Zobrazeno 1 - 10
of 90
pro vyhledávání: '"Li, Oscar"'
Large language model (LLM) training and finetuning are often bottlenecked by limited GPU memory. While existing projection-based optimization methods address this by projecting gradients into a lower-dimensional subspace to reduce optimizer state mem
Externí odkaz:
http://arxiv.org/abs/2406.17660
Autor:
Song, Xingyou, Li, Oscar, Lee, Chansoo, Yang, Bangding, Peng, Daiyi, Perel, Sagi, Chen, Yutian
Over the broad landscape of experimental design, regression has been a powerful tool to accurately predict the outcome metrics of a system or model given a set of parameters, but has been traditionally restricted to methods which are only applicable
Externí odkaz:
http://arxiv.org/abs/2402.14547
Unrolled computation graphs are prevalent throughout machine learning but present challenges to automatic differentiation (AD) gradient estimation methods when their loss functions exhibit extreme local sensitivtiy, discontinuity, or blackbox charact
Externí odkaz:
http://arxiv.org/abs/2304.12180
Publikováno v:
In Journal of Pain and Symptom Management July 2024 68(1):e1-e7
We categorize meta-learning evaluation into two settings: $\textit{in-distribution}$ [ID], in which the train and test tasks are sampled $\textit{iid}$ from the same underlying task distribution, and $\textit{out-of-distribution}$ [OOD], in which the
Externí odkaz:
http://arxiv.org/abs/2102.11503
Autor:
Li, Oscar, Sun, Jiankai, Yang, Xin, Gao, Weihao, Zhang, Hongyi, Xie, Junyuan, Smith, Virginia, Wang, Chong
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 private label information from the other party during split training, and
Externí odkaz:
http://arxiv.org/abs/2102.08504
Publikováno v:
NeurIPS 2020 Workshop on Meta-learning
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, these tasks are typically constructed by sampling a small number of
Externí odkaz:
http://arxiv.org/abs/2011.14048
Vision models are interpretable when they classify objects on the basis of features that a person can directly understand. Recently, methods relying on visual feature prototypes have been developed for this purpose. However, in contrast to how humans
Externí odkaz:
http://arxiv.org/abs/1906.10651
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
Advances in Neural Information Processing Systems 32 (NeurIPS 2019)
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. The mounting evidence for each of the classes helps us make our fina
Externí odkaz:
http://arxiv.org/abs/1806.10574