[HTML][HTML] Strategies and principles of distributed machine learning on big data
The rise of big data has led to new demands for machine learning (ML) systems to learn
complex models, with millions to billions of parameters, that promise adequate capacity to digest …
complex models, with millions to billions of parameters, that promise adequate capacity to digest …
On unifying deep generative models
Deep generative models have achieved impressive success in recent years. Generative
Adversarial Networks (GANs) and Variational Autoencoders (VAEs), as emerging families for …
Adversarial Networks (GANs) and Variational Autoencoders (VAEs), as emerging families for …
Toward controlled generation of text
Generic generation and manipulation of text is challenging and has limited success compared
to recent deep generative modeling in visual domain. This paper aims at generating …
to recent deep generative modeling in visual domain. This paper aims at generating …
[PDF][PDF] Feature selection for high-dimensional genomic microarray data
We report on the successful application of feature selection methods to a classification
problem in molecular biology involving only 72 data points in a 7130 dimensional space. Our …
problem in molecular biology involving only 72 data points in a 7130 dimensional space. Our …
Self-challenging improves cross-domain generalization
Convolutional Neural Networks (CNN) conduct image classification by activating dominant
features that correlated with labels. When the training and testing data are under similar …
features that correlated with labels. When the training and testing data are under similar …
Deep kernel learning
We introduce scalable deep kernels, which combine the structural properties of deep
learning architectures with the non-parametric flexibility of kernel methods. Specifically, we …
learning architectures with the non-parametric flexibility of kernel methods. Specifically, we …
More effective distributed ml via a stale synchronous parallel parameter server
We propose a parameter server system for distributed ML, which follows a Stale Synchronous
Parallel (SSP) model of computation that maximizes the time computational workers …
Parallel (SSP) model of computation that maximizes the time computational workers …
Dags with no tears: Continuous optimization for structure learning
…, PK Ravikumar, EP Xing - Advances in neural …, 2018 - proceedings.neurips.cc
Estimating the structure of directed acyclic graphs (DAGs, also known as Bayesian networks)
is a challenging problem since the search space of DAGs is combinatorial and scales …
is a challenging problem since the search space of DAGs is combinatorial and scales …
Tree-guided group lasso for multi-response regression with structured sparsity, with an application to eQTL mapping
The balanced weighting scheme of tree lasso and additional experimental results. We prove
that the weighting scheme of the tree-lasso penalty achieves a balanced penalization of all …
that the weighting scheme of the tree-lasso penalty achieves a balanced penalization of all …
Neural architecture search with bayesian optimisation and optimal transport
Bayesian Optimisation (BO) refers to a class of methods for global optimisation of a function
f which is only accessible via point evaluations. It is typically used in settings where f is …
f which is only accessible via point evaluations. It is typically used in settings where f is …