no code implementations • ICML 2020 • Yingyi Ma, Vignesh Ganapathiraman, Yao-Liang Yu, Xinhua Zhang
Invariance (defined in a general sense) has been one of the most effective priors for representation learning.
no code implementations • ICML 2018 • Vignesh Ganapathiraman, Zhan Shi, Xinhua Zhang, Yao-Liang Yu
Latent prediction models, exemplified by multi-layer networks, employ hidden variables that automate abstract feature discovery.
no code implementations • NeurIPS 2016 • Vignesh Ganapathiraman, Xinhua Zhang, Yao-Liang Yu, Junfeng Wen
Unsupervised learning of structured predictors has been a long standing pursuit in machine learning.