3.2k citations · 6.1k across the 82 of their papers we have counts for
88 papers
RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representations
Jiajun He, Gergely Flamich, Zongyu Guo +1
COMpression with Bayesian Implicit NEural Representations (COMBINER) is a recent data compression method that addresses a key inefficiency of previous Implicit Neural Representatio…
SE(3) Equivariant Augmented Coupling Flows
Laurence I. Midgley, Vincent Stimper, Javier Antorán +3
Coupling normalizing flows allow for fast sampling and density evaluation, making them the tool of choice for probabilistic modeling of physical systems. However, the standard coup…
Minimal Random Code Learning with Mean-KL Parameterization
Jihao Andreas Lin, Gergely Flamich, José Miguel Hernández-Lobato
This paper studies the qualitative behavior and robustness of two variants of Minimal Random Code Learning (MIRACLE) used to compress variational Bayesian neural networks. MIRACLE…
Online Laplace Model Selection Revisited
Jihao Andreas Lin, Javier Antorán, José Miguel Hernández-Lobato
The Laplace approximation provides a closed-form model selection objective for neural networks (NN). Online variants, which optimise NN parameters jointly with hyperparameters, lik…
Leveraging Task Structures for Improved Identifiability in Neural Network Representations
Wenlin Chen, Julien Horwood, Juyeon Heo +1
This work extends the theory of identifiability in supervised learning by considering the consequences of having access to a distribution of tasks. In such cases, we show that line…
Tanimoto Random Features for Scalable Molecular Machine Learning
Austin Tripp, Sergio Bacallado, Sukriti Singh +1
The Tanimoto coefficient is commonly used to measure the similarity between molecules represented as discrete fingerprints, either as a distance metric or a positive definite kerne…
Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent
Jihao Andreas Lin, Javier Antorán, Shreyas Padhy +3
Gaussian processes are a powerful framework for quantifying uncertainty and for sequential decision-making but are limited by the requirement of solving linear systems. In general,…
Compression with Bayesian Implicit Neural Representations
Zongyu Guo, Gergely Flamich, Jiajun He +2
Many common types of data can be represented as functions that map coordinates to signal values, such as pixel locations to RGB values in the case of an image. Based on this view,…
normflows: A PyTorch Package for Normalizing Flows
Vincent Stimper, David Liu, Andrew Campbell +4
Normalizing flows model probability distributions through an expressive tractable density. They transform a simple base distribution, such as a Gaussian, through a sequence of inve…
Image Reconstruction via Deep Image Prior Subspaces
Riccardo Barbano, Javier Antorán, Johannes Leuschner +3
Deep learning has been widely used for solving image reconstruction tasks but its deployability has been held back due to the shortage of high-quality training data. Unsupervised l…
Flow Annealed Importance Sampling Bootstrap
Laurence Illing Midgley, Vincent Stimper, Gregor N. C. Simm +2
Normalizing flows are tractable density models that can approximate complicated target distributions, e.g. Boltzmann distributions of physical systems. However, current methods for…
Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Prediction
Wenlin Chen, Austin Tripp, José Miguel Hernández-Lobato
We propose Adaptive Deep Kernel Fitting with Implicit Function Theorem (ADKF-IFT), a novel framework for learning deep kernel Gaussian processes (GPs) by interpolating between meta…
Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo
Ignacio Peis, Chao Ma, José Miguel Hernández-Lobato
Variational Autoencoders (VAEs) have recently been highly successful at imputing and acquiring heterogeneous missing data. However, within this specific application domain, existin…
DOCKSTRING: easy molecular docking yields better benchmarks for ligand design
Miguel García-Ortegón, Gregor N. C. Simm, Austin J. Tripp +3
The field of machine learning for drug discovery is witnessing an explosion of novel methods. These methods are often benchmarked on simple physicochemical properties such as solub…
Resampling Base Distributions of Normalizing Flows
Vincent Stimper, Bernhard Schölkopf, José Miguel Hernández-Lobato
Normalizing flows are a popular class of models for approximating probability distributions. However, their invertible nature limits their ability to model target distributions who…
Scalable One-Pass Optimisation of High-Dimensional Weight-Update Hyperparameters by Implicit Differentiation
Ross M. Clarke, Elre T. Oldewage, José Miguel Hernández-Lobato
Machine learning training methods depend plentifully and intricately on hyperparameters, motivating automated strategies for their optimisation. Many existing algorithms restart tr…
Action-Sufficient State Representation Learning for Control with Structural Constraints
Biwei Huang, Chaochao Lu, Liu Leqi +4
Perceived signals in real-world scenarios are usually high-dimensional and noisy, and finding and using their representation that contains essential and sufficient information requ…
Improving black-box optimization in VAE latent space using decoder uncertainty
Pascal Notin, José Miguel Hernández-Lobato, Yarin Gal
Optimization in the latent space of variational autoencoders is a promising approach to generate high-dimensional discrete objects that maximize an expensive black-box property (e.…
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…
Results and Insights from Diagnostic Questions: The NeurIPS 2020 Education Challenge
Zichao Wang, Angus Lamb, Evgeny Saveliev +9
This competition concerns educational diagnostic questions, which are pedagogically effective, multiple-choice questions (MCQs) whose distractors embody misconceptions. With a larg…
Nonlinear Invariant Risk Minimization: A Causal Approach
Chaochao Lu, Yuhuai Wu, Jośe Miguel Hernández-Lobato +1
Due to spurious correlations, machine learning systems often fail to generalize to environments whose distributions differ from the ones used at training time. Prior work addressin…
Active Slices for Sliced Stein Discrepancy
Wenbo Gong, Kaibo Zhang, Yingzhen Li +1
Sliced Stein discrepancy (SSD) and its kernelized variants have demonstrated promising successes in goodness-of-fit tests and model learning in high dimensions. Despite their theor…
Barking up the right tree: an approach to search over molecule synthesis DAGs
John Bradshaw, Brooks Paige, Matt J. Kusner +2
When designing new molecules with particular properties, it is not only important what to make but crucially how to make it. These instructions form a synthesis directed acyclic gr…
Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentation
Chaochao Lu, Biwei Huang, Ke Wang +3
Reinforcement learning (RL) algorithms usually require a substantial amount of interaction data and perform well only for specific tasks in a fixed environment. In some scenarios s…