Big Learning with Bayesian Methods
arXiv:1411.6370
Abstract
Explosive growth in data and availability of cheap computing resources have sparked increasing interest in Big learning, an emerging subfield that studies scalable machine learning algorithms, systems, and applications with Big Data. Bayesian methods represent one important class of statistic methods for machine learning, with substantial recent developments on adaptive, flexible and scalable Bayesian learning. This article provides a survey of the recent advances in Big learning with Bayesian methods, termed Big Bayesian Learning, including nonparametric Bayesian methods for adaptively inferring model complexity, regularized Bayesian inference for improving the flexibility via posterior regularization, and scalable algorithms and systems based on stochastic subsampling and distributed computing for dealing with large-scale applications.
21 pages, 6 figures
References in corpus (27)
- Auto-Encoding Variational Bayes
- Practical Bayesian Optimization of Machine Learning Algorithms
- Caffe: Convolutional Architecture for Fast Feature Embedding
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning
- Supervised Topic Models
- Stochastic Gradient Hamiltonian Monte Carlo
- GraphLab: A New Framework For Parallel Machine Learning
- A General Framework for the Parametrization of Hierarchical Models
- Bayesian variable selection with shrinking and diffusing priors
- Variational Bayesian Inference with Stochastic Search
- Parallelizing MCMC via Weierstrass Sampler
- Automatic Construction and Natural-Language Description of Nonparametric Regression Models
- Max-Margin Nonparametric Latent Feature Models for Link Prediction
- Efficient Gradient-Based Inference through Transformations between Bayes Nets and Neural Nets
- Ergodicity of Approximate MCMC Chains with Applications to Large Data Sets
- Online Bayesian Passive-Aggressive Learning
- Peacock: Learning Long-Tail Topic Features for Industrial Applications
- Automated Machine Learning on Big Data using Stochastic Algorithm Tuning
- Consistency and fluctuations for stochastic gradient Langevin dynamics
- Primitives for Dynamic Big Model Parallelism
- Bayesian Conditional Density Filtering
- Accelerating Metropolis-Hastings algorithms: Delayed acceptance with prefetching
- Petuum: A New Platform for Distributed Machine Learning on Big Data
- Model-Parallel Inference for Big Topic Models
- Exploiting the Statistics of Learning and Inference
- Fast Hamiltonian Monte Carlo Using GPU Computing