Sampled softmax with random fourier features
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 …
number of classes. For the settings where a large number of classes are involved, a …
Stochastic negative mining for learning with large output spaces
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 …
size of the output space is very large. Retrieval methods are modeled as set-valued …
Augment and reduce: Stochastic inference for large categorical distributions
Categorical distributions are ubiquitous in machine learning, eg, in classification, language
models, and recommendation systems. However, when the number of possible outcomes is …
models, and recommendation systems. However, when the number of possible outcomes is …
ADMM-Softmax: an ADMM approach for multinomial logistic regression
We present ADMM-Softmax, an alternating direction method of multipliers (ADMM) for
solving multinomial logistic regression (MLR) problems. Our method is geared toward …
solving multinomial logistic regression (MLR) problems. Our method is geared toward …
Unbiased scalable softmax optimization
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 …
large number of categories. Since calculating the softmax normalizing constant in this …
Large-scale parameter estimation in geophysics and machine learning
SW Fung - 2019 - search.proquest.com
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 …
opportunities for scientific discovery. It has led to a new class of large-scale parameter …
Distributed parallel sparse multinomial logistic regression
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 …
classification, multi-class object recognition, and so on, because it has the function of …
Soft labels and supervised image classification
S Tyrväinen - 2021 - open.library.ubc.ca
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 …
financial systems. Failures in such institutions can have dire consequences. Adversarial …
Reconsidering analytical variational bounds for output layers of deep networks
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 …
has caused a sensation in Bayesian deep learning, allowing the training of realistic …
Communication‐efficient distributed large‐scale sparse multinomial logistic regression
D Lei, J Huang, H Chen, J Li… - … and Computation: Practice …, 2023 - Wiley Online Library
Sparse multinomial logistic regression (SMLR) is widely used in image classification and
text classification due to its feature selection and probabilistic output. However, the …
text classification due to its feature selection and probabilistic output. However, the …