Professor Marc Deisenroth is the DeepMind Chair of Machine Learning and Artificial Intelligence at University College London and the Deputy Director of UCL’s AI Centre. He also holds visiting faculty positions at the University of Johannesburg and Imperial College London. Marc leads the Statistical Machine Learning Group at UCL. His research interests center around data-efficient machine learning, probabilistic modeling and autonomous decision making.
Marc was Program Chair of EWRL 2012, Workshops Chair of RSS 2013, EXPO Chair at ICML 2020, Tutorials Chair at NeurIPS 2021, and Program Chair at ICLR 2022. He received Paper Awards at ICRA 2014, ICCAS 2016, ICML 2020, and AISTATS 2021. In 2019, Marc co-organized the Machine Learning Summer School in London.
In 2018, Marc received The President’s Award for Outstanding Early Career Researcher at Imperial College. He is a recipient of a Google Faculty Research Award and a Microsoft PhD Grant.
In 2018, Marc spent four months at the African Institute for Mathematical Sciences (Rwanda), where he taught a course on Foundations of Machine Learning as part of the African Masters in Machine Intelligence. He is co-author of the book Mathematics for Machine Learning, published by Cambridge University Press.
Machine Learning: Data-efficient machine learning, Gaussian processes, reinforcement learning, Bayesian optimization, approximate inference, deep probabilistic models
Robotics and Control: Robot learning, legged locomotion, planning under uncertainty, imitation learning, adaptive control, robust control, learning control, optimal control
Signal Processing: Nonlinear state estimation, Kalman filtering, time-series modeling, dynamical systems, system identification, stochastic information processing
Bayesian optimization is a useful tool for sample-efficient optimization of expensive-to-evaluate black-box functions. In the first part of the talk, we will have a look at a motivating robotics example, where Bayesian optimization can be used for learning gaits of a walking robot. In the second part, we will investigate some intricate details of the inner workings of Bayesian optimization, i.e., the acquisition function (which tells us which experiment to conduct next) and how to optimize it efficiently.
On our path toward fully autonomous systems, i.e., systems that operate in the real world without significant human intervention, machine learning is a promising framework for automatically learning to solve problems. While machine learning has had many successes recently, a practical challenge we face is that it is data hungry. In real-world problems (e.g., robotics) it is not always possible to conduct millions of experiments, e.g., due to time or hardware constraints. In this talk, I will discuss two approaches toward practical and data-efficient robot learning: model-based reinforcement learning and Bayesian optimization.
Vector-valued Gaussian Processes on Riemannian Manifolds via Gauge Independent Projected Kernels
As Gaussian processes are used to answer increasingly complex questions, analytic solutions become scarcer and scarcer. Monte Carlo methods act as a convenient bridge for connecting intractable mathematical expressions with actionable estimates via sampling. Conventional approaches for simulating Gaussian process posteriors view samples as draws from marginal distributions of process values at finite sets of input locations. This distribution-centric characterization leads to generative strategies that scale cubically in the size of the desired random vector. These methods are prohibitively expensive in cases where we would, ideally, like to draw high-dimensional vectors or even continuous sample paths. In this work, we investigate a different line of reasoning: rather than focusing on distributions, we articulate Gaussian conditionals at the level of random variables. We show how this pathwise interpretation of conditioning gives rise to a general family of approximations that lend themselves to efficiently sampling Gaussian process posteriors. Starting from first principles, we derive these methods and analyze the approximation errors they introduce. We, then, ground these results by exploring the practical implications of pathwise conditioning in various applied settings, such as global optimization and reinforcement learning.
Dynamic time warping (DTW) is a useful method for aligning, comparing and combining time series, but it requires them to live in comparable spaces. In this work, we consider a setting in which time series live on different spaces without a sensible ground metric, causing DTW to become ill-defined. To alleviate this, we propose Gromov dynamic time warping (GDTW), a distance between time series on potentially incomparable spaces that avoids the comparability requirement by instead considering intra-relational geometry. We demonstrate its effectiveness at aligning, combining and comparing time series living on incomparable spaces. We further propose a smoothed version of GDTW as a differentiable loss and assess its properties in a variety of settings, including barycentric averaging, generative modeling and imitation learning.
Learning physically structured representations of dynamical systems that include contact between different objects is an important problem for deep learning based approaches in robotics. Black-box neural networks can learn to approximately represent discontinuous dynamics, but typically require impractical quantities of data, and often suffer from pathological behaviour when forecasting for longer time horizons. In this work, we use connections between deep neural networks and differential equations to design a family of deep network architectures for representing contact dynamics between objects. We show that these networks can learn discontinuous contact events in a data-efficient manner from noisy observations in settings which are traditionally difficult for black-box approaches and recent physics inspired neural networks. Our results indicate that an idealised form of touch feedback—which is heavily relied upon by biological systems—is a key component of making this learning problem tractable. Together with the inductive biases introduced through the network architectures, our techniques enable accurate learning of contact dynamics from physical data.
Gaussian processes are a versatile framework for learning unknown functions in a manner that permits one to utilize prior information about their properties. Although many different Gaussian process models are readily available when the input space is Euclidean, the choice is much more limited for Gaussian processes whose input space is an undirected graph. In this work, we leverage the stochastic partial differential equation characterization of Matérn Gaussian processes—a widely-used model class in the Euclidean setting—to study their analog for undirected graphs. We show that the resulting Gaussian processes inherit various attractive properties of their Euclidean and Riemannian analogs, and provide techniques that allow them to be trained using standard methods, such as inducing points. This enables graph Matérn Gaussian processes to be employed in mini-batch, online, and non-conjugate settings, thereby making them more accessible to practitioners and easier to deploy within larger learning frameworks.