← Search

Viktoria Schram

2 accepted papers

2026

Active Budget Allocation for Efficient Scaling Law Estimation via Surrogate-Guided Pruning

ICML 2026poster

Predicting model performance at larger scales enables the design of training strategies and architectures tailored to specific performance targets. Empirical scaling law research identifies functional forms to aid this prediction task. These describe the relationship between loss and compute using a…

Cited by 0SourceScholar
2025

Zero-Shot Performance Prediction for Probabilistic Scaling Laws

NeurIPS 2025poster

The prediction of learning curves for Natural Language Processing (NLP) models enables informed decision-making to meet specific performance objectives, while reducing computational overhead and lowering the costs associated with dataset acquisition and curation. In this work, we formulate the predi…

Cited by 0SourceScholar