed schemes, designed and performing well in the classical low-dimensional regime, can break down in the high-dimensional case; and (ii) existing convergence studies may fail to predict algorithmic behaviors; some are in fact confuted by experiments. This is mainly due to the fact that the majority of distributed algorithms have been designed and studied only from the optimization perspective, lacking the statistical dimension. This talk will discuss some vignettes from high-dimensional statistical inference suggesting new analyses (and designs) aiming at bringing statistical thinking in distributed optimization.
Gesualdo Scutari is a Professor with the School of Industrial Engineering and Electrical and Computer Engineering at Purdue University, West Lafayette, IN, USA, and he is a Purdue Faculty Scholar. His research interests include optimization, equilibrium programming, and their applications to signal processing and machine learning. Among others, he was a recipient of the 2013 NSF CAREER Award, the 2015 IEEE Signal Processing Society Young Author Best Paper Award, and the 2020 IEEE Signal Processing Society Best Paper Award.
He serves as an IEEE Signal Processing Distinguish Lecturer (2023-2024). He served on the editorial broad of several IEEE journals and he is currently an Associate Editor of SIAM Journal on Optimization. He is IEEE Fellow.
