Keller Jordan

According to our database, Keller Jordan authored at least 4 papers between 2023 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

94% on CIFAR-10 in 3.29 Seconds on a Single GPU.

Keller Jordan

CoRR, 2024

On the Variance of Neural Network Training with respect to Test Sets and Distributions.

Keller Jordan

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Calibrated Chaos: Variance Between Runs of Neural Network Training is Harmless and Inevitable.

Keller Jordan

CoRR, 2023

REPAIR: REnormalizing Permuted Activations for Interpolation Repair.

Keller Jordan, Hanie Sedghi, Olga Saukh, Rahim Entezari, Behnam Neyshabur

Proceedings of the Eleventh International Conference on Learning Representations, 2023