Search Results for author:
Found 64 papers, 25 papers with code
Iterated INLA for State and Parameter Estimation in Nonlinear Dynamical Systems
Data assimilation (DA) methods use priors arising from differential equations to robustly interpolate and extrapolate data.
Plasma Surrogate Modelling using Fourier Neural Operators
Predicting plasma evolution within a Tokamak reactor is crucial to realizing the goal of sustainable fusion.
Gaussian Processes on Cellular Complexes
In this paper, we go beyond this dyadic setting and consider polyadic relations that include interactions between vertices, edges and one of their generalisations, known as cells.
A Unifying Variational Framework for Gaussian Process Motion Planning
To control how a robot moves, motion planning algorithms must compute paths in high-dimensional state spaces while accounting for physical constraints related to motors and joints, generating smooth and stable motions, avoiding obstacles, and preventing collisions.
Faster Training of Neural ODEs Using Gauß-Legendre Quadrature
In this paper, we propose an alternative way to speed up the training of neural ODEs.
Grasp Transfer based on Self-Aligning Implicit Representations of Local Surfaces
This work addresses the problem of transferring a grasp experience or a demonstration to a novel object that shares shape similarities with objects the robot has previously encountered.
On Combining Expert Demonstrations in Imitation Learning via Optimal Transport
One of the key approaches to IL is to define a distance between agent and expert and to find an agent policy that minimizes that distance.
Implicit regularisation in stochastic gradient descent: from single-objective to two-player games
In this work, we provide a novel approach to use BEA, and show how our approach can be used to construct continuous-time flows with vector fields that can be written as gradients.
Investigating the Edge of Stability Phenomenon in Reinforcement Learning
Recent progress has been made in understanding optimisation dynamics in neural networks trained with full-batch gradient descent with momentum with the uncovering of the edge of stability phenomenon in supervised learning.
Actually Sparse Variational Gaussian Processes
For large datasets, sparse GPs reduce these demands by conditioning on a small set of inducing variables designed to summarise the data.
Finetuning from Offline Reinforcement Learning: Challenges, Trade-offs and Practical Solutions
While offline RL algorithms can in principle be used for finetuning, in practice, their online performance improves slowly.
Queer In AI: A Case Study in Community-Led Participatory AI
We present Queer in AI as a case study for community-led participatory design in AI.
Optimal Transport for Offline Imitation Learning
In this paper, we introduce Optimal Transport Reward labeling (OTR), an algorithm that assigns rewards to offline trajectories, with a few high-quality demonstrations.
Short-term Prediction and Filtering of Solar Power Using State-Space Gaussian Processes
Short-term forecasting of solar photovoltaic energy (PV) production is important for powerplant management.
One-Shot Transfer of Affordance Regions? AffCorrs!
In this work, we tackle one-shot visual search of object parts.
Vector-valued Gaussian Processes on Riemannian Manifolds via Gauge Independent Projected Kernels
Gaussian processes are machine learning models capable of learning unknown functions in a way that represents uncertainty, thereby facilitating construction of optimal decision-making systems.
Gaussian Process Sampling and Optimization with Approximate Upper and Lower Bounds
More specifically, we propose the first use of such bounds to improve Gaussian process (GP) posterior sampling and Bayesian optimization (BO).
Imitation Learning from Pixel Observations for Continuous Control
In this setting, we explore recipes for imitation learning based on adversarial learning and optimal transport.
Learning to Transfer: A Foliated Theory
Learning to transfer considers learning solutions to tasks in a such way that relevant knowledge can be transferred from known task solutions to new, related tasks.
The Graph Cut Kernel for Ranked Data
Many algorithms for ranked data become computationally intractable as the number of objects grows due to the complex geometric structure induced by rankings.
Learning Contact Dynamics using Physically Structured Neural Networks
Learning physically structured representations of dynamical systems that include contact between different objects is an important problem for learning-based approaches in robotics.
Healing Products of Gaussian Processes
Gaussian processes (GPs) are nonparametric Bayesian models that have been applied to regression and classification problems.
Sliced Multi-Marginal Optimal Transport
To construct this distance, we introduce a characterization of the one-dimensional multi-marginal Kantorovich problem and use it to highlight a number of properties of the sliced multi-marginal Wasserstein distance.
Using Gaussian Processes to Design Dynamic Experiments for Black-Box Model Discrimination under Uncertainty
Typically, several rival mechanistic models can explain the available data, so design of dynamic experiments for model discrimination helps optimally collect additional data by finding experimental settings that maximise model prediction divergence.
Cauchy-Schwarz Regularized Autoencoder
To perform efficient inference for GMM priors, we introduce a new constrained objective based on the Cauchy-Schwarz divergence, which can be computed analytically for GMMs.
GENNI: Visualising the Geometry of Equivalences for Neural Network Identifiability
We propose an efficient algorithm to visualise symmetries in neural networks.
Pathwise Conditioning of Gaussian Processes
As Gaussian processes are used to answer increasingly complex questions, analytic solutions become scarcer and scarcer.
Matérn Gaussian Processes on Graphs
Gaussian processes are a versatile framework for learning unknown functions in a manner that permits one to utilize prior information about their properties.
A Foliated View of Transfer Learning
Transfer learning considers a learning process where a new task is solved by transferring relevant knowledge from known solutions to related tasks.
Probabilistic Active Meta-Learning
However, this setting does not take into account the sequential nature that naturally arises when training a model from scratch in real-life: how do we collect a set of training tasks in a data-efficient manner?
Estimating Barycenters of Measures in High Dimensions
Barycentric averaging is a principled way of summarizing populations of measures.
Stochastic Differential Equations with Variational Wishart Diffusions
We present a Bayesian non-parametric way of inferring stochastic differential equations for both regression tasks and continuous-time dynamical modelling.
Aligning Time Series on Incomparable Spaces
Dynamic time warping (DTW) is a useful method for aligning, comparing and combining time series, but it requires them to live in comparable spaces.
Matérn Gaussian processes on Riemannian manifolds
Gaussian processes are an effective model class for learning unknown functions, particularly in settings where accurately representing predictive uncertainty is of key importance.
Efficiently Sampling Functions from Gaussian Process Posteriors
Gaussian processes are the gold standard for many real-world modeling problems, especially in cases where a model's success hinges upon its ability to faithfully represent predictive uncertainty.
Variational Integrator Networks for Physically Structured Embeddings
Learning workable representations of dynamical systems is becoming an increasingly important problem in a number of application areas.
Deep Gaussian Processes with Importance-Weighted Variational Inference
Deep Gaussian processes (DGPs) can model complex marginal densities as well as complex mappings.
Differentially Private Empirical Risk Minimization with Sparsity-Inducing Norms
This is the first work that analyzes the dual optimization problems of risk minimization problems in the context of differential privacy.
GPdoemd: a Python package for design of experiments for model discrimination
Given rival mathematical models and an initial experimental data set, optimal design of experiments suggests maximally informative experimental observations that maximise a design criterion weighted by prediction uncertainty.
Maximizing acquisition functions for Bayesian optimization
Bayesian optimization is a sample-efficient approach to global optimization that relies on theoretically motivated value heuristics (acquisition functions) to guide its search process.
Meta Reinforcement Learning with Latent Variable Gaussian Processes
Learning from small data sets is critical in many practical applications where data collection is time consuming or expensive, e. g., robotics, animal experiments or drug design.
Design of Experiments for Model Discrimination Hybridising Analytical and Data-Driven Approaches
Healthcare companies must submit pharmaceutical drugs or medical devices to regulatory bodies before marketing new technology.
Hybed: Hyperbolic Neural Graph Embedding
Neural embeddings have been used with great success in Natural Language Processing (NLP) where they provide compact representations that encapsulate word similarity and attain state-of-the-art performance in a range of linguistic tasks.
The reparameterization trick for acquisition functions
Bayesian optimization is a sample-efficient approach to solving global optimization problems.
A Brief Survey of Deep Reinforcement Learning
Deep reinforcement learning is poised to revolutionise the field of AI and represents a step towards building autonomous systems with a higher level understanding of the visual world.
Data-Efficient Reinforcement Learning with Probabilistic Model Predictive Control
Trial-and-error based reinforcement learning (RL) has seen rapid advancements in recent times, especially with the advent of deep neural networks.
Identification of Gaussian Process State Space Models
To address this challenge, we impose a structured Gaussian variational posterior distribution over the latent states, which is parameterised by a recognition model in the form of a bi-directional recurrent neural network.
Neural Embeddings of Graphs in Hyperbolic Space
Neural embeddings have been used with great success in Natural Language Processing (NLP).
Customer Lifetime Value Prediction Using Embeddings
We detail the system deployed at ASOS and show that learning feature representations is a promising extension to the state of the art in CLTV modelling.
Accelerating the BSM interpretation of LHC data with machine learning
The interpretation of Large Hadron Collider (LHC) data in the framework of Beyond the Standard Model (BSM) theories is hampered by the need to run computationally expensive event generators and detector simulators.
Probabilistic Inference of Twitter Users' Age based on What They Follow
Enhancing Twitter data with user ages would advance our ability to study social network structures, information flows and the spread of contagions.
Real-Time Community Detection in Large Social Networks on a Laptop
For a broad range of research, governmental and commercial applications it is important to understand the allegiances, communities and structure of key players in society.
Bayesian Optimization with Dimension Scheduling: Application to Biological Systems
But experiments may be less expensive than BO methods assume: In some simulation models, we may be able to conduct multiple thousands of experiments in a few hours, and the computational burden of BO is no longer negligible compared to experimentation time.
Data-Efficient Learning of Feedback Policies from Image Pixels using Deep Dynamical Models
We consider a particularly important instance of this challenge, the pixels-to-torques problem, where an RL agent learns a closed-loop control policy ("torques") from pixel information only.
Model-based Reinforcement Learning
Model Predictive Control
+2
Gaussian Processes for Data-Efficient Learning in Robotics and Control
Autonomous learning has been a promising direction in control and robotics for more than a decade since data-driven learning allows to reduce the amount of engineering knowledge, which is otherwise required.
Distributed Gaussian Processes
To scale Gaussian processes (GPs) to large data sets we introduce the robust Bayesian Committee Machine (rBCM), a practical and scalable product-of-experts model for large-scale distributed GP regression.
From Pixels to Torques: Policy Learning with Deep Dynamical Models
In this paper, we consider one instance of this challenge, the pixels to torques problem, where an agent must learn a closed-loop control policy from pixel information only.
Model-based Reinforcement Learning
Model Predictive Control
+2
Hierarchical Mixture-of-Experts Model for Large-Scale Gaussian Process Regression
We propose a practical and scalable Gaussian process model for large-scale nonlinear probabilistic regression.
Learning deep dynamical models from image pixels
In particular, we jointly learn a low-dimensional embedding of the observation by means of deep auto-encoders and a predictive transition model in this low-dimensional space.
Manifold Gaussian Processes for Regression
This feature space is often learned in an unsupervised way, which might lead to data representations that are not useful for the overall regression task.
Multi-Task Policy Search
Learning policies that generalize across multiple tasks is an important and challenging research topic in reinforcement learning and robotics.
Expectation Propagation in Gaussian Process Dynamical Systems: Extended Version
Rich and complex time-series data, such as those generated from engineering systems, financial markets, videos or neural recordings, are now a common feature of modern data analysis.
Robust Filtering and Smoothing with Gaussian Processes
We propose a principled algorithm for robust Bayesian filtering and smoothing in nonlinear stochastic dynamic systems when both the transition function and the measurement function are described by non-parametric Gaussian process (GP) models.
A Probabilistic Perspective on Gaussian Filtering and Smoothing
We present a general probabilistic perspective on Gaussian filtering and smoothing.
