29 citations · 37 across the 8 of their papers we have counts for
3 papers · 1 filter
Active Budget Allocation for Efficient Scaling Law Estimation via Surrogate-Guided Pruning
Viktoria Schram, Markus Hiller, Daniel Beck +1
Predicting model performance at larger scales enables the design of training strategies and architectures tailored to specific performance targets. Empirical scaling law research i…
Zero-Shot Performance Prediction for Probabilistic Scaling Laws
Viktoria Schram, Markus Hiller, Daniel Beck +1
The prediction of learning curves for Natural Language Processing (NLP) models enables informed decision-making to meet specific performance objectives, while reducing computationa…
On Enforcing Better Conditioned Meta-Learning for Rapid Few-Shot Adaptation
Markus Hiller, Mehrtash Harandi, Tom Drummond
Inspired by the concept of preconditioning, we propose a novel method to increase adaptation speed for gradient-based meta-learning methods without incurring extra parameters. We d…