
Variational Integrator Networks for Physically Meaningful Embeddings
Learning workable representations of dynamical systems is becoming an in...
read it

Deep Gaussian Processes with ImportanceWeighted Variational Inference
Deep Gaussian processes (DGPs) can model complex marginal densities as w...
read it

Differentially Private Empirical Risk Minimization with SparsityInducing Norms
Differential privacy is concerned about the prediction quality while mea...
read it

Efficiently sampling functions from Gaussian process posteriors
Gaussian processes are the gold standard for many realworld modeling pr...
read it

A Brief Survey of Deep Reinforcement Learning
Deep reinforcement learning is poised to revolutionise the field of AI a...
read it

DataEfficient Reinforcement Learning with Probabilistic Model Predictive Control
Trialanderror based reinforcement learning (RL) has seen rapid advance...
read it

Identification of Gaussian Process State Space Models
The Gaussian process state space model (GPSSM) is a nonlinear dynamical...
read it

Neural Embeddings of Graphs in Hyperbolic Space
Neural embeddings have been used with great success in Natural Language ...
read it

Customer Lifetime Value Prediction Using Embeddings
We describe the Customer LifeTime Value (CLTV) prediction system deploye...
read it

Accelerating the BSM interpretation of LHC data with machine learning
The interpretation of Large Hadron Collider (LHC) data in the framework ...
read it

The reparameterization trick for acquisition functions
Bayesian optimization is a sampleefficient approach to solving global o...
read it

Probabilistic Inference of Twitter Users' Age based on What They Follow
Twitter provides an open and rich source of data for studying human beha...
read it

RealTime Community Detection in Large Social Networks on a Laptop
For a broad range of research, governmental and commercial applications ...
read it

Bayesian Optimization with Dimension Scheduling: Application to Biological Systems
Bayesian Optimization (BO) is a dataefficient method for global blackb...
read it

Gaussian Processes for DataEfficient Learning in Robotics and Control
Autonomous learning has been a promising direction in control and roboti...
read it

Distributed Gaussian Processes
To scale Gaussian processes (GPs) to large data sets we introduce the ro...
read it

From Pixels to Torques: Policy Learning with Deep Dynamical Models
Dataefficient learning in continuous stateaction spaces using very hig...
read it

Hierarchical MixtureofExperts Model for LargeScale Gaussian Process Regression
We propose a practical and scalable Gaussian process model for largesca...
read it

Learning deep dynamical models from image pixels
Modeling dynamical systems is important in many disciplines, e.g., contr...
read it

Manifold Gaussian Processes for Regression
Offtheshelf Gaussian Process (GP) covariance functions encode smoothne...
read it

DataEfficient Learning of Feedback Policies from Image Pixels using Deep Dynamical Models
Dataefficient reinforcement learning (RL) in continuous stateaction sp...
read it

MultiTask Policy Search
Learning policies that generalize across multiple tasks is an important ...
read it

Expectation Propagation in Gaussian Process Dynamical Systems: Extended Version
Rich and complex timeseries data, such as those generated from engineer...
read it

Robust Filtering and Smoothing with Gaussian Processes
We propose a principled algorithm for robust Bayesian filtering and smoo...
read it

Meta Reinforcement Learning with Latent Variable Gaussian Processes
Data efficiency, i.e., learning from small data sets, is critical in man...
read it

Design of Experiments for Model Discrimination Hybridising Analytical and DataDriven Approaches
Healthcare companies must submit pharmaceutical drugs or medical devices...
read it

Maximizing acquisition functions for Bayesian optimization
Bayesian optimization is a sampleefficient approach to global optimizat...
read it