3 papers
cs.LG2026
TBDFiltering: Sample-Efficient Tree-Based Data Filtering
Robert Istvan Busa-Fekete, Julian Zimmert, Anne Xiangyi Zheng +2
The quality of machine learning models depends heavily on their training data. Selecting high-quality, diverse training sets for large language models (LLMs) is a difficult task, d…
cs.LG2025
Toward Understanding In-context vs. In-weight Learning
Bryan Chan, Xinyi Chen, András György +1
It has recently been demonstrated empirically that in-context learning emerges in transformers when certain distributional properties are present in the training data, but this abi…
cs.LG2025
Partition Tree Weighting for Non-Stationary Stochastic Bandits
Joel Veness, Marcus Hutter, Andras Gyorgy +1
This paper considers a generalisation of universal source coding for interaction data, namely data streams that have actions interleaved with observations. Our goal will be to cons…