The computational cost of training with softmax cross entropy loss grows linearly with the
number of classes. For the settings where a large number of classes are involved, a …

We consider the problem of retrieving the most relevant labels for a given input when the
size of the output space is very large. Retrieval methods are modeled as set-valued …

Categorical distributions are ubiquitous in machine learning, eg, in classification, language
models, and recommendation systems. However, when the number of possible outcomes is …

We present ADMM-Softmax, an alternating direction method of multipliers (ADMM) for
solving multinomial logistic regression (MLR) problems. Our method is geared toward …

Recent neural network and language models rely on softmax distributions with an extremely
large number of categories. Since calculating the softmax normalizing constant in this …

The ability to collect large amounts of data with relative ease has given rise to new
opportunities for scientific discovery. It has led to a new class of large-scale parameter …

Sparse Multinomial Logistic Regression (SMLR) is widely used in the field of image
classification, multi-class object recognition, and so on, because it has the function of …

Abstract Machine learning is used daily in areas such as security, medical care, and
financial systems. Failures in such institutions can have dire consequences. Adversarial …

The combination of the re-parameterization trick with the use of variational auto-encoders
has caused a sensation in Bayesian deep learning, allowing the training of realistic …

Sparse multinomial logistic regression (SMLR) is widely used in image classification and
text classification due to its feature selection and probabilistic output. However, the …