970 citations · 3k across the 88 of their papers we have counts for
5 papers · 1 filter
Scaling up Continuous-Time Markov Chains Helps Resolve Underspecification
Alkis Gotovos, Rebekka Burkholz, John Quackenbush +1
Modeling the time evolution of discrete sets of items (e.g., genetic mutations) is a fundamental problem in many biomedical applications. We approach this problem through the lens…
Can contrastive learning avoid shortcut solutions?
Joshua Robinson, Li Sun, Ke Yu +3
The generalization of representations learned via contrastive learning depends crucially on what features of the data are extracted. However, we observe that the contrastive loss d…
What training reveals about neural network complexity
Andreas Loukas, Marinos Poiitis, Stefanie Jegelka
This work explores the Benevolent Training Hypothesis (BTH) which argues that the complexity of the function a deep neural network (NN) is learning can be deduced by its training d…
Measuring Generalization with Optimal Transport
Ching-Yao Chuang, Youssef Mroueh, Kristjan Greenewald +2
Understanding the generalization of deep neural networks is one of the most important tasks in deep learning. Although much progress has been made, theoretical error bounds still o…
Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth
Keyulu Xu, Mozhi Zhang, Stefanie Jegelka +1
Graph Neural Networks (GNNs) have been studied through the lens of expressive power and generalization. However, their optimization properties are less well understood. We take the…