2 papers
cs.LG2026
The Finetuner's Fallacy: When to Pretrain with Your Finetuning Data
Christina Baek, Ricardo Pio Monti, David Schwab +31
Real-world model deployments demand strong performance on narrow domains where data is often scarce. Typically, practitioners finetune models to specialize them, but this risks ove…
cs.CV2024
Scaling Training Data with Lossy Image Compression
Katherine L. Mentzer, Andrea Montanari
Empirically-determined scaling laws have been broadly successful in predicting the evolution of large machine learning models with training data and number of parameters. As a cons…