Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Terminal Shrinkage Averaging Reveals a Schedule-Estimator Interaction in LLM Pretraining
Adam Ousherovitch, Yixin Wang
Large language model (LLM) pretraining conventionally returns the raw final iterate. This couples two design choices: the learning-rate schedule that generates the parameter trajec…
cs.LG2026
Learning to Extrapolate to New Tasks: A Relational Approach to Task Extrapolation
Adam Ousherovitch, Yixin Wang
Modern learning systems excel at interpolation but struggle to generalize to unseen tasks outside the training distribution's support. This failure occurs even in simple settings,…
cs.LG2023
Imputing Brain Measurements Across Data Sets via Graph Neural Networks
Yixin Wang, Wei Peng, Susan F. Tapert +2
Publicly available data sets of structural MRIs might not contain specific measurements of brain Regions of Interests (ROIs) that are important for training machine learning models…