Publications (142)
Image Reconstruction via Deep Image Prior Subspaces
Riccardo Barbano, Javier Antorán, Johannes Leuschner +3
Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning
David Janz, Jiri Hron, PrzemysÅaw Mazur +3
Gaussian Process Vine Copulas for Multivariate Dependence
David Lopez-Paz, José Miguel Hernández-Lobato, Zoubin Ghahramani
Aligning Multimodal Representations through an Information Bottleneck
Antonio Almudévar, José Miguel Hernández-Lobato, Sameer Khurana +2
Getting a CLUE: A Method for Explaining Uncertainty Estimates
Javier Antorán, Umang Bhatt, Tameem Adel +2
Deconfounding Reinforcement Learning in Observational Settings
Chaochao Lu, Bernhard Schölkopf, José Miguel Hernández-Lobato
No Trick, No Treat: Pursuits and Challenges Towards Simulation-free Training of Neural Samplers
Jiajun He, Yuanqi Du, Francisco Vargas +5
Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI
Theodore Papamarkou, Maria Skoularidou, Konstantina Palla +22
SE(3) Equivariant Augmented Coupling Flows
Laurence I. Midgley, Vincent Stimper, Javier Antorán +3
Conditional Diffusion Sampling
Francisco M. Castro-MacÃas, Pablo Morales-Ãlvarez, Saifuddin Syed +3
Training Neural Samplers with Reverse Diffusive KL Divergence
Jiajun He, Wenlin Chen, Mingtian Zhang +2
Symmetry-Aware Actor-Critic for 3D Molecular Design
Gregor N. C. Simm, Robert Pinsler, Gábor Csányi +1
Best Practices for Multi-Fidelity Bayesian Optimization in Materials and Molecular Research
VÃctor Sabanza-Gil, Riccardo Barbano, Daniel Pacheco Gutiérrez +4
Stochastic Interpolants in Hilbert Spaces
James Boran Yu, RuiKang OuYang, Julien Horwood +1
normflows: A PyTorch Package for Normalizing Flows
Vincent Stimper, David Liu, Andrew Campbell +4
Convergent Expectation Propagation in Linear Models with Spike-and-slab Priors
José Miguel Hernández-Lobato, Daniel Hernández-Lobato
Meta-Learning for Stochastic Gradient MCMC
Wenbo Gong, Yingzhen Li, José Miguel Hernández-Lobato
Introducing instance label correlation in multiple instance learning. Application to cancer detection on histopathological images
Pablo Morales-Ãlvarez, Arne Schmidt, José Miguel Hernández-Lobato +1
Excursion Search for Constrained Bayesian Optimization under a Limited Budget of Failures
Alonso Marco, Alexander von Rohr, Dominik Baumann +2
Instructions and Guide for Diagnostic Questions: The NeurIPS 2020 Education Challenge
Zichao Wang, Angus Lamb, Evgeny Saveliev +9
EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE
Chao Ma, Sebastian Tschiatschek, Konstantina Palla +3
Predictive Entropy Search for Efficient Global Optimization of Black-box Functions
José Miguel Hernández-Lobato, Matthew W. Hoffman, Zoubin Ghahramani
Improving Antibody Design with Force-Guided Sampling in Diffusion Models
Paulina KulytÄ, Francisco Vargas, Simon Valentin Mathis +3
Sliced Kernelized Stein Discrepancy
Wenbo Gong, Yingzhen Li, José Miguel Hernández-Lobato
Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks
Stefan Depeweg, José Miguel Hernández-Lobato, Finale Doshi-Velez +1
Retro-fallback: retrosynthetic planning in an uncertain world
Austin Tripp, Krzysztof Maziarz, Sarah Lewis +2
Minimal Random Code Learning with Mean-KL Parameterization
Jihao Andreas Lin, Gergely Flamich, José Miguel Hernández-Lobato
Interpretable Outcome Prediction with Sparse Bayesian Neural Networks in Intensive Care
Hiske Overweg, Anna-Lena Popkes, Ari Ercole +4
Bayesian Deep Learning via Subnetwork Inference
Erik Daxberger, Eric Nalisnick, James Urquhart Allingham +2
Taking gradients through experiments: LSTMs and memory proximal policy optimization for black-box quantum control
Moritz August, José Miguel Hernández-Lobato
Stochastic Expectation Propagation for Large Scale Gaussian Process Classification
Daniel Hernández-Lobato, José Miguel Hernández-Lobato, Yingzhen Li +2
Expanding the Chaos: Neural Operator for Stochastic (Partial) Differential Equations
Dai Shi, Lequan Lin, Andi Han +4
A Model to Search for Synthesizable Molecules
John Bradshaw, Brooks Paige, Matt J. Kusner +2
Active Slices for Sliced Stein Discrepancy
Wenbo Gong, Kaibo Zhang, Yingzhen Li +1
Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters
Marton Havasi, Robert Peharz, José Miguel Hernández-Lobato
'In-Between' Uncertainty in Bayesian Neural Networks
Andrew Y. K. Foong, Yingzhen Li, José Miguel Hernández-Lobato +1
Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentation
Chaochao Lu, Biwei Huang, Ke Wang +3
Predictive Entropy Search for Multi-objective Bayesian Optimization
Daniel Hernández-Lobato, José Miguel Hernández-Lobato, Amar Shah +1
Ergodic Inference: Accelerate Convergence by Optimisation
Yichuan Zhang, José Miguel Hernández-Lobato
Automatic chemical design using a data-driven continuous representation of molecules
Rafael Gómez-Bombarelli, Jennifer N. Wei, David Duvenaud +7
Uncertainty Decomposition in Bayesian Neural Networks with Latent Variables
Stefan Depeweg, José Miguel Hernández-Lobato, Finale Doshi-Velez +1
Batched Bayesian optimization by maximizing the probability of including the optimum
Jenna Fromer, Runzhong Wang, Mrunali Manjrekar +3
Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control
Natasha Jaques, Shixiang Gu, Dzmitry Bahdanau +3
Training Deep Gaussian Processes using Stochastic Expectation Propagation and Probabilistic Backpropagation
Thang D. Bui, José Miguel Hernández-Lobato, Yingzhen Li +2
Bootstrap Your Flow
Laurence Illing Midgley, Vincent Stimper, Gregor N. C. Simm +1
BSODA: A Bipartite Scalable Framework for Online Disease Diagnosis
Weijie He, Xiaohao Mao, Chao Ma +3
Reinforcement Learning for Molecular Design Guided by Quantum Mechanics
Gregor N. C. Simm, Robert Pinsler, José Miguel Hernández-Lobato
There Was Never a Bottleneck in Concept Bottleneck Models
Antonio Almudévar, José Miguel Hernández-Lobato, Alfonso Ortega
Dynamic Covariance Models for Multivariate Financial Time Series
Yue Wu, José Miguel Hernández-Lobato, Zoubin Ghahramani
Decoupled PFNs: Identifiable Epistemic-Aleatoric Decomposition via Structured Synthetic Priors
Richard Bergna, Stefan Depeweg, José Miguel Hernández-Lobato
Grammar Variational Autoencoder
Matt J. Kusner, Brooks Paige, José Miguel Hernández-Lobato
Compressing Images by Encoding Their Latent Representations with Relative Entropy Coding
Gergely Flamich, Marton Havasi, José Miguel Hernández-Lobato
Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining
Austin Tripp, Erik Daxberger, José Miguel Hernández-Lobato
Contextual HyperNetworks for Novel Feature Adaptation
Angus Lamb, Evgeny Saveliev, Yingzhen Li +7
Stochastic Gradient Descent for Gaussian Processes Done Right
Jihao Andreas Lin, Shreyas Padhy, Javier Antorán +5
Deep Gaussian Processes for Regression using Approximate Expectation Propagation
Thang D. Bui, Daniel Hernández-Lobato, Yingzhen Li +2
RNE: plug-and-play diffusion inference-time control and energy-based training
Jiajun He, José Miguel Hernández-Lobato, Yuanqi Du +1
Scalable Gaussian Processes with Latent Kronecker Structure
Jihao Andreas Lin, Sebastian Ament, Maximilian Balandat +3
Predictive Complexity Priors
Eric Nalisnick, Jonathan Gordon, José Miguel Hernández-Lobato
Nonparametric Heterogeneous Long-term Causal Effect Estimation via Data Combination
Weilin Chen, Ruichu Cai, Junjie Wan +2
A General Framework for Constrained Bayesian Optimization using Information-based Search
José Miguel Hernández-Lobato, Michael A. Gelbart, Ryan P. Adams +2
Constrained Bayesian Optimization for Automatic Chemical Design
Ryan-Rhys Griffiths, José Miguel Hernández-Lobato
Depth Uncertainty in Neural Networks
Javier Antorán, James Urquhart Allingham, José Miguel Hernández-Lobato
Towards Diverse Scientific Hypothesis Search with Large Language Models
Haorui Wang, Parshin Shojaee, Kazem Meidani +7
Black-box $α$-divergence Minimization
José Miguel Hernández-Lobato, Yingzhen Li, Mark Rowland +3
Free energy Estimation on Any State Space
Jiajun He, Zijing Ou, Francisco Vargas +4
A Generative Model of Symmetry Transformations
James Urquhart Allingham, Bruno Kacper Mlodozeniec, Shreyas Padhy +5
Actively Learning what makes a Discrete Sequence Valid
David Janz, Jos van der Westhuizen, José Miguel Hernández-Lobato
A Diffusive Classification Loss for Learning Energy-based Generative Models
RuiKang OuYang, Louis Grenioux, José Miguel Hernández-Lobato
Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent
Jihao Andreas Lin, Javier Antorán, Shreyas Padhy +3
Bayesian Experimental Design for Computed Tomography with the Linearised Deep Image Prior
Riccardo Barbano, Johannes Leuschner, Javier Antorán +2
Addressing Bias in Active Learning with Depth Uncertainty Networks... or Not
Chelsea Murray, James U. Allingham, Javier Antorán +1
GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution
Matt J. Kusner, José Miguel Hernández-Lobato
Adapting the Linearised Laplace Model Evidence for Modern Deep Learning
Javier Antorán, David Janz, James Urquhart Allingham +4
Improving Linear System Solvers for Hyperparameter Optimisation in Iterative Gaussian Processes
Jihao Andreas Lin, Shreyas Padhy, Bruno Mlodozeniec +2
Long-term Causal Inference via Modeling Sequential Latent Confounding
Weilin Chen, Ruichu Cai, Yuguang Yan +2
Depth Uncertainty Networks for Active Learning
Chelsea Murray, James U. Allingham, Javier Antorán +1
A Deep Generative Model for the Design of Synthesizable Ionizable Lipids
Yuxuan Ou, Jingyi Zhao, Austin Tripp +2
Icebreaker: Element-wise Active Information Acquisition with Bayesian Deep Latent Gaussian Model
Wenbo Gong, Sebastian Tschiatschek, Richard Turner +3
Generative Active Learning for the Search of Small-molecule Protein Binders
Maksym Korablyov, Cheng-Hao Liu, Moksh Jain +31
A COLD Approach to Generating Optimal Samples
Omar Mahmood, José Miguel Hernández-Lobato
Getting Free Bits Back from Rotational Symmetries in LLMs
Jiajun He, Gergely Flamich, José Miguel Hernández-Lobato
Series of Hessian-Vector Products for Tractable Saddle-Free Newton Optimisation of Neural Networks
Elre T. Oldewage, Ross M. Clarke, José Miguel Hernández-Lobato
CREPE: Controlling Diffusion with Replica Exchange
Jiajun He, Paul Jeha, Peter Potaptchik +5
Diagnosing and fixing common problems in Bayesian optimization for molecule design
Austin Tripp, José Miguel Hernández-Lobato
Learning a Generative Model for Validity in Complex Discrete Structures
David Janz, Jos van der Westhuizen, Brooks Paige +2
Flow Annealed Importance Sampling Bootstrap
Laurence Illing Midgley, Vincent Stimper, Gregor N. C. Simm +2
BNEM: A Boltzmann Sampler Based on Bootstrapped Noised Energy Matching
RuiKang OuYang, Bo Qiang, José Miguel Hernández-Lobato
Deep Gaussian Processes with Decoupled Inducing Inputs
Marton Havasi, José Miguel Hernández-Lobato, Juan José Murillo-Fuentes
VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data
Chao Ma, Sebastian Tschiatschek, José Miguel Hernández-Lobato +2
Generative Model for Synthesizing Ionizable Lipids: A Monte Carlo Tree Search Approach
Jingyi Zhao, Yuxuan Ou, Austin Tripp +2
Bayesian Batch Active Learning as Sparse Subset Approximation
Robert Pinsler, Jonathan Gordon, Eric Nalisnick +1
Compression as Adaptation: Implicit Visual Representation with Diffusion Foundation Models
Zongyu Guo, Jiajun He, Zhaoyang Jia +6
Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Space
José Miguel Hernández-Lobato, James Requeima, Edward O. Pyzer-Knapp +1
Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks
José Miguel Hernández-Lobato, Ryan P. Adams
Action-Sufficient State Representation Learning for Control with Structural Constraints
Biwei Huang, Chaochao Lu, Liu Leqi +4
RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representations
Jiajun He, Gergely Flamich, Zongyu Guo +1
Inference in Deep Gaussian Processes using Stochastic Gradient Hamiltonian Monte Carlo
Marton Havasi, José Miguel Hernández-Lobato, Juan José Murillo-Fuentes
DOCKSTRING: easy molecular docking yields better benchmarks for ligand design
Miguel GarcÃa-Ortegón, Gregor N. C. Simm, Austin J. Tripp +3
Improving black-box optimization in VAE latent space using decoder uncertainty
Pascal Notin, José Miguel Hernández-Lobato, Yarin Gal