280 citations · 2k across the 81 of their papers we have counts for
25 papers · 1 filter
PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solvers
Phillip Lippe, Bastiaan S. Veeling, Paris Perdikaris +2
Time-dependent partial differential equations (PDEs) are ubiquitous in science and engineering. Recently, mostly due to the high computational cost of traditional solution techniqu…
Beyond Intuition, a Framework for Applying GPs to Real-World Data
Kenza Tazi, Jihao Andreas Lin, Ross Viljoen +4
Gaussian Processes (GPs) offer an attractive method for regression over small, structured and correlated datasets. However, their deployment is hindered by computational costs and…
Comparing the Efficacy of Fine-Tuning and Meta-Learning for Few-Shot Policy Imitation
Massimiliano Patacchiola, Mingfei Sun, Katja Hofmann +1
In this paper we explore few-shot imitation learning for control problems, which involves learning to imitate a target policy by accessing a limited set of offline rollouts. This s…
An Introduction to Transformers
Richard E. Turner
The transformer is a neural network component that can be used to learn useful representations of sequences or sets of data-points. The transformer has driven recent advances in na…
Adversarial Attacks are a Surprisingly Strong Baseline for Poisoning Few-Shot Meta-Learners
Elre T. Oldewage, John Bronskill, Richard E. Turner
This paper examines the robustness of deployed few-shot meta-learning systems when they are fed an imperceptibly perturbed few-shot dataset. We attack amortized meta-learners, whic…
Differentially private partitioned variational inference
Mikko A. Heikkilä, Matthew Ashman, Siddharth Swaroop +2
Learning a privacy-preserving model from sensitive data which are distributed across multiple devices is an increasingly important problem. The problem is often formulated in the f…
The Neural Process Family: Survey, Applications and Perspectives
Saurav Jha, Dong Gong, Xuesong Wang +2
The standard approaches to neural network implementation yield powerful function approximation capabilities but are limited in their abilities to learn meta representations and rea…
Challenges and Pitfalls of Bayesian Unlearning
Ambrish Rawat, James Requeima, Wessel Bruinsma +1
Machine unlearning refers to the task of removing a subset of training data, thereby removing its contributions to a trained model. Approximate unlearning are one class of methods…
Multi-disciplinary fairness considerations in machine learning for clinical trials
Isabel Chien, Nina Deliu, Richard E. Turner +3
While interest in the application of machine learning to improve healthcare has grown tremendously in recent years, a number of barriers prevent deployment in medical practice. A n…
Efficient Gaussian Neural Processes for Regression
Stratis Markou, James Requeima, Wessel Bruinsma +1
Conditional Neural Processes (CNP; Garnelo et al., 2018) are an attractive family of meta-learning models which produce well-calibrated predictions, enable fast inference at test t…
Combining Pseudo-Point and State Space Approximations for Sum-Separable Gaussian Processes
Will Tebbutt, Arno Solin, Richard E. Turner
Gaussian processes (GPs) are important probabilistic tools for inference and learning in spatio-temporal modelling problems such as those in climate science and epidemiology. Howev…
Contextual HyperNetworks for Novel Feature Adaptation
Angus Lamb, Evgeny Saveliev, Yingzhen Li +7
While deep learning has obtained state-of-the-art results in many applications, the adaptation of neural network architectures to incorporate new output features remains a challeng…
Convolutional conditional neural processes for local climate downscaling
Anna Vaughan, Will Tebbutt, J. Scott Hosking +1
A new model is presented for multisite statistical downscaling of temperature and precipitation using convolutional conditional neural processes (convCNPs). ConvCNPs are a recently…
Generalized Variational Continual Learning
Noel Loo, Siddharth Swaroop, Richard E. Turner
Continual learning deals with training models on new tasks and datasets in an online fashion. One strand of research has used probabilistic regularization for continual learning, w…
Interpreting Spatially Infinite Generative Models
Chaochao Lu, Richard E. Turner, Yingzhen Li +1
Traditional deep generative models of images and other spatial modalities can only generate fixed sized outputs. The generated images have exactly the same resolution as the traini…
VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data
Chao Ma, Sebastian Tschiatschek, José Miguel Hernández-Lobato +2
Deep generative models often perform poorly in real-world applications due to the heterogeneity of natural data sets. Heterogeneity arises from data containing different types of f…
Icebreaker: Element-wise Active Information Acquisition with Bayesian Deep Latent Gaussian Model
Wenbo Gong, Sebastian Tschiatschek, Richard Turner +3
In this paper we introduce the ice-start problem, i.e., the challenge of deploying machine learning models when only little or no training data is initially available, and acquirin…
Infinite-Horizon Gaussian Processes
Arno Solin, James Hensman, Richard E. Turner
Gaussian processes provide a flexible framework for forecasting, removing noise, and interpreting long temporal datasets. State space modelling (Kalman filtering) enables these non…
Deterministic Variational Inference for Robust Bayesian Neural Networks
Anqi Wu, Sebastian Nowozin, Edward Meeds +3
Bayesian neural networks (BNNs) hold great promise as a flexible and principled solution to deal with uncertainty when learning from finite data. Among approaches to realize probab…
Structured Evolution with Compact Architectures for Scalable Policy Optimization
Krzysztof Choromanski, Mark Rowland, Vikas Sindhwani +2
We present a new method of blackbox optimization via gradient approximation with the use of structured random orthogonal matrices, providing more accurate estimators than baselines…
The Mirage of Action-Dependent Baselines in Reinforcement Learning
George Tucker, Surya Bhupatiraju, Shixiang Gu +3
Policy gradient methods are a widely used class of model-free reinforcement learning algorithms where a state-dependent baseline is used to reduce gradient estimator variance. Seve…
Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning
Shixiang Gu, Timothy Lillicrap, Zoubin Ghahramani +3
Off-policy model-free deep reinforcement learning methods using previously collected data can improve sample efficiency over on-policy policy gradient techniques. On the other hand…
Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control
Natasha Jaques, Shixiang Gu, Dzmitry Bahdanau +3
This paper proposes a general method for improving the structure and quality of sequences generated by a recurrent neural network (RNN), while maintaining information originally le…
Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic
Shixiang Gu, Timothy Lillicrap, Zoubin Ghahramani +2
Model-free deep reinforcement learning (RL) methods have been successful in a wide variety of simulated domains. However, a major obstacle facing deep RL in the real world is their…