Relax: Composable Abstractions for End-to-End Dynamic Machine Learning

no code implementations • 1 Nov 2023 • Ruihang Lai, Junru Shao, Siyuan Feng, Steven S. Lyubomirsky, Bohan Hou, Wuwei Lin, Zihao Ye, Hongyi Jin, Yuchen Jin, Jiawei Liu, Lesheng Jin, Yaxing Cai, Ziheng Jiang, Yong Wu, Sunghyun Park, Prakalp Srivastava, Jared G. Roesch, Todd C. Mowry, Tianqi Chen

Dynamic shape computations have become critical in modern machine learning workloads, especially in emerging large language models.

AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the Fly

1 code implementation • ICLR 2021 • Yuchen Jin, Tianyi Zhou, Liangyu Zhao, Yibo Zhu, Chuanxiong Guo, Marco Canini, Arvind Krishnamurthy

This mutual-training process between BO and the loss-prediction model allows us to limit the training steps invested in the BO search.

Image Classification Machine Translation +1

Progressive transfer learning for low frequency data prediction in full waveform inversion

no code implementations • 20 Dec 2019 • Wenyi Hu, Yuchen Jin, Xuqing Wu, Jiefu Chen

For the purpose of effective suppression of the cycle-skipping phenomenon in full waveform inversion (FWI), we developed a Deep Neural Network (DNN) approach to predict the absent low-frequency components by exploiting the implicit relation connecting the low-frequency and high-frequency data through the subsurface geological and geophysical properties.

Transfer Learning