Niao He
Associate Professor of Computer Science at ETH Zurich
IAS SEMINAR #19/2026
Turin / OGR / Duomo / October 27, 2026 / 06:00 – 08:00 pm CEST
Minima Selection in Deep Learning
EVENT&WEBINAR
Deep learning operates in highly overparameterized, nonconvex regimes where the loss landscape often contains many global minimizers forming connected manifolds. In such settings, optimization does not simply find a minimizer. Empirically, even after training error reaches zero, test performance often continues to improve, suggesting that learning dynamics keep evolving within the manifold of solutions. This raises a fundamental question: which minima do learning algorithms select? More ambitiously, can we steer learning dynamics toward desirable minima? In this talk, I will present recent results that shed light on both implicit and active minima selection, highlighting the roles played by optimization dynamics, stochastic noise, and the geometry of the solution manifold.
NIAO HE
Niao He is an Associate Professor in the Department of Computer Science at ETH Zurich, where she leads the Optimization and Decision Intelligence (ODI) Group. She is Co-Director of the Max Planck ETH Center for Learning Systems, a core faculty member of the ETH AI Center, and an ELLIS Scholar. Before joining ETH Zurich, she was an Assistant Professor at the University of Illinois Urbana-Champaign from 2016 to 2020. She received her Ph.D. in Operations Research from the Georgia Institute of Technology in 2015. Her research develops optimization foundations for modern AI, spanning resource-efficient optimization, reinforcement learning, multi-agent systems, and generative models. Her work has been recognized with honors including an AISTATS Best Paper Award, an NSF CRII Award, and an SNSF Starting Grant. She currently serves as an Associate Editor for the SIAM Journal on Optimization and Mathematics of Operations Research, and regularly serves as a Senior Area Chair for major machine learning conferences including NeurIPS and ICML.
In collaboration with:
Register for In-Person Attendance
Joining us in person offers the opportunity for direct networking and interaction with both speakers and participants.
Please complete the form below to reserve your seat.
By clicking, you will be automatically registered for the in-person event.
Note: If you see a message saying you’re already subscribed, please ignore it — your in-person registration will still be confirmed.
Please note that, by attending, you implicitly authorize AI4I to film and photograph the audience during the seminar. By submitting your registration, you acknowledge and accept the AI4I Data Privacy Policy. Seats are limited: if you are unable to attend, we kindly ask you to inform us as soon as possible at ias@ai4i.it
LINK ZOOM
