AIConfPaper
← Search

Carl Edward Rasmussen

15 accepted papers

2026

ExoPredicator: Learning Abstract Models of Dynamic Worlds for Robot Planning

Yichao Liang, Thanh Dat Nguyen, Cambridge Yang, Tianyang Li, Joshua B. Tenenbaum, Carl Edward Rasmussen +4
ICLR 2026poster

Long‑horizon embodied planning is challenging because the world does not only change through an agent’s actions: exogenous processes (e.g., water heating, dominoes cascading) unfold concurrently with the agent's actions. We propose a framework for abstract world models that jointly learns (i) symbol…

Cited by 0Source ↗Scholar ↗
2022

Sparse Gaussian Process Hyperparameters: Optimize or Integrate?

Vidhi Lalchand, Wessel Bruinsma, David R. Burt, Carl Edward Rasmussen
NeurIPS 2022accept

The kernel function and its hyperparameters are the central model selection choice in a Gaussian process (Rasmussen and Williams, 2006). Typically, the hyperparameters of the kernel are chosen by maximising the marginal likelihood, an approach known as Type-II maximum likelihood (ML-II). However, ML…

Cited by 9Source ↗PDF ↗Scholar ↗
2021

Kernel Identification Through Transformers

Fergus Simpson, Ian Davies, Vidhi Lalchand, Alessandro Vullo, Nicolas Durrande, Carl Edward Rasmussen
NeurIPS 2021poster

Kernel selection plays a central role in determining the performance of Gaussian Process (GP) models, as the chosen kernel determines both the inductive biases and prior support of functions under the GP prior. This work addresses the challenge of constructing custom kernel functions for high-dimens…

Cited by 13Source ↗PDF ↗code ↗Scholar ↗
2021

Marginalised Gaussian Processes with Nested Sampling

Fergus Simpson, Vidhi Lalchand, Carl Edward Rasmussen
NeurIPS 2021poster

Gaussian Process models are a rich distribution over functions with inductive biases controlled by a kernel function. Learning occurs through optimisation of the kernel hyperparameters using the marginal likelihood as the objective. This work proposes nested sampling as a means of marginalising kern…

Cited by 17Source ↗PDF ↗code ↗Scholar ↗
2020

Deep Structured Mixtures of Gaussian Processes

Martin Trapp, Robert Peharz, Franz Pernkopf, Carl Edward Rasmussen
AISTATS 2020poster

Gaussian Processes (GPs) are powerful non-parametric Bayesian regression models that allow exact posterior inference, but exhibit high computational and memory costs. In order to improve scalability of GPs, approximate posterior inference is frequently employed, where a prominent class of approximat…

Cited by 43Source ↗PDF ↗code ↗Scholar ↗
2020

Ensembling geophysical models with Bayesian Neural Networks

Ushnish Sengupta, Matt Amos, Scott Hosking, Carl Edward Rasmussen, Matthew Juniper, Paul Young
NeurIPS 2020poster

Ensembles of geophysical models improve projection accuracy and express uncertainties. We develop a novel data-driven ensembling strategy for combining geophysical models using Bayesian Neural Networks, which infers spatiotemporally varying model weights and bias while accounting for heteroscedastic…

Cited by 31Source ↗PDF ↗code ↗Scholar ↗
2020

Improving Sample-Efficiency in Reinforcement Learning for Dialogue Systems by Using Trainable-Action-Mask

Yen-Chen Wu, Bo-Hsiang Tseng, Carl Edward Rasmussen
ICASSP 2020accepted

By interacting with human and learning from reward signals, reinforcement learning is an ideal way to build conversational AI. Concerning the expenses of real-users' responses, improving sample-efficiency has been the key issue when applying reinforcement learning in real-world spoken dialogue syste…

Cited by 0Source ↗Scholar ↗
2019

Deep Convolutional Networks as shallow Gaussian Processes

Adrià Garriga-Alonso, Carl Edward Rasmussen, Laurence Aitchison
ICLR 2019poster

We show that the output of a (residual) CNN with an appropriate prior over the weights and biases is a GP in the limit of infinitely many convolutional filters, extending similar results for dense networks. For a CNN, the equivalent kernel can be computed exactly and, unlike "deep kernels", has very…

Cited by 321Source ↗PDF ↗Scholar ↗
2019

Overcoming Mean-Field Approximations in Recurrent Gaussian Process Models

Alessandro Davide Ialongo, Mark Van Der Wilk, James Hensman, Carl Edward Rasmussen
ICML 2019oral

We identify a new variational inference scheme for dynamical systems whose transition function is modelled by a Gaussian process. Inference in this setting has either employed computationally intensive MCMC methods, or relied on factorisations of the variational posterior. As we demonstrate in our e…

Cited by 38Source ↗PDF ↗code ↗Scholar ↗
2018

PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos

Paavo Parmas, Carl Edward Rasmussen, Jan Peters, Kenji Doya
ICML 2018oral

Previously, the exploding gradient problem has been explained to be central in deep learning and model-based reinforcement learning, because it causes numerical issues and instability in optimization. Our experiments in model-based reinforcement learning imply that the problem is not just a numerica…

Cited by 96Source ↗PDF ↗code ↗Scholar ↗
2017

Data-Efficient Reinforcement Learning in Continuous State-Action Gaussian-POMDPs

Rowan McAllister, Carl Edward Rasmussen
NeurIPS 2017poster

We present a data-efficient reinforcement learning method for continuous state-action systems under significant observation noise. Data-efficient solutions under small noise exist, such as PILCO which learns the cartpole swing-up task in 30s. PILCO evaluates policies by planning state-trajectories u…

Cited by 47Source ↗PDF ↗Scholar ↗
2016

Understanding Probabilistic Sparse Gaussian Process Approximations

Matthias Bauer, Mark van der Wilk, Carl Edward Rasmussen
NeurIPS 2016poster

Good sparse approximations are essential for practical inference in Gaussian Processes as the computational cost of exact methods is prohibitive for large datasets. The Fully Independent Training Conditional (FITC) and the Variational Free Energy (VFE) approximations are two recent popular methods.…

Cited by 286Source ↗PDF ↗Scholar ↗