José Miguel Hernández-Lobato

发表

Actively Learning what makes a Discrete Sequence Valid pdf

David Janz, Jos van der Westhuizen, José Miguel Hernández-Lobato, 2017, ArXiv.

Icebreaker: Element-wise Active Information Acquisition with Bayesian Deep Latent Gaussian Model pdf

Sebastian Nowozin, Sebastian Tschiatschek, Cheng Zhang, 2019, ArXiv.

Generating Molecules via Chemical Reactions

Matt J. Kusner, Brooks Paige, José Miguel Hernández-Lobato, 2019, DGS@ICLR.

A Generative Model for Molecular Distance Geometry pdf

José Miguel Hernández-Lobato, Gregor N. C. Simm, 2020, ICML.

A Probabilistic Model for Dirty Multi-task Feature Selection

Daniel Hernández-Lobato, Zoubin Ghahramani, José Miguel Hernández-Lobato, 2015, ICML.

Cold-start Active Learning with Robust Ordinal Matrix Factorization

Zoubin Ghahramani, José Miguel Hernández-Lobato, Neil Houlsby, 2014, ICML.

Gaussianity Measures for Detecting the Direction of Causal Time Series

José Miguel Hernández-Lobato, Alberto Suárez, Pablo Morales-Mombiela, 2011, IJCAI.

Pruning Adaptive Boosting Ensembles by Means of a Genetic Algorithm

Daniel Hernández-Lobato, José Miguel Hernández-Lobato, Rubén Ruiz-Torrubiano, 2006, IDEAL.

Combining deep generative and discriminative models for Bayesian semi-supervised learning

José Miguel Hernández-Lobato, Jonathan Gordon, Jonathan Gordon, 2020, Pattern Recognit..

Minerva: Enabling Low-Power, Highly-Accurate Deep Neural Network Accelerators

Gu-Yeon Wei, David M. Brooks, José Miguel Hernández-Lobato, 2016, 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA).

Dynamic Covariance Models for Multivariate Financial Time Series

Zoubin Ghahramani, José Miguel Hernández-Lobato, Yue Wu, 2013, ICML.

Competitive and Collaborative Mixtures of Experts for Financial Risk Analysis

José Miguel Hernández-Lobato, Alberto Suárez, 2006, ICANN.

Generalized spike-and-slab priors for Bayesian group feature selection using expectation propagation

Daniel Hernández-Lobato, Pierre Dupont, José Miguel Hernández-Lobato, 2013, J. Mach. Learn. Res..

Successor Uncertainties: exploration and uncertainty in temporal difference learning

Sebastian Tschiatschek, David Janz, José Miguel Hernández-Lobato, 2018, NeurIPS.

Stochastic Inference for Scalable Probabilistic Modeling of Binary Matrices

Zoubin Ghahramani, José Miguel Hernández-Lobato, Neil Houlsby, 2014, ICML.

Sensitivity analysis for predictive uncertainty

Thomas A. Runkler, Steffen Udluft, José Miguel Hernández-Lobato, 2017, ESANN.

Deep Gaussian Processes for Regression using Approximate Expectation Propagation

Daniel Hernández-Lobato, Richard E. Turner, Thang D. Bui, 2016, ICML.

Variational Implicit Processes

José Miguel Hernández-Lobato, Chao Ma, Yingzhen Li, 2018, ICML.

Predictive Entropy Search for Efficient Global Optimization of Black-box Functions

Matthew W. Hoffman, Zoubin Ghahramani, José Miguel Hernández-Lobato, 2014, NIPS.

Deterministic Variational Inference for Robust Bayesian Neural Networks

Sebastian Nowozin, Richard E. Turner, Alexander L. Gaunt, 2018, ICLR.

DRIFT: Deep Reinforcement Learning for Functional Software Testing pdf

José Miguel Hernández-Lobato, Levent Özgür, Cheng Zhang, 2020, ArXiv.

A case for efficient accelerator design space exploration via Bayesian optimization

Gu-Yeon Wei, David M. Brooks, Paul N. Whatmough, 2017, 2017 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED).

Interpretable Outcome Prediction with Sparse Bayesian Neural Networks in Intensive Care pdf

Yordan Zaykov, José Miguel Hernández-Lobato, Cheng Zhang, 2019, ArXiv.

Probabilistic Matrix Factorization with Non-random Missing Data

Zoubin Ghahramani, José Miguel Hernández-Lobato, Neil Houlsby, 2014, ICML.

A General Framework for Constrained Bayesian Optimization using Information-based Search

Matthew W. Hoffman, Ryan P. Adams, Zoubin Ghahramani, 2015, J. Mach. Learn. Res..

Stochastic Expectation Propagation

Richard E. Turner, José Miguel Hernández-Lobato, Yingzhen Li, 2015, NIPS.

A COLD Approach to Generating Optimal Samples pdf

José Miguel Hernández-Lobato, Omar Mahmood, O. Mahmood, 2019, ArXiv.

Ambiguity Helps: Classification with Disagreements in Crowdsourced Annotations

Daniel Hernández-Lobato, José Miguel Hernández-Lobato, Novi Quadrianto, 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control

Richard E. Turner, Natasha Jaques, José Miguel Hernández-Lobato, 2016, ICML.

Grammar Variational Autoencoder

Matt J. Kusner, Brooks Paige, José Miguel Hernández-Lobato, 2017, ICML.

Barking up the right tree: an approach to search over molecule synthesis DAGs pdf

Matt J. Kusner, Brooks Paige, José Miguel Hernández-Lobato, 2020, NeurIPS.

Bayes Machines for binary classification

Daniel Hernández-Lobato, José Miguel Hernández-Lobato, 2008, Pattern Recognit. Lett..

Bayesian EDDI: Sequential Variable Selection with Bayesian Partial VAE

Sebastian Nowozin, Sebastian Tschiatschek, Cheng Zhang, 2019 .

Robust Multi-Class Gaussian Process Classification

Daniel Hernández-Lobato, Pierre Dupont, José Miguel Hernández-Lobato, 2011, NIPS.

Ergodic Inference: Accelerate Convergence by Optimisation

José Miguel Hernández-Lobato, Yichuan Zhang, 2018 .

Refining the variational posterior through iterative optimization

Jasper Snoek, Dustin Tran, José Miguel Hernández-Lobato, 2019 .

Learning a Generative Model for Validity in Complex Discrete Structures pdf

Matt J. Kusner, Brooks Paige, David Janz, 2017, ICLR.

HM-VAEs: a Deep Generative Model for Real-valued Data with Heterogeneous Marginals

Sebastian Tschiatschek, Cheng Zhang, Richard E. Turner, 2019, AABI.

Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters pdf

Robert Peharz, José Miguel Hernández-Lobato, Marton Havasi, 2018, ICLR.

Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks

Ryan P. Adams, José Miguel Hernández-Lobato, 2015, ICML.

Semiparametric bivariate Archimedean copulas

José Miguel Hernández-Lobato, Alberto Suárez, A. Suárez, 2011, Comput. Stat. Data Anal..

Collaborative Gaussian Processes for Preference Learning

Zoubin Ghahramani, José Miguel Hernández-Lobato, Neil Houlsby, 2012, NIPS.

Expectation Propagation for Bayesian Multi-task Feature Selection

Thibault Helleputte, Daniel Hernández-Lobato, Pierre Dupont, 2010, ECML/PKDD.

Regulator Discovery from Gene Expression Time Series of Malaria Parasites: a Hierachical Approach

Tom Heskes, José Miguel Hernández-Lobato, Tjeerd Dijkstra, 2007, NIPS.

Compression without Quantization

José Miguel Hernández-Lobato, Marton Havasi, Gergely Flamich, 2019 .

Balancing flexibility and robustness in machine learning: semi-parametric methods and sparse linear models

José Miguel Hernández-Lobato, 2010 .

Dropout as a Structured Shrinkage Prior

Padhraic Smyth, José Miguel Hernández-Lobato, Eric T. Nalisnick, 2018, ICML.

Variational Measure Preserving Flows pdf

Zoubin Ghahramani, José Miguel Hernández-Lobato, Yichuan Zhang, 2018, ArXiv.

'In-Between' Uncertainty in Bayesian Neural Networks pdf

Richard E. Turner, José Miguel Hernández-Lobato, Yingzhen Li, 2019, ArXiv.

GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution pdf

Matt J. Kusner, José Miguel Hernández-Lobato, 2016, ArXiv.

A Model to Search for Synthesizable Molecules

Matt J. Kusner, Brooks Paige, José Miguel Hernández-Lobato, 2019, NeurIPS.

A Generative Model For Electron Paths

Matt J. Kusner, Brooks Paige, José Miguel Hernández-Lobato, 2018, ICLR.

Meta-Learning for Stochastic Gradient MCMC pdf

José Miguel Hernández-Lobato, Wenbo Gong, Yingzhen Li, 2018, ICLR.

Inference in Deep Gaussian Processes using Stochastic Gradient Hamiltonian Monte Carlo

Juan José Murillo-Fuentes, José Miguel Hernández-Lobato, Marton Havasi, 2018, NeurIPS.

Constrained Bayesian optimization for automatic chemical design using variational autoencoders.

José Miguel Hernández-Lobato, Ryan-Rhys Griffiths, 2019 .

Icebreaker: Element-wise Efficient Information Acquisition with a Bayesian Deep Latent Gaussian Model

Sebastian Nowozin, Sebastian Tschiatschek, Cheng Zhang, 2019, NeurIPS.

Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning

Finale Doshi-Velez, Steffen Udluft, José Miguel Hernández-Lobato, 2017, ICML.

Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks pdf

Finale Doshi-Velez, Steffen Udluft, José Miguel Hernández-Lobato, 2016, ICLR.

Predictive Entropy Search for Bayesian Optimization with Unknown Constraints

Matthew W. Hoffman, Ryan P. Adams, Zoubin Ghahramani, 2015, ICML.

Learning Feature Selection Dependencies in Multi-task Learning

Daniel Hernández-Lobato, José Miguel Hernández-Lobato, D. Hernández-Lobato, 2013, NIPS.

GARCH Processes with Non-parametric Innovations for Market Risk Estimation

Daniel Hernández-Lobato, José Miguel Hernández-Lobato, Alberto Suárez, 2007, ICANN.

Expectation Propagation for microarray data classification

Daniel Hernández-Lobato, José Miguel Hernández-Lobato, Alberto Suárez, 2010, Pattern Recognit. Lett..

Hub Gene Selection Methods for the Reconstruction of Transcription Networks

Tjeerd Dijkstra, José Miguel Hernández-Lobato, T. Dijkstra, 2010, ECML/PKDD.

Semi-Supervised Domain Adaptation with Non-Parametric Copulas

Bernhard Schölkopf, David Lopez-Paz, José Miguel Hernández-Lobato, 2012, NIPS.

Predicting Electron Paths pdf

John Bradshaw, Matt J. Kusner, Brooks Paige, 2018, ArXiv.

Bringing Representativeness into Social Media Monitoring and Analysis

Reinhard Riedl, Guillaume Bouchard, Michael Kaschesky, 2013, 2013 46th Hawaii International Conference on System Sciences.

Bayesian Batch Active Learning as Sparse Subset Approximation

José Miguel Hernández-Lobato, Jonathan Gordon, Eric T. Nalisnick, 2019, NeurIPS.

Gaussian Process Conditional Copulas with Applications to Financial Time Series

Daniel Hernández-Lobato, José Miguel Hernández-Lobato, James Robert Lloyd, 2013, NIPS.

Scalable Gaussian Process Classification via Expectation Propagation

Daniel Hernández-Lobato, José Miguel Hernández-Lobato, D. Hernández-Lobato, 2015, AISTATS.

A comprehensive methodology to determine optimal coherence interfaces for many-accelerator SoCs

Gu-Yeon Wei, David M. Brooks, José Miguel Hernández-Lobato, 2020, ISLPED.

Black-Box Alpha Divergence Minimization

Daniel Hernández-Lobato, Richard E. Turner, Thang D. Bui, 2015, ICML.

EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE

Sebastian Nowozin, Sebastian Tschiatschek, Cheng Zhang, 2018, ICML.

Semi-Supervised Domain Adaptation with Copulas

Bernhard Schölkopf, David Lopez-Paz, José Miguel Hernández-Lobato, 2012, NIPS 2012.

Deconfounding Reinforcement Learning in Observational Settings pdf

Bernhard Schölkopf, José Miguel Hernández-Lobato, Chaochao Lu, 2018, ArXiv.

Decomposition of Uncertainty for Active Learning and Reliable Reinforcement Learning in Stochastic Systems pdf

Finale Doshi-Velez, Steffen Udluft, José Miguel Hernández-Lobato, 2017, ArXiv.

Fixing Variational Bayes: Deterministic Variational Inference for Bayesian Neural Networks pdf

Sebastian Nowozin, Richard E. Turner, Alexander L. Gaunt, 2018, ArXiv.

Gaussian Process Volatility Model

Zoubin Ghahramani, José Miguel Hernández-Lobato, Yue Wu, 2014, NIPS.

Minerva: Enabling Low-Power, Highly-Accurate Deep Neural Network Accelerators

Gu-Yeon Wei, José Miguel Hernández-Lobato, Sae Kyu Lee, 2016, 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA).

Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Space

Alán Aspuru-Guzik, James Requeima, Edward O. Pyzer-Knapp, 2017, ICML.

Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules

Alán Aspuru-Guzik, Ryan P. Adams, David Duvenaud, 2016, ACS central science.

Expectation propagation in linear regression models with spike-and-slab priors

Daniel Hernández-Lobato, José Miguel Hernández-Lobato, Alberto Suárez, 2015, Machine Learning.

Taking gradients through experiments: LSTMs and memory proximal policy optimization for black-box quantum control

José Miguel Hernández-Lobato, Moritz August, Moritz August, 2018, ISC Workshops.

Resampling Base Distributions of Normalizing Flows pdf

Bernhard Schölkopf, José Miguel Hernández-Lobato, Vincent Stimper, 2021, ArXiv.

Educational Question Mining At Scale: Prediction, Analysis and Personalization

Sebastian Tschiatschek, Zichao Wang, Richard G. Baraniuk, 2021, AAAI.

Activation-level uncertainty in deep neural networks

Daniel Hernández-Lobato, Pablo Morales-Alvarez, Rafael Molina, 2021, ICLR.

Bayesian Deep Learning via Subnetwork Inference

José Miguel Hernández-Lobato, Eric T. Nalisnick, James Urquhart Allingham, 2021, ICML.

A Gradient Based Strategy for Hamiltonian Monte Carlo Hyperparameter Optimization

José Miguel Hernández-Lobato, Wenlong Chen, Vincent Stimper, 2021, ICML.

Bayesian Semisupervised Learning with Deep Generative Models

José Miguel Hernández-Lobato, Jonathan Gordon, 2017, 1706.09751.

Uncertainty Decomposition in Bayesian Neural Networks with Latent Variables

José Miguel Hernández-Lobato, Stefan Depeweg, Finale Doshi-Velez, 2017, 1706.08495.

Black-box α-divergence minimization

Richard E. Turner, José Miguel Hernández-Lobato, Mark Rowland, 2016, ICML 2016.

Quantifying mismatch in Bayesian optimization

José Miguel Hernández-Lobato, Zoubin Ghahramani, S. Gershman, 2016, NIPS 2016.

ETA-L EARNING FOR S TOCHASTIC G RADIENT MCMC

José Miguel Hernández-Lobato, Yingzhen Li, Wenbo Gong, 2019 .

ROBUST BAYESIAN NEURAL NETWORKS

Richard E. Turner, Alexander L. Gaunt, José Miguel Hernández-Lobato, 2019 .

Importance Weighted Autoencoders with Random Neural Network Parameters

José Miguel Hernández-Lobato, D. Hernández-Lobato, 2016 .

M L ] 1 0 N ov 2 01 5 Black-box α-divergence Minimization

Richard E. Turner, José Miguel Hernández-Lobato, Yingzhen Li, 2015 .

Bayesian Variational Autoencoders for Unsupervised Out-of-Distribution Detection

José Miguel Hernández-Lobato, Erik A. Daxberger, 2019, arXiv.org.

Bayesian Deep Generative Models for Semi-Supervised and Active Learning

José Miguel Hernández-Lobato, 2017 .

Amortised Variational Inference for Hierarchical Mixture Models

José Miguel Hernández-Lobato, Finale Doshi-Velez, Jiayu Yao, 2020 .

Principled Uncertainty Estimation for High Dimensional Data

José Miguel Hernández-Lobato, Y. Gal, Pascal Notin, 2020 .

Partial VAE for Hybrid Recommender System

José Miguel Hernández-Lobato, S. Nowozin, Noam Koenigstein, 2018 .

Designing Neural Network Hardware Accelerators with Decoupled Objective Evaluations

José Miguel Hernández-Lobato, 2016 .

Learning the Semantics of Discrete Random Variables : Ordinal or Categorical ?

José Miguel Hernández-Lobato, 2014 .

Automatic Chemical Design using Variational Autoencoders

David Duvenaud, José Miguel Hernández-Lobato, Rafael Gómez-Bombarelli, 2016 .

Sensitivity analysis for predictive uncertainty in Bayesian neural networks

Thomas A. Runkler, Steffen Udluft, José Miguel Hernández-Lobato, 2018 .

Meta-learning Feature Representations for Adaptive Gaussian Processes via Implicit Differentiation

José Miguel Hernández-Lobato, Wenlin Chen, Austin Tripp, 2022 .

Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Prediction

José Miguel Hernández-Lobato, Wenlin Chen, Austin Tripp, 2022, ArXiv.

Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo

José Miguel Hernández-Lobato, Chao Ma, I. Peis, 2022, ArXiv.

Nonlinear Invariant Risk Minimization: A Causal Approach pdf

José Miguel Hernández-Lobato, Bernhard Scholkopf, Chaochao Lu, 2021, ArXiv.

Action-Sufficient State Representation Learning for Control with Structural Constraints

José Miguel Hernández-Lobato, C. Glymour, B. Schölkopf, 2021, ICML.

Stochastic Expectation Propagation for Large Scale Gaussian Process Classification

Richard E. Turner, José Miguel Hernández-Lobato, Yingzhen Li, 2015, 1511.03249.

Flow Annealed Importance Sampling Bootstrap

José Miguel Hernández-Lobato, Laurence Illing Midgley, B. Scholkopf, 2022, ArXiv.

Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo

José Miguel Hernández-Lobato, Chao Ma, I. Peis, 2022, ArXiv.

DOCKSTRING: Easy Molecular Docking Yields Better Benchmarks for Ligand Design pdf

Andreas Bender, Jos'e Miguel Hern'andez-Lobato, José Miguel Hernández-Lobato, 2021, J. Chem. Inf. Model..

Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Prediction

José Miguel Hernández-Lobato, Wenlin Chen, Austin Tripp, 2022, ArXiv.

Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo

José Miguel Hernández-Lobato, Chao Ma, I. Peis, 2022, ArXiv.

Flow Annealed Importance Sampling Bootstrap

José Miguel Hernández-Lobato, B. Scholkopf, G. Simm, 2022, ArXiv.

Depth Uncertainty in Neural Networks

José Miguel Hernández-Lobato, J. Allingham, Javier Antor'an, 2020, NeurIPS.

Nonlinear Invariant Risk Minimization: A Causal Approach

José Miguel Hernández-Lobato, Yuhuai Wu, B. Schölkopf, 2021, ArXiv.

Active Slices for Sliced Stein Discrepancy pdf

Jos'e Miguel Hern'andez-Lobato, José Miguel Hernández-Lobato, Wenbo Gong, 2021, ICML.

Network-based sparse Bayesian classification

Daniel Hernández-Lobato, José Miguel Hernández-Lobato, Alberto Suárez, 2011, Pattern Recognit..

Constrained Bayesian Optimization for Automatic Chemical Design

Jos'e Miguel Hern'andez-Lobato, José Miguel Hernández-Lobato, Ryan-Rhys Griffiths, 2017 .

Excursion Search for Constrained Bayesian Optimization under a Limited Budget of Failures pdf

Jos'e Miguel Hern'andez-Lobato, José Miguel Hernández-Lobato, Sebastian Trimpe, 2020, ArXiv.

Predictive Entropy Search for Multi-objective Bayesian Optimization with Constraints

Daniel Hern'andez-Lobato, Ryan P. Adams, Jos'e Miguel Hern'andez-Lobato, 2016, Neurocomputing.

Bayesian Deep Learning via Subnetwork Inference

José Miguel Hernández-Lobato, Eric T. Nalisnick, Erik A. Daxberger, 2020, ICML.

Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining pdf

Jos'e Miguel Hern'andez-Lobato, José Miguel Hernández-Lobato, Erik Daxberger, 2020, NeurIPS.

Getting a CLUE: A Method for Explaining Uncertainty Estimates

José Miguel Hernández-Lobato, Adrian Weller, T. Adel, 2020, ICLR.

Symmetry-Aware Actor-Critic for 3D Molecular Design pdf

Jos'e Miguel Hern'andez-Lobato, José Miguel Hernández-Lobato, Gregor N. C. Simm, 2020, ICLR.

A Generative Model for Molecular Distance Geometry

José Miguel Hernández-Lobato, G. Simm, 2019, ICML.

Reinforcement Learning for Molecular Design Guided by Quantum Mechanics

José Miguel Hernández-Lobato, Robert Pinsler, G. Simm, 2020, ICML.

Flow Annealed Importance Sampling Bootstrap

José Miguel Hernández-Lobato, B. Schölkopf, B. Scholkopf, 2022, ICLR.

Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo

José Miguel Hernández-Lobato, Chao Ma, I. Peis, 2022, NeurIPS.

VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data pdf

Sebastian Tschiatschek, Cheng Zhang, Richard E. Turner, 2020, NeurIPS.

Contextual HyperNetworks for Novel Feature Adaptation pdf

Sebastian Tschiatschek, Richard E. Turner, Angus Lamb, 2021, ArXiv.

Large-Scale Educational Question Analysis with Partial Variational Auto-encoders pdf

Sebastian Tschiatschek, Zichao Wang, Simon Woodhead, 2020, ArXiv.

Diagnostic Questions: The NeurIPS 2020 Education Challenge pdf

Zichao Wang, Simon Woodhead, Simon Peyton Jones, 2020, ArXiv.

Results and Insights from Diagnostic Questions: The NeurIPS 2020 Education Challenge

Richard E. Turner, José Miguel Hernández-Lobato, Simon L. Peyton Jones, 2021, NeurIPS.

FIT: a Fast and Accurate Framework for Solving Medical Inquiring and Diagnosing Tasks

José Miguel Hernández-Lobato, Chao Ma, Ting Chen, 2020, ArXiv.

Compression with Bayesian Implicit Neural Representations

José Miguel Hernández-Lobato, Zhibo Chen, Zongyu Guo, 2023, ArXiv.

Improving black-box optimization in VAE latent space using decoder uncertainty pdf

Jos'e Miguel Hern'andez-Lobato, José Miguel Hernández-Lobato, Yarin Gal, 2021, NeurIPS.

Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Prediction

José Miguel Hernández-Lobato, Wenlin Chen, Austin Tripp, 2022, ICLR.

Scalable One-Pass Optimisation of High-Dimensional Weight-Update Hyperparameters by Implicit Differentiation

José Miguel Hernández-Lobato, E. T. Oldewage, Ross M. Clarke, 2021, ArXiv.

Compressing Images by Encoding Their Latent Representations with Relative Entropy Coding

José Miguel Hernández-Lobato, Marton Havasi, Gergely Flamich, 2020, NeurIPS.

Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentation pdf

Jos'e Miguel Hern'andez-Lobato, José Miguel Hernández-Lobato, Kun Zhang, 2020, ArXiv.

Compression with Bayesian Implicit Neural Representations

José Miguel Hernández-Lobato, Zhibo Chen, Zongyu Guo, 2023, ArXiv.

EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE

José Miguel Hernández-Lobato, S. Nowozin, Konstantina Palla, 2018, ICML.

Online Laplace Model Selection Revisited

José Miguel Hernández-Lobato, Javier Antor'an, J. Lin, 2023, ArXiv.

Expressive yet Tractable Bayesian Deep Learning via Subnetwork Inference pdf

Jos'e Miguel Hern'andez-Lobato, José Miguel Hernández-Lobato, Eric Nalisnick, 2020, ArXiv.

Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent

José Miguel Hernández-Lobato, David Janz, Alexander Terenin, 2023, arXiv.org.

Constrained Bayesian Optimization for Automatic Chemical Design

José Miguel Hernández-Lobato, Ryan-Rhys Griffiths, 2017, 1709.05501.

normflows: A PyTorch Package for Normalizing Flows

José Miguel Hernández-Lobato, B. Schölkopf, Vincent Berenz, 2023, J. Open Source Softw..

Resampling Base Distributions of Normalizing Flows

José Miguel Hernández-Lobato, B. Schölkopf, Vincent Stimper, 2021, AISTATS.

Sliced Kernelized Stein Discrepancy pdf

Jos'e Miguel Hern'andez-Lobato, José Miguel Hernández-Lobato, Wenbo Gong, 2020, ICLR.

Tanimoto Random Features for Scalable Molecular Machine Learning

José Miguel Hernández-Lobato, S. Bacallado, Austin Tripp, 2023, arXiv.org.

Variational Depth Search in ResNets

José Miguel Hernández-Lobato, J. Allingham, Javier Antor'an, 2020, ArXiv.

Investigating Inference in Bayesian Neural Networks via Active Learning

José Miguel Hernández-Lobato, Jonathan Gordon, Robert Pinsler, 2019 .

Image Reconstruction via Deep Image Prior Subspaces

José Miguel Hernández-Lobato, Johannes Leuschner, Bangti Jin, 2023, 2302.10279.

Predictive Complexity Priors pdf

Jos'e Miguel Hern'andez-Lobato, José Miguel Hernández-Lobato, Eric Nalisnick, 2020, AISTATS.

Ergodic Inference: Accelerate Convergence by Optimisation

José Miguel Hernández-Lobato, Yichuan Zhang, 2018, 1805.10377.

Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent

José Miguel Hernández-Lobato, David Janz, Alexander Terenin, 2023, Neural Information Processing Systems.

RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representations

José Miguel Hernández-Lobato, Gergely Flamich, Jiajun He, 2023, ArXiv.

Compression with Bayesian Implicit Neural Representations

José Miguel Hernández-Lobato, Zhibo Chen, Zongyu Guo, 2023, ArXiv.

Probabilistic Matrix Factorization with Non-random Missing Data

José Miguel Hernández-Lobato, Zoubin Ghahramani, N. Houlsby, 2014, ICML.

Minimal Random Code Learning with Mean-KL Parameterization

José Miguel Hernández-Lobato, Gergely Flamich, J. Lin, 2023, arXiv.org.

Black-Box Alpha Divergence Minimization

Richard E. Turner, José Miguel Hernández-Lobato, Mark Rowland, 2016, ICML.

Leveraging Task Structures for Improved Identifiability in Neural Network Representations

José Miguel Hernández-Lobato, Wenlin Chen, Juyeon Heo, 2023, ArXiv.

Cold-start Active Learning with Robust Ordinal Matrix Factorization

José Miguel Hernández-Lobato, Zoubin Ghahramani, N. Houlsby, 2014, ICML.

Predictive Entropy Search for Multi-objective Bayesian Optimization

Ryan P. Adams, José Miguel Hernández-Lobato, D. Hernández-Lobato, 2015, ICML.

Tanimoto Random Features for Scalable Molecular Machine Learning

José Miguel Hernández-Lobato, S. Bacallado, Austin Tripp, 2023, NeurIPS.

Getting a CLUE: A Method for Explaining Uncertainty Estimates pdf

Jos'e Miguel Hern'andez-Lobato, José Miguel Hernández-Lobato, Adrian Weller, 2020, ICLR.

Expressive yet Tractable Bayesian Deep Learning via Subnetwork Inference

José Miguel Hernández-Lobato, Erik A. Daxberger, J. Allingham, 2020, ArXiv.