no code implementations • 24 Jun 2023 • Alycia Lee, Brando Miranda, Sudharsan Sundar, Sanmi Koyejo
Current trends to pre-train capable Large Language Models (LLMs) mostly focus on scaling of model and dataset size.
no code implementations • 29 Sep 2021 • Alycia Lee, Anthony L Pineci, Uriah Israel, Omer Bar-Tal, Leeat Keren, David A. Van Valen, Anima Anandkumar, Yisong Yue, Anqi Liu
For each layer, we also achieve higher accuracy when the overall accuracy is kept fixed across different methods.
no code implementations • 17 Apr 2019 • Kevin K. Yang, Yuxin Chen, Alycia Lee, Yisong Yue
Importantly, we show that our objective function can be efficiently decomposed as a difference of submodular functions (DS), which allows us to employ DS optimization tools to greedily identify sets of constraints that increase the likelihood of finding items with high utility.