Partition-based methods are increasingly-used in extreme multi-label
cla...
Many optimizers have been proposed for training deep neural networks, an...
Generative adversarial networks (GAN) have shown remarkable results in i...
Metric learning is an important family of algorithms for classification ...
Among multiple ways of interpreting a machine learning model, measuring ...
We introduce a new way of learning to encode position information for
no...
A novel gradient boosting framework is proposed where shallow neural net...
In this paper, we study the robustness of graph convolutional networks
(...
In this paper, we proposed a general framework for data poisoning attack...
We study the problem of computing the minimum adversarial perturbation o...
Neural Ordinary Differential Equation (Neural ODE) has been proposed as ...
Graph convolutional network (GCN) has been successfully applied to many
...
We present a new algorithm to train a robust neural network against
adve...
Trust region and cubic regularization methods have demonstrated good
per...
In this paper we study a family of variance reduction methods with rando...
In this paper, we are interested in two seemingly different concepts:
ad...
Recent studies have revealed the vulnerability of deep neural networks -...
We propose a fast proximal Newton-type algorithm for minimizing regulari...