Goto

Collaborating Authors

 Statistical Learning

a02ef8389f6d40f84b50504613117f88-Paper.pdf

7ff97417474268e6b5a38bcbfae04944-Supplemental-Conference.pdf

7ff97417474268e6b5a38bcbfae04944-Paper-Conference.pdf

a0205b87490c847182672e8d371e9948-Supplemental.pdf

Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing

Neural Information Processing Systems

In this work, we investigate the problem of federated hyperparameter tuning.

ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs

Neural Information Processing Systems

However, this approach confronts two major challenges.

ca4b5656b7e193e6bb9064c672ac8dce-Paper.pdf

main

Neural Information Processing Systems

However, a considerable drawback is that these methods require both problem-specific potentials and individually tailored analyses.

Tighter Expected Generalization Error Bounds via Wasserstein Distance

Neural Information Processing Systems

This work presents several expected generalization error bounds based on the Wasserstein distance.

Tighter Expected Generalization Error Bounds via Wasserstein Distance

Neural Information Processing Systems

This work presents several expected generalization error bounds based on the Wasserstein distance.