IEM Seminar Series: Survival of the Deepest: A Tale of ML's Hardiest Species
Abstract
Machine learning (ML) has undergone a dramatic evolutionary shift over the past decade—from the carefully structured world of mathematical optimization to the fast-paced, empirical frontier of deep learning. In this talk, I'll take the audience on my journey through this transformation, using the lens of natural selection. We'll revisit the "Jurassic era" of ML, when semidefinite programs and convex analysis roamed free, and explore how today's research ecosystem favors fast-moving, GPU-powered neural networks.
Along the way, I'll share how my group's research has evolved and adapted—from our work in semidefinite programming to current projects blending rigorous theory with real-world impact in areas like adversarial robustness, game theory, reinforcement learning, and large language models. We'll examine climate change in ML conferences, why theory still matters, and how optimization can survive (and even thrive) in the Deepocene epoch. Expect evolutionary metaphors, a few memes, and hopefully some laughs as we chart the survival strategies that will shape ML's future.
Bio
Volkan Cevher received the B.Sc. (valedictorian) in electrical engineering from Bilkent University in Ankara, Turkey, in 1999 and the Ph.D. in electrical and computer engineering from the Georgia Institute of Technology in Atlanta, GA in 2005. He was a Research Scientist with the University of Maryland, College Park, from 2006-2007 and also with Rice University in Houston, TX, from 2008-2009. He was also a Faculty Fellow in the Electrical and Computer Engineering Department at Rice University from 2010-2020. Currently, he is an Associate Professor at the Swiss Federal Institute of Technology Lausanne and an Amazon Scholar. His research interests include machine learning, optimization theory and methods, and automated control. Dr. Cevher is an IEEE Fellow ('24), an ELLIS fellow, and was the recipient of the ICML AdvML Best Paper Award in 2023, Google Faculty Research award in 2018, the IEEE Signal Processing Society Best Paper Award in 2016, a Best Paper Award at CAMSAP in 2015, a Best Paper Award at SPARS in 2009, and an ERC CG in 2016 as well as an ERC StG in 2011.
Machine learning (ML) has undergone a dramatic evolutionary shift over the past decade—from the carefully structured world of mathematical optimization to the fast-paced, empirical frontier of deep learning. In this talk, I'll take the audience on my journey through this transformation, using the lens of natural selection. We'll revisit the "Jurassic era" of ML, when semidefinite programs and convex analysis roamed free, and explore how today's research ecosystem favors fast-moving, GPU-powered neural networks.
Along the way, I'll share how my group's research has evolved and adapted—from our work in semidefinite programming to current projects blending rigorous theory with real-world impact in areas like adversarial robustness, game theory, reinforcement learning, and large language models. We'll examine climate change in ML conferences, why theory still matters, and how optimization can survive (and even thrive) in the Deepocene epoch. Expect evolutionary metaphors, a few memes, and hopefully some laughs as we chart the survival strategies that will shape ML's future.
Bio
Volkan Cevher received the B.Sc. (valedictorian) in electrical engineering from Bilkent University in Ankara, Turkey, in 1999 and the Ph.D. in electrical and computer engineering from the Georgia Institute of Technology in Atlanta, GA in 2005. He was a Research Scientist with the University of Maryland, College Park, from 2006-2007 and also with Rice University in Houston, TX, from 2008-2009. He was also a Faculty Fellow in the Electrical and Computer Engineering Department at Rice University from 2010-2020. Currently, he is an Associate Professor at the Swiss Federal Institute of Technology Lausanne and an Amazon Scholar. His research interests include machine learning, optimization theory and methods, and automated control. Dr. Cevher is an IEEE Fellow ('24), an ELLIS fellow, and was the recipient of the ICML AdvML Best Paper Award in 2023, Google Faculty Research award in 2018, the IEEE Signal Processing Society Best Paper Award in 2016, a Best Paper Award at CAMSAP in 2015, a Best Paper Award at SPARS in 2009, and an ERC CG in 2016 as well as an ERC StG in 2011.
Practical information
- General public
- Free
Contact
- Prof. Jean-Philippe Thiran, IEM Director