The massive datasets being compiled by our society present new challenges and opportunities to the field of statistical learning and inference. The increasing dimensionality of modern datasets lead to unique geometric and probabilistic phenomena, including scaling limits, phase transitions, and universality. A deeper understanding and clever exploitation of such fascinating (and sometimes counter-intuitive) high-dimensional phenomena can translate to both theoretical breakthroughs and novel algorithms.

In this talk, I will present several lines of recent work on signal estimation and multilayer neural networks where such high-dimensional phenomena are explored and exploited.

Co-sponsored by: Fairleigh Dickinson University

Speaker(s): Dr. Yue M. Lu,

Agenda:
The massive datasets being compiled by our society present new challenges and opportunities to the field of statistical learning and inference. The increasing dimensionality of modern datasets lead to unique geometric and probabilistic phenomena, including scaling limits, phase transitions, and universality. A deeper understanding and clever exploitation of such fascinating (and sometimes counter-intuitive) high-dimensional phenomena can translate to both theoretical breakthroughs and novel algorithms.

In this talk, I will present several lines of recent work on signal estimation and multilayer neural networks where such high-dimensional phenomena are explored and exploited.

Room: M105, Bldg: Muscarelle Center, M105, , 1000 River Road , Teaneck , New Jersey, United States, 07666, Virtual: https://events.vtools.ieee.org/m/319524