Presentation: 2025 ND EPSCoR Annual conference
October 21, 2025, NDSU Memorial Union, Fargo, North Dakota
Winning The Lottery Every Time: Reliably Identifying Strong Lottery Tickets in Neural Networks
Bryce
Christopherson
Assistant Professor
University of North Dakota
Co-authors: Darian Colgrove, Master's Student, University of North Dakota, Jack Baretz, Undergraduate Student, University of North Dakota, Daniel Kwakye, Master's Student, University of North Dakota, Salah Dandan, Undergraduate Student, University of North Dakota, Martin Epstein, Undergraduate Student, University of North Dakota
Session
Concurrent Presentation Session C, Group 3
Hidatsa Room
In 2019, Frankle and Carbin provided an interesting conjecture known as the lottery ticket hypothesis, which supposes that large random neural networks usually contain a 'lucky' sub-network that is 'just as good' as the larger network. A stronger form of the conjecture was later proven, revealing that pruning allows for universal approximation in the same fashion as training. It has been an open question how to reliably find such subnetworks. We show that the standard edge-popup algorithm provided by Ramanujan et. al. is enough to do this in sufficiently sparse networks and, based on some observations from this, provide a variant of the edge-popup algorithm that allows for strong lottery ticket extraction in any network.