Newton bilevel methods drop the lower-level strong-convexity assumption
Experiments cover synthetic tasks, data hyper-cleaning, and GPT-2 reweighting, with claimed better complexity than GALET and sl-BAMM.
2 stories, newest first · one card per story
Experiments cover synthetic tasks, data hyper-cleaning, and GPT-2 reweighting, with claimed better complexity than GALET and sl-BAMM.
EvoDuet co-evolves candidate solutions and web-search queries to improve LLM scientific discovery.
Today 2.5K readers · 2.7K views · 144 reads · all time 206K views