248 citations · 640 across the 8 of their papers we have counts for
8 papers
Inconsistency, Instability, and Generalization Gap of Deep Neural Network Training
Rie Johnson, Tong Zhang
As deep neural networks are highly expressive, it is important to find solutions with small generalization gap (the difference between the performance on the training data and unse…
Guided Learning of Nonconvex Models through Successive Functional Gradient Optimization
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…
Composite Functional Gradient Learning of Generative Adversarial Models
Rie Johnson, Tong Zhang
This paper first presents a theory for generative adversarial methods that does not rely on the traditional minimax formulation. It shows that with a strong discriminator, a good g…
Convolutional Neural Networks for Text Categorization: Shallow Word-level vs. Deep Character-level
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 th…
Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings
Rie Johnson, Tong Zhang
One-hot CNN (convolutional neural network) has been shown to be effective for text categorization (Johnson & Zhang, 2015). We view it as a special case of a general framework which…
Semi-supervised Convolutional Neural Networks for Text Categorization via Region Embedding
Rie Johnson, Tong Zhang
This paper presents a new semi-supervised framework with convolutional neural networks (CNNs) for text categorization. Unlike the previous approaches that rely on word embeddings,…
Effective Use of Word Order for Text Categorization with Convolutional Neural Networks
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. This paper studies CNN on text ca…
Learning Nonlinear Functions Using Regularized Greedy Forest
Rie Johnson, Tong Zhang
We consider the problem of learning a forest of nonlinear decision rules with general loss functions. The standard methods employ boosted decision trees such as Adaboost for expone…