no code implementations • ICML 2020 • Rie Johnson, Tong Zhang
This paper presents a framework of successive functional gradient optimization for training nonconvex models such as neural networks, where training is driven by mirror descent in a function space.
no code implementations • ICML 2018 • Rie Johnson, Tong Zhang
This paper first presents a theory for generative adversarial methods that does not rely on the traditional minimax formulation.
1 code implementation • ACL 2017 • Rie Johnson, Tong Zhang
This paper proposes a low-complexity word-level deep convolutional neural network (CNN) architecture for text categorization that can efficiently represent long-range associations in text.
Ranked #2 on Sentiment Analysis on Amazon Review Full
no code implementations • 31 Aug 2016 • Rie Johnson, Tong Zhang
This paper reports the performances of shallow word-level convolutional neural networks (CNN), our earlier work (2015), on the eight datasets with relatively large training data that were used for testing the very deep character-level CNN in Conneau et al. (2016).
no code implementations • 7 Feb 2016 • Rie Johnson, Tong Zhang
The best results were obtained by combining region embeddings in the form of LSTM and convolution layers trained on unlabeled data.
Ranked #1 on Text Classification on RCV1
no code implementations • NeurIPS 2015 • Rie Johnson, Tong Zhang
This paper presents a new semi-supervised framework with convolutional neural networks (CNNs) for text categorization.
Ranked #1000000000 on Text Classification on IMDb
4 code implementations • HLT 2015 • Rie Johnson, Tong Zhang
Convolutional neural network (CNN) is a neural network that can make use of the internal structure of data such as the 2D structure of image data.
Ranked #29 on Sentiment Analysis on IMDb
no code implementations • NeurIPS 2013 • Rie Johnson, Tong Zhang
Stochastic gradient descent is popular for large scale optimization but has slow convergence asymptotically due to the inherent variance.
1 code implementation • 5 Sep 2011 • Rie Johnson, Tong Zhang
We consider the problem of learning a forest of nonlinear decision rules with general loss functions.