3 papers
cs.LG2026
Favorability of Loss Landscape with Weight Decay Requires Both Large Overparametrization and Initialization
Etienne Boursier, Matthew Bowditch, Matthias Englert +1
The optimization of neural networks under weight decay remains poorly understood from a theoretical standpoint. While weight decay is standard practice in modern training procedure…
cs.LG2026
Mildly Overparameterized ReLU Networks on Orthogonal Data: Incremental Learning and Implicit Bias
James Town, Etienne Boursier, Ben Lewis +2
The successful training of neural networks hinges on the use of first order optimization methods, yet the theoretical characterization of these methods remains incomplete. This is…
cs.CV2026
Velocity and stroke rate reconstruction of canoe sprint team boats based on panned and zoomed video recordings
Julian Ziegler, Daniel Matthes, Finn Gerdts +5
Pacing strategies, defined by velocity and stroke rate profiles, are essential for peak performance in canoe sprint. While GPS is the gold standard for analysis, its limited availa…