
Structured secondorder methods via natural gradient descent
In this paper, we propose new structured secondorder methods and struct...
read it

The Bayesian Learning Rule
We show that many machinelearning algorithms are specific instances of ...
read it

KnowledgeAdaptation Priors
Humans and animals have a natural ability to quickly adapt to their surr...
read it

Beyond Target Networks: Improving Deep Qlearning with Functional Regularization
Target networks are at the core of recent success in Reinforcement Learn...
read it

Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning
Marginallikelihood based modelselection, even though promising, is rar...
read it

Tractable structured natural gradient descent using local parameterizations
Naturalgradient descent on structured parameter spaces (e.g., lowrank ...
read it

Fast Variational Learning in StateSpace Gaussian Process Models
Gaussian process (GP) regression with 1D inputs can often be performed i...
read it

Continual Deep Learning by Functional Regularisation of Memorable Past
Continually learning new skills is important for intelligent systems, ye...
read it

Training Binary Neural Networks using the Bayesian Learning Rule
Neural networks with binary weights are computationefficient and hardwa...
read it

Handling the PositiveDefinite Constraint in the Bayesian Learning Rule
Bayesian learning rule is a recently proposed variational inference meth...
read it

Stein's Lemma for the Reparameterization Trick with Exponential Family Mixtures
Stein's method (Stein, 1973; 1981) is a powerful tool for statistical ap...
read it

VILD: Variational Imitation Learning with Diversequality Demonstrations
The goal of imitation learning (IL) is to learn a good policy from high...
read it

Fast and Simple NaturalGradient Variational Inference with Mixture of Exponentialfamily Approximations
Naturalgradient methods enable fast and simple algorithms for variation...
read it

Practical Deep Learning with Bayesian Principles
Bayesian methods promise to fix many shortcomings of deep learning, but ...
read it

Approximate Inference Turns Deep Networks into Gaussian Processes
Deep neural networks (DNN) and Gaussian processes (GP) are two powerful ...
read it

Scalable Training of Inference Networks for GaussianProcess Models
Inference in Gaussian process (GP) models is computationally challenging...
read it

A Generalization Bound for Online Variational Inference
Bayesian inference provides an attractive onlinelearning framework to a...
read it

TDRegularized ActorCritic Methods
Actorcritic methods can achieve incredible performance on difficult rei...
read it

SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient
Uncertainty estimation in large deeplearning models is a computationall...
read it

Fast yet Simple NaturalGradient Descent for Variational Inference in Complex Models
Bayesian inference plays an important role in advancing machine learning...
read it

Fast and Scalable Bayesian Deep Learning by WeightPerturbation in Adam
Uncertainty computation in deep learning is essential to design robust a...
read it

LowRank Tensor Decomposition via Multiple Reshaping and Reordering Operations
Tensor decomposition has been widely applied to find lowrank representa...
read it

Variational Message Passing with Structured Inference Networks
Recent efforts on combining deep models with probabilistic graphical mod...
read it

Vprop: Variational Inference using RMSprop
Many computationallyefficient methods for Bayesian deep learning rely o...
read it

Variational AdaptiveNewton Method for Explorative Learning
We present the Variational Adaptive Newton (VAN) method which is a black...
read it

Faster Stochastic Variational Inference using ProximalGradient Methods with General Divergence Functions
Several recent works have explored stochastic gradient methods for varia...
read it

UAVs using Bayesian Optimization to Locate WiFi Devices
We address the problem of localizing noncollaborative WiFi devices in a...
read it

Fast Dual Variational Inference for NonConjugate LGMs
Latent Gaussian models (LGMs) are widely used in statistics and machine ...
read it