Bayesian

78 results found

Sort

Bayesian counterfactual risk minimization

Ben London, Ted Sandler

ICML 2019

2019

We present a Bayesian view of counterfactual risk minimization (CRM) for offline learning from logged bandit feedback. Using PACBayesian analysis, we derive a new generalization bound for the truncated inverse propensity score estimator. We apply the bound to a class of Bayesian policies, which motivates a novel, potentially data-dependent, regularization technique for CRM. Experimental results indicate

Machine learning
On acquisition functions for active multi-source Bayesian quadrature

Alexandra Gessner, Maren Mahsereci, Javier González

NeurIPS 2018, UAI 2019

2018

Bayesian quadrature (BQ) is a sample efficient probabilistic numerical method to solve integrals of expensive-to-evaluate black-box functions, yet so far, active BQ learning schemes focus merely on the integrand itself as information source, and do not allow for information transfer from cheaper, related functions. Here, we set the scene for active learning in BQ when multiple related information sources

Machine learning
Facilitating Bayesian continual learning by natural gradients and Stein gradients

Yu Chen, Tom Diethe, Neil Lawrence

NeurIPS 2018

2018

Continual learning aims to enable machine learning models to learn a general solution space for past and future tasks in a sequential manner. Conventional models tend to forget the knowledge of previous tasks while learning a new task, a phenomenon known as catastrophic forgetting. When using Bayesian models in continual learning, knowledge from previous tasks can be retained in two ways: (i) posterior

Machine learning
β-BNN: A rate-distortion perspective on Bayesian neural networks

Shell Hu, Andreas Damianou, Pablo Garcia Moreno

NeurIPS 2018

2018

We propose an alternative training framework for Bayesian neural networks (BNNs), which is motivated by viewing the Bayesian model for supervised learning as an autoencoder for data transmission. Then, a natural objective can be invoked from the rate-distortion theory. Specifically, we end up minimizing the mutual information between the weights and the dataset with a constraint that the negative log-likelihood

Machine learning
A PAC-Bayesian analysis of randomized learning with application to stochastic gradient descent

Ben London

NeurIPS 2017

2017

We study the generalization error of randomized learning algorithms—focusing on stochastic gradient descent (SGD)—using a novel combination of PAC-Bayes and algorithmic stability. Importantly, our generalization bounds hold for all posterior distributions on an algorithm’s random hyperparameters, including distributions that depend on the training data. This inspires an adaptive sampling algorithm for SGD

Machine learning
Kalman Folding 5: Non-linear models and the EKF

Brian Beckman

ACM 2016

2016

We exhibit a foldable Extended Kalman Filter that internally integrates non-linear equations of motion with a nested fold of generic integrators over lazy streams in constant memory. Functional form allows us to switch integrators easily and to diagnose filter divergence accurately, achieving orders of magnitude better speed than the source example from the literature. As with all Kalman folds, we can move

Cloud and systems
Adaptive, personalized diversity for visual discovery

Choon Hui Teo, Houssam Nassif, Daniel N. Hill, Sriram Srinivasan, Mitchell Goodman, Vijai Mohan, S. V. N. Vishwanathan

RecSys 2016

2016

Search queries are appropriate when users have explicit intent, but they perform poorly when the intent is difficult to express or if the user is simply looking to be inspired. Visual browsing systems allow e-commerce platforms to address these scenarios while offering the user an engaging shopping experience. Here we explore extensions in the direction of adaptive personalization and item diversification

Search and information retrieval
Bayesian intermittent demand forecasting for large inventories

Matthias Seeger, David Salinas, Valentin Flunkert

NeurIPS 2016

2016

We present a scalable and robust Bayesian method for demand forecasting in the context of a large e-commerce platform, paying special attention to intermittent and bursty target statistics. Inference is approximated by the Newton-Raphson algorithm, reduced to linear-time Kalman smoothing, which allows us to operate on several orders of magnitude larger problems than previous related work. In a study on

Operations research and optimization

...

Bayesian

Work with us