4 papers
Dynamics Over Landscape: The Emergence of Linear Separability via Spectral Alignment in Contrastive Learning
Jeff Calder, Wonjun Lee
Contrastive learning effectively clusters data despite a loss landscape filled with poor solutions, a success that is heavily dependent on the choice of data augmentations. How opt…
An Elementary Proof of a Minimax Theorem
Jeff Calder
Here, we give a self-contained and elementary proof of a minimax theorem due to Fan in a simplified setting that can be taught in an advanced undergraduate course. Our proof follow…
GLL: A Differentiable Graph Learning Layer for Neural Networks
Jason Brown, Bohan Chen, Harris Hardiman-Mostow +2
Standard deep learning architectures used for classification generate label predictions with a projection head and softmax activation function. Although successful, these methods f…
Numerical solution of a PDE arising from prediction with expert advice
Jeff Calder, Nadejda Drenska, Drisana Mosaphir
This work investigates the online machine learning problem of prediction with expert advice in an adversarial setting through numerical analysis of, and experiments with, a related…