José Miguel Hernández-Lobato

Aligning Multimodal Representations through an Information Bottleneck ICML 2025 Domain-Adapted Diffusion Model for PROTAC Linker Design Through the Lens of Density Ratio in Chemical Space ICML 2025 Progressive Tempering Sampler with Diffusion ICML 2025 Scalable Gaussian Processes with Latent Kronecker Structure ICML 2025 Training Neural Samplers with Reverse Diffusive KL Divergence AISTATS 2025 Uncertainty Modeling in Graph Neural Networks via Stochastic Differential Equations ICLR 2025 Accelerating Relative Entropy Coding with Space Partitioning NeurIPS 2024 A Generative Model of Symmetry Transformations NeurIPS 2024 Diffusive Gibbs Sampling ICML 2024 Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation ICML 2024 Improving Linear System Solvers for Hyperparameter Optimisation in Iterative Gaussian Processes NeurIPS 2024 On conditional diffusion models for PDE simulations NeurIPS 2024 Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI ICML 2024 RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representations ICLR 2024 Retro-fallback: retrosynthetic planning in an uncertain world ICLR 2024 Stochastic Gradient Descent for Gaussian Processes Done Right ICLR 2024 Studying K-FAC Heuristics by Viewing Adam through a Second-Order Lens ICML 2024 Compression with Bayesian Implicit Neural Representations NeurIPS 2023 Faster Relative Entropy Coding with Greedy Rejection Coding NeurIPS 2023 Flow Annealed Importance Sampling Bootstrap ICLR 2023 Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Prediction ICLR 2023 Sampling-based inference for large linear models, with application to linearised Laplace ICLR 2023 Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent NeurIPS 2023 SE(3) Equivariant Augmented Coupling Flows NeurIPS 2023 Tanimoto Random Features for Scalable Molecular Machine Learning NeurIPS 2023 Action-Sufficient State Representation Learning for Control with Structural Constraints ICML 2022 Adapting the Linearised Laplace Model Evidence for Modern Deep Learning ICML 2022 Fast Relative Entropy Coding with A* coding ICML 2022 Invariant Causal Representation Learning for Out-of-Distribution Generalization ICLR 2022 Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo NeurIPS 2022 Resampling Base Distributions of Normalizing Flows AISTATS 2022 Scalable One-Pass Optimisation of High-Dimensional Weight-Update Hyperparameters by Implicit Differentiation ICLR 2022 Activation-level uncertainty in deep neural networks ICLR 2021 Active Slices for Sliced Stein Discrepancy ICML 2021 A Gradient Based Strategy for Hamiltonian Monte Carlo Hyperparameter Optimization ICML 2021 Bayesian Deep Learning via Subnetwork Inference ICML 2021 Educational Question Mining At Scale: Prediction, Analysis and Personalization AAAI 2021 Functional Variational Inference based on Stochastic Process Generators NeurIPS 2021 Getting a CLUE: A Method for Explaining Uncertainty Estimates ICLR 2021 Improving black-box optimization in VAE latent space using decoder uncertainty NeurIPS 2021 Predictive Complexity Priors AISTATS 2021 Sliced Kernelized Stein Discrepancy ICLR 2021 Symmetry-Aware Actor-Critic for 3D Molecular Design ICLR 2021 A Generative Model for Molecular Distance Geometry ICML 2020 Barking up the right tree: an approach to search over molecule synthesis DAGs NeurIPS 2020 Compressing Images by Encoding Their Latent Representations with Relative Entropy Coding NeurIPS 2020 Depth Uncertainty in Neural Networks NeurIPS 2020 Reinforcement Learning for Molecular Design Guided by Quantum Mechanics ICML 2020 Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining NeurIPS 2020 VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data NeurIPS 2020 A Generative Model For Electron Paths ICLR 2019 A Model to Search for Synthesizable Molecules NeurIPS 2019 Bayesian Batch Active Learning as Sparse Subset Approximation NeurIPS 2019 Deterministic Variational Inference for Robust Bayesian Neural Networks ICLR 2019 Dropout as a Structured Shrinkage Prior ICML 2019 EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE ICML 2019 Icebreaker: Element-wise Efficient Information Acquisition with a Bayesian Deep Latent Gaussian Model NeurIPS 2019 Meta-Learning For Stochastic Gradient MCMC ICLR 2019 Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters ICLR 2019 Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning NeurIPS 2019 Variational Implicit Processes ICML 2019 Inference in Deep Gaussian Processes using Stochastic Gradient Hamiltonian Monte Carlo NeurIPS 2018 Learning a Generative Model for Validity in Complex Discrete Structures ICLR 2018 Grammar Variational Autoencoder ICML 2017 Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Space ICML 2017 Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control ICML 2017 A General Framework for Constrained Bayesian Optimization using Information-based Search JMLR 2016 Ambiguity Helps: Classification With Disagreements in Crowdsourced Annotations CVPR 2016 Scalable Gaussian Process Classification via Expectation Propagation AISTATS 2016 A Probabilistic Model for Dirty Multi-task Feature Selection ICML 2015 Predictive Entropy Search for Bayesian Optimization with Unknown Constraints ICML 2015 Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks ICML 2015 Stochastic Expectation Propagation NeurIPS 2015 Cold-start Active Learning with Robust Ordinal Matrix Factorization ICML 2014 Gaussian Process Volatility Model NeurIPS 2014 Predictive Entropy Search for Efficient Global Optimization of Black-box Functions NeurIPS 2014 Probabilistic Matrix Factorization with Non-random Missing Data ICML 2014 Stochastic Inference for Scalable Probabilistic Modeling of Binary Matrices ICML 2014 Dynamic Covariance Models for Multivariate Financial Time Series ICML 2013 Gaussian Process Conditional Copulas with Applications to Financial Time Series NeurIPS 2013 Gaussian Process Vine Copulas for Multivariate Dependence ICML 2013 Generalized Spike-and-Slab Priors for Bayesian Group Feature Selection Using Expectation Propagation JMLR 2013 Learning Feature Selection Dependencies in Multi-task Learning NeurIPS 2013