Many modern unsupervised or semi-supervised machine learning algorithms rely on
Bayesian probabilistic models. These models are usually intractable and thus require …

We propose a new regularization method based on virtual adversarial loss: a new measure
of local smoothness of the conditional label distribution given input. Virtual adversarial loss …

We introduce the Kronecker factored online Laplace approximation for overcoming
catastrophic forgetting in neural networks. The method is grounded in a Bayesian online …

We present SDA-Bayes, a framework for (S) treaming,(D) istributed,(A) synchronous
computation of a Bayesian posterior. The framework makes streaming updates to the …

Continual Learning (CL) algorithms incrementally learn a predictor or representation across
multiple sequentially observed tasks. Designing CL algorithms that perform reliably and …

To optimize a neural network one often thinks of optimizing its parameters, but it is ultimately
a matter of optimizing the function that maps inputs to outputs. Since a change in the …

This work addresses continual learning for non-stationary data, using Bayesian neural
networks and memory-based online variational Bayes. We represent the posterior …

Sequential Bayesian inference over predictive functions is a natural framework for continual
learning from streams of data. However, applying it to neural networks has proved …

Locally weighted regression (LWR) was created as a nonparametric method that can
approximate a wide range of functions, is computationally efficient, and can learn continually …

We consider the problem of online learning in the presence of distribution shifts that occur at
an unknown rate and of unknown intensity. We derive a new Bayesian online inference …