560 citations · 820 across the 9 of their papers we have counts for
6 papers · 1 filter
Grass: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients
Aashiq Muhamed, Oscar Li, David Woodruff +2
Large language model (LLM) training and finetuning are often bottlenecked by limited GPU memory. While existing projection-based optimization methods address this by projecting gra…
OmniPred: Language Models as Universal Regressors
Xingyou Song, Oscar Li, Chansoo Lee +4
Regression is a powerful tool to accurately predict the outcome metric of a system given a set of parameters, but has traditionally been restricted to methods which are only applic…
Two Sides of Meta-Learning Evaluation: In vs. Out of Distribution
Amrith Setlur, Oscar Li, Virginia Smith
We categorize meta-learning evaluation into two settings: [ID], in which the train and test tasks are sampled from the same underlying tas…
Label Leakage and Protection in Two-party Split Learning
Oscar Li, Jiankai Sun, Xin Yang +5
Two-party split learning is a popular technique for learning a model across feature-partitioned data. In this work, we explore whether it is possible for one party to steal the pri…
Is Support Set Diversity Necessary for Meta-Learning?
Amrith Setlur, Oscar Li, Virginia Smith
Meta-learning is a popular framework for learning with limited data in which an algorithm is produced by training over multiple few-shot learning tasks. For classification problems…
This Looks Like That: Deep Learning for Interpretable Image Recognition
Chaofan Chen, Oscar Li, Chaofan Tao +3
When we are faced with challenging image classification tasks, we often explain our reasoning by dissecting the image, and pointing out prototypical aspects of one class or another…