Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDJosé Miguel Hernández-Lobato
Person information
- affiliation: University of Cambridge, Cambridge, UK
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2023
[j12]Vincent Stimper
, David Liu, Andrew Campbell, Vincent Berenz, Lukas Ryll, Bernhard Schölkopf, José Miguel Hernández-Lobato:
normflows: A PyTorch Package for Normalizing Flows. J. Open Source Softw. 8(87): 5361 (2023)- [c85]Javier Antorán, Shreyas Padhy, Riccardo Barbano, Eric T. Nalisnick, David Janz, José Miguel Hernández-Lobato:
Sampling-based inference for large linear models, with application to linearised Laplace. ICLR 2023 - [c84]Wenlin Chen, Austin Tripp, José Miguel Hernández-Lobato:
Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Prediction. ICLR 2023 - [c83]Laurence Illing Midgley, Vincent Stimper, Gregor N. C. Simm, Bernhard Schölkopf, José Miguel Hernández-Lobato:
Flow Annealed Importance Sampling Bootstrap. ICLR 2023 - [d3]Vincent Stimper, David Liu, Andrew Campbell, Vincent Berenz, Lukas Ryll, Bernhard Schölkopf, José Miguel Hernández-Lobato:
normflows: A PyTorch Package for Normalizing Flows. Version v1.7.0. Zenodo, 2023 [all versions]
- [d2]Vincent Stimper, David Liu, Andrew Campbell, Vincent Berenz, Lukas Ryll, Bernhard Schölkopf, José Miguel Hernández-Lobato:
normflows: A PyTorch Package for Normalizing Flows. Version v1.7.1. Zenodo, 2023 [all versions] - [d1]Vincent Stimper, David Liu, Andrew Campbell, Vincent Berenz, Lukas Ryll, Bernhard Schölkopf, José Miguel Hernández-Lobato:
normflows: A PyTorch Package for Normalizing Flows. Version v1.7.2. Zenodo, 2023 [all versions] - [i77]Riccardo Barbano, Javier Antorán, Johannes Leuschner, José Miguel Hernández-Lobato, Zeljko Kereta, Bangti Jin:
Fast and Painless Image Reconstruction in Deep Image Prior Subspaces. CoRR abs/2302.10279 (2023) - [i76]Vincent Stimper, David Liu, Andrew Campbell, Vincent Berenz, Lukas Ryll, Bernhard Schölkopf, José Miguel Hernández-Lobato:
normflows: A PyTorch Package for Normalizing Flows. CoRR abs/2302.12014 (2023) - [i75]Zongyu Guo, Gergely Flamich, Jiajun He, Zhibo Chen, José Miguel Hernández-Lobato:
Compression with Bayesian Implicit Neural Representations. CoRR abs/2305.19185 (2023) - [i74]Jihao Andreas Lin, Javier Antorán, Shreyas Padhy, David Janz, José Miguel Hernández-Lobato, Alexander Terenin:
Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent. CoRR abs/2306.11589 (2023) - [i73]Austin Tripp, Sergio Bacallado, Sukriti Singh, José Miguel Hernández-Lobato:
Tanimoto Random Features for Scalable Molecular Machine Learning. CoRR abs/2306.14809 (2023) - [i72]Wenlin Chen, Julien Horwood, Juyeon Heo, José Miguel Hernández-Lobato:
Leveraging Task Structures for Improved Identifiability in Neural Network Representations. CoRR abs/2306.14861 (2023) - [i71]Jihao Andreas Lin, Javier Antorán, José Miguel Hernández-Lobato:
Online Laplace Model Selection Revisited. CoRR abs/2307.06093 (2023) - [i70]Jihao Andreas Lin, Gergely Flamich, José Miguel Hernández-Lobato:
Minimal Random Code Learning with Mean-KL Parameterization. CoRR abs/2307.07816 (2023) - [i69]Laurence I. Midgley, Vincent Stimper, Javier Antorán, Emile Mathieu, Bernhard Schölkopf, José Miguel Hernández-Lobato:
SE(3) Equivariant Augmented Coupling Flows. CoRR abs/2308.10364 (2023) - [i68]Richard Bergna, Felix L. Opolka, Pietro Liò, José Miguel Hernández-Lobato:
Graph Neural Stochastic Differential Equations. CoRR abs/2308.12316 (2023) - 2022
- [j11]Miguel García-Ortegón, Gregor N. C. Simm, Austin J. Tripp, José Miguel Hernández-Lobato, Andreas Bender, Sergio Bacallado:
DOCKSTRING: Easy Molecular Docking Yields Better Benchmarks for Ligand Design. J. Chem. Inf. Model. 62(15): 3486-3502 (2022) - [c82]Vincent Stimper, Bernhard Schölkopf, José Miguel Hernández-Lobato:
Resampling Base Distributions of Normalizing Flows. AISTATS 2022: 4915-4936 - [c81]Ross M. Clarke, Elre Talea Oldewage, José Miguel Hernández-Lobato:
Scalable One-Pass Optimisation of High-Dimensional Weight-Update Hyperparameters by Implicit Differentiation. ICLR 2022 - [c80]Chaochao Lu, Yuhuai Wu, José Miguel Hernández-Lobato, Bernhard Schölkopf:
Invariant Causal Representation Learning for Out-of-Distribution Generalization. ICLR 2022 - [c79]Javier Antorán, David Janz, James Urquhart Allingham, Erik A. Daxberger, Riccardo Barbano, Eric T. Nalisnick, José Miguel Hernández-Lobato:
Adapting the Linearised Laplace Model Evidence for Modern Deep Learning. ICML 2022: 796-821 - [c78]Gergely Flamich, Stratis Markou, José Miguel Hernández-Lobato:
Fast Relative Entropy Coding with A* coding. ICML 2022: 6548-6577 - [c77]Biwei Huang, Chaochao Lu, Liu Leqi, José Miguel Hernández-Lobato, Clark Glymour, Bernhard Schölkopf, Kun Zhang:
Action-Sufficient State Representation Learning for Control with Structural Constraints. ICML 2022: 9260-9279 - [c76]Ignacio Peis, Chao Ma, José Miguel Hernández-Lobato:
Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo. NeurIPS 2022 - [c75]Weijie He, Xiaohao Mao, Chao Ma, Yu Huang, José Miguel Hernández-Lobato, Ting Chen:
BSODA: A Bipartite Scalable Framework for Online Disease Diagnosis. WWW 2022: 2511-2521 - [i67]Gergely Flamich, Stratis Markou, José Miguel Hernández-Lobato:
Fast Relative Entropy Coding with A* coding. CoRR abs/2201.12857 (2022) - [i66]Ignacio Peis, Chao Ma, José Miguel Hernández-Lobato:
Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo. CoRR abs/2202.04599 (2022) - [i65]Javier Antorán, Riccardo Barbano, Johannes Leuschner, José Miguel Hernández-Lobato, Bangti Jin:
A Probabilistic Deep Image Prior for Computational Tomography. CoRR abs/2203.00479 (2022) - [i64]Wenlin Chen, Austin Tripp, José Miguel Hernández-Lobato:
Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Prediction. CoRR abs/2205.02708 (2022) - [i63]Javier Antorán, David Janz, James Urquhart Allingham, Erik A. Daxberger, Riccardo Barbano, Eric T. Nalisnick, José Miguel Hernández-Lobato:
Adapting the Linearised Laplace Model Evidence for Modern Deep Learning. CoRR abs/2206.08900 (2022) - [i62]Riccardo Barbano, Johannes Leuschner, Javier Antorán, Bangti Jin, José Miguel Hernández-Lobato:
Bayesian Experimental Design for Computed Tomography with the Linearised Deep Image Prior. CoRR abs/2207.05714 (2022) - [i61]Laurence Illing Midgley, Vincent Stimper, Gregor N. C. Simm, Bernhard Schölkopf, José Miguel Hernández-Lobato:
Flow Annealed Importance Sampling Bootstrap. CoRR abs/2208.01893 (2022) - [i60]Javier Antorán, Shreyas Padhy, Riccardo Barbano, Eric T. Nalisnick, David Janz, José Miguel Hernández-Lobato:
Sampling-based inference for large linear models, with application to linearised Laplace. CoRR abs/2210.04994 (2022) - 2021
- [j10]Marton Havasi, Jasper Snoek, Dustin Tran, Jonathan Gordon, José Miguel Hernández-Lobato:
Sampling the Variational Posterior with Local Refinement. Entropy 23(11): 1475 (2021) - [c74]Zichao Wang, Sebastian Tschiatschek, Simon Woodhead, José Miguel Hernández-Lobato, Simon Peyton Jones, Richard G. Baraniuk, Cheng Zhang:
Educational Question Mining At Scale: Prediction, Analysis and Personalization. AAAI 2021: 15669-15677 - [c73]Eric T. Nalisnick, Jonathan Gordon, José Miguel Hernández-Lobato:
Predictive Complexity Priors. AISTATS 2021: 694-702 - [c72]Chelsea Murray, James Urquhart Allingham, Javier Antorán, José Miguel Hernández-Lobato:
Addressing Bias in Active Learning with Depth Uncertainty Networks... or Not. ICBINB@NeurIPS 2021: 59-63 - [c71]Wenbo Gong, Yingzhen Li, José Miguel Hernández-Lobato:
Sliced Kernelized Stein Discrepancy. ICLR 2021 - [c70]Javier Antorán, Umang Bhatt, Tameem Adel, Adrian Weller, José Miguel Hernández-Lobato:
Getting a CLUE: A Method for Explaining Uncertainty Estimates. ICLR 2021 - [c69]Pablo Morales-Alvarez, Daniel Hernández-Lobato, Rafael Molina, José Miguel Hernández-Lobato:
Activation-level uncertainty in deep neural networks. ICLR 2021 - [c68]Gregor N. C. Simm, Robert Pinsler, Gábor Csányi, José Miguel Hernández-Lobato:
Symmetry-Aware Actor-Critic for 3D Molecular Design. ICLR 2021 - [c67]Andrew Campbell, Wenlong Chen, Vincent Stimper, José Miguel Hernández-Lobato, Yichuan Zhang:
A Gradient Based Strategy for Hamiltonian Monte Carlo Hyperparameter Optimization. ICML 2021: 1238-1248 - [c66]Erik A. Daxberger, Eric T. Nalisnick, James Urquhart Allingham, Javier Antorán, José Miguel Hernández-Lobato:
Bayesian Deep Learning via Subnetwork Inference. ICML 2021: 2510-2521 - [c65]Wenbo Gong, Kaibo Zhang, Yingzhen Li, José Miguel Hernández-Lobato:
Active Slices for Sliced Stein Discrepancy. ICML 2021: 3766-3776 - [c64]Pascal Notin, José Miguel Hernández-Lobato, Yarin Gal:
Improving black-box optimization in VAE latent space using decoder uncertainty. NeurIPS 2021: 802-814 - [c63]Chao Ma, José Miguel Hernández-Lobato:
Functional Variational Inference based on Stochastic Process Generators. NeurIPS 2021: 21795-21807 - [i59]Wenbo Gong, Kaibo Zhang, Yingzhen Li, José Miguel Hernández-Lobato:
Active Slices for Sliced Stein Discrepancy. CoRR abs/2102.03159 (2021) - [i58]Chaochao Lu, Yuhuai Wu, José Miguel Hernández-Lobato, Bernhard Schölkopf:
Nonlinear Invariant Risk Minimization: A Causal Approach. CoRR abs/2102.12353 (2021) - [i57]Zichao Wang, Angus Lamb, Evgeny Saveliev, Pashmina Cameron, Yordan Zaykov, José Miguel Hernández-Lobato, Richard E. Turner, Richard G. Baraniuk, Craig Barton, Simon Peyton Jones, Simon Woodhead, Cheng Zhang:
Results and Insights from Diagnostic Questions: The NeurIPS 2020 Education Challenge. CoRR abs/2104.04034 (2021) - [i56]Angus Lamb, Evgeny Saveliev, Yingzhen Li, Sebastian Tschiatschek, Camilla Longden, Simon Woodhead, José Miguel Hernández-Lobato, Richard E. Turner, Pashmina Cameron, Cheng Zhang:
Contextual HyperNetworks for Novel Feature Adaptation. CoRR abs/2104.05860 (2021) - [i55]Pascal Notin, José Miguel Hernández-Lobato, Yarin Gal:
Improving black-box optimization in VAE latent space using decoder uncertainty. CoRR abs/2107.00096 (2021) - [i54]Biwei Huang, Chaochao Lu, Liu Leqi, José Miguel Hernández-Lobato, Clark Glymour, Bernhard Schölkopf, Kun Zhang:
Action-Sufficient State Representation Learning for Control with Structural Constraints. CoRR abs/2110.05721 (2021) - [i53]Ross M. Clarke, Elre T. Oldewage, José Miguel Hernández-Lobato:
Scalable One-Pass Optimisation of High-Dimensional Weight-Update Hyperparameters by Implicit Differentiation. CoRR abs/2110.10461 (2021) - [i52]Miguel García-Ortegón, Gregor N. C. Simm, Austin J. Tripp, José Miguel Hernández-Lobato, Andreas Bender, Sergio Bacallado:
DOCKSTRING: easy molecular docking yields better benchmarks for ligand design. CoRR abs/2110.15486 (2021) - [i51]Vincent Stimper, Bernhard Schölkopf, José Miguel Hernández-Lobato:
Resampling Base Distributions of Normalizing Flows. CoRR abs/2110.15828 (2021) - [i50]Laurence Illing Midgley, Vincent Stimper, Gregor N. C. Simm, José Miguel Hernández-Lobato:
Bootstrap Your Flow. CoRR abs/2111.11510 (2021) - [i49]Chelsea Murray, James Urquhart Allingham, Javier Antorán, José Miguel Hernández-Lobato:
Depth Uncertainty Networks for Active Learning. CoRR abs/2112.06796 (2021) - [i48]Chelsea Murray, James Urquhart Allingham, Javier Antorán, José Miguel Hernández-Lobato:
Addressing Bias in Active Learning with Depth Uncertainty Networks... or Not. CoRR abs/2112.06926 (2021) - 2020
- [j9]Jonathan Gordon, José Miguel Hernández-Lobato:
Combining deep generative and discriminative models for Bayesian semi-supervised learning. Pattern Recognit. 100: 107156 (2020) - [c62]Gregor N. C. Simm, José Miguel Hernández-Lobato:
A Generative Model for Molecular Distance Geometry. ICML 2020: 8949-8958 - [c61]Gregor N. C. Simm, Robert Pinsler, José Miguel Hernández-Lobato:
Reinforcement Learning for Molecular Design Guided by Quantum Mechanics. ICML 2020: 8959-8969 - [c60]Kshitij Bhardwaj, Marton Havasi, Yuan Yao, David M. Brooks, José Miguel Hernández-Lobato, Gu-Yeon Wei:
A comprehensive methodology to determine optimal coherence interfaces for many-accelerator SoCs. ISLPED 2020: 145-150 - [c59]Zichao Wang, Angus Lamb, Evgeny Saveliev, Pashmina Cameron, Yordan Zaykov, José Miguel Hernández-Lobato, Richard E. Turner, Richard G. Baraniuk, Craig Barton, Simon Peyton Jones, Simon Woodhead, Cheng Zhang:
Results and Insights from Diagnostic Questions: The NeurIPS 2020 Education Challenge. NeurIPS (Competition and Demos) 2020: 191-205 - [c58]Javier Antorán, James Urquhart Allingham, José Miguel Hernández-Lobato:
Depth Uncertainty in Neural Networks. NeurIPS 2020 - [c57]John Bradshaw, Brooks Paige, Matt J. Kusner, Marwin H. S. Segler, José Miguel Hernández-Lobato:
Barking up the right tree: an approach to search over molecule synthesis DAGs. NeurIPS 2020 - [c56]Gergely Flamich, Marton Havasi, José Miguel Hernández-Lobato:
Compressing Images by Encoding Their Latent Representations with Relative Entropy Coding. NeurIPS 2020 - [c55]Chao Ma, Sebastian Tschiatschek, Richard E. Turner, José Miguel Hernández-Lobato, Cheng Zhang:
VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data. NeurIPS 2020 - [c54]Austin Tripp, Erik A. Daxberger, José Miguel Hernández-Lobato:
Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining. NeurIPS 2020 - [i47]Javier Antorán, James Urquhart Allingham, José Miguel Hernández-Lobato:
Variational Depth Search in ResNets. CoRR abs/2002.02797 (2020) - [i46]Gregor N. C. Simm, Robert Pinsler, José Miguel Hernández-Lobato:
Reinforcement Learning for Molecular Design Guided by Quantum Mechanics. CoRR abs/2002.07717 (2020) - [i45]Zichao Wang, Sebastian Tschiatschek, Simon Woodhead, José Miguel Hernández-Lobato, Simon Peyton Jones, Cheng Zhang:
Large-Scale Educational Question Analysis with Partial Variational Auto-encoders. CoRR abs/2003.05980 (2020) - [i44]Alonso Marco, Alexander von Rohr, Dominik Baumann, José Miguel Hernández-Lobato, Sebastian Trimpe:
Excursion Search for Constrained Bayesian Optimization under a Limited Budget of Failures. CoRR abs/2005.07443 (2020) - [i43]Javier Antorán, Umang Bhatt, Tameem Adel, Adrian Weller, José Miguel Hernández-Lobato:
Getting a CLUE: A Method for Explaining Uncertainty Estimates. CoRR abs/2006.06848 (2020) - [i42]Javier Antorán, James Urquhart Allingham, José Miguel Hernández-Lobato:
Depth Uncertainty in Neural Networks. CoRR abs/2006.08437 (2020) - [i41]Austin Tripp, Erik A. Daxberger, José Miguel Hernández-Lobato:
Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining. CoRR abs/2006.09191 (2020) - [i40]Eric T. Nalisnick, Jonathan Gordon, José Miguel Hernández-Lobato:
Predictive Complexity Priors. CoRR abs/2006.10801 (2020) - [i39]Chao Ma, Sebastian Tschiatschek, José Miguel Hernández-Lobato, Richard E. Turner, Cheng Zhang:
VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data. CoRR abs/2006.11941 (2020) - [i38]Wenbo Gong, Yingzhen Li, José Miguel Hernández-Lobato:
Sliced Kernelized Stein Discrepancy. CoRR abs/2006.16531 (2020) - [i37]Luke Harries, Rebekah Storan Clarke, Timothy Chapman, Swamy V. P. L. N. Nallamalli, Levent Özgür, Shuktika Jain, Alex Leung, Steve Lim, Aaron Dietrich, José Miguel Hernández-Lobato, Tom Ellis, Cheng Zhang, Kamil Ciosek:
DRIFT: Deep Reinforcement Learning for Functional Software Testing. CoRR abs/2007.08220 (2020) - [i36]Zichao Wang, Angus Lamb, Evgeny Saveliev, Pashmina Cameron, Yordan Zaykov, José Miguel Hernández-Lobato, Richard E. Turner, Richard G. Baraniuk, Craig Barton, Simon Peyton Jones, Simon Woodhead, Cheng Zhang:
Diagnostic Questions: The NeurIPS 2020 Education Challenge. CoRR abs/2007.12061 (2020) - [i35]Gergely Flamich, Marton Havasi, José Miguel Hernández-Lobato:
Compressing Images by Encoding Their Latent Representations with Relative Entropy Coding. CoRR abs/2010.01185 (2020) - [i34]Erik A. Daxberger, Eric T. Nalisnick, James Urquhart Allingham, Javier Antorán, José Miguel Hernández-Lobato:
Expressive yet Tractable Bayesian Deep Learning via Subnetwork Inference. CoRR abs/2010.14689 (2020) - [i33]Gregor N. C. Simm, Robert Pinsler, Gábor Csányi, José Miguel Hernández-Lobato:
Symmetry-Aware Actor-Critic for 3D Molecular Design. CoRR abs/2011.12747 (2020) - [i32]Weijie He, Xiaohao Mao, Chao Ma, José Miguel Hernández-Lobato, Ting Chen:
FIT: a Fast and Accurate Framework for Solving Medical Inquiring and Diagnosing Tasks. CoRR abs/2012.01065 (2020) - [i31]Chaochao Lu, Biwei Huang, Ke Wang, José Miguel Hernández-Lobato, Kun Zhang, Bernhard Schölkopf:
Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentation. CoRR abs/2012.09092 (2020) - [i30]John Bradshaw, Brooks Paige, Matt J. Kusner, Marwin H. S. Segler, José Miguel Hernández-Lobato:
Barking up the right tree: an approach to search over molecule synthesis DAGs. CoRR abs/2012.11522 (2020)
2010 – 2019
- 2019
- [j8]Kshitij Bhardwaj, Marton Havasi, Yuan Yao, David M. Brooks, José Miguel Hernández-Lobato, Gu-Yeon Wei:
Determining Optimal Coherency Interface for Many-Accelerator SoCs Using Bayesian Optimization. IEEE Comput. Archit. Lett. 18(2): 119-123 (2019) - [c53]Chao Ma, Sebastian Tschiatschek, Yingzhen Li, Richard E. Turner, José Miguel Hernández-Lobato, Cheng Zhang:
HM-VAEs: a Deep Generative Model for Real-valued Data with Heterogeneous Marginals. AABI 2019: 1-8 - [c52]John Bradshaw, Matt J. Kusner, Brooks Paige, Marwin H. S. Segler, José Miguel Hernández-Lobato:
A Generative Model For Electron Paths. ICLR (Poster) 2019 - [c51]John Bradshaw, Matt J. Kusner, Brooks Paige, Marwin H. S. Segler, José Miguel Hernández-Lobato:
Generating Molecules via Chemical Reactions. DGS@ICLR 2019 - [c50]Wenbo Gong, Yingzhen Li, José Miguel Hernández-Lobato:
Meta-Learning For Stochastic Gradient MCMC. ICLR (Poster) 2019 - [c49]Marton Havasi, Robert Peharz, José Miguel Hernández-Lobato:
Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters. ICLR (Poster) 2019 - [c48]Anqi Wu, Sebastian Nowozin, Edward Meeds, Richard E. Turner, José Miguel Hernández-Lobato, Alexander L. Gaunt:
Deterministic Variational Inference for Robust Bayesian Neural Networks. ICLR 2019 - [c47]Chao Ma, Yingzhen Li, José Miguel Hernández-Lobato:
Variational Implicit Processes. ICML 2019: 4222-4233 - [c46]Chao Ma, Sebastian Tschiatschek, Konstantina Palla, José Miguel Hernández-Lobato, Sebastian Nowozin, Cheng Zhang:
EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE. ICML 2019: 4234-4243 - [c45]Eric T. Nalisnick, José Miguel Hernández-Lobato, Padhraic Smyth:
Dropout as a Structured Shrinkage Prior. ICML 2019: 4712-4722 - [c44]David Janz, Jiri Hron, Przemyslaw Mazur, Katja Hofmann, José Miguel Hernández-Lobato, Sebastian Tschiatschek:
Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning. NeurIPS 2019: 4509-4518 - [c43]Robert Pinsler, Jonathan Gordon, Eric T. Nalisnick, José Miguel Hernández-Lobato:
Bayesian Batch Active Learning as Sparse Subset Approximation. NeurIPS 2019: 6356-6367 - [c42]John Bradshaw, Brooks Paige, Matt J. Kusner, Marwin H. S. Segler, José Miguel Hernández-Lobato:
A Model to Search for Synthesizable Molecules. NeurIPS 2019: 7935-7947 - [c41]Wenbo Gong, Sebastian Tschiatschek, Sebastian Nowozin, Richard E. Turner, José Miguel Hernández-Lobato, Cheng Zhang:
Icebreaker: Element-wise Efficient Information Acquisition with a Bayesian Deep Latent Gaussian Model. NeurIPS 2019: 14791-14802 - [i29]Anna-Lena Popkes, Hiske Overweg, Ari Ercole, Yingzhen Li, José Miguel Hernández-Lobato, Yordan Zaykov, Cheng Zhang:
Interpretable Outcome Prediction with Sparse Bayesian Neural Networks in Intensive Care. CoRR abs/1905.02599 (2019) - [i28]Omar Mahmood, José Miguel Hernández-Lobato:
A COLD Approach to Generating Optimal Samples. CoRR abs/1905.09885 (2019) - [i27]John Bradshaw, Brooks Paige, Matt J. Kusner, Marwin H. S. Segler, José Miguel Hernández-Lobato:
A Model to Search for Synthesizable Molecules. CoRR abs/1906.05221 (2019) - [i26]Andrew Y. K. Foong, Yingzhen Li, José Miguel Hernández-Lobato, Richard E. Turner:
'In-Between' Uncertainty in Bayesian Neural Networks. CoRR abs/1906.11537 (2019) - [i25]Robert Pinsler, Jonathan Gordon, Eric T. Nalisnick, José Miguel Hernández-Lobato:
Bayesian Batch Active Learning as Sparse Subset Approximation. CoRR abs/1908.02144 (2019) - [i24]Wenbo Gong, Sebastian Tschiatschek, Richard E. Turner, Sebastian Nowozin, José Miguel Hernández-Lobato, Cheng Zhang:
Icebreaker: Element-wise Active Information Acquisition with Bayesian Deep Latent Gaussian Model. CoRR abs/1908.04537 (2019) - [i23]Gregor N. C. Simm, José Miguel Hernández-Lobato:
A Generative Model for Molecular Distance Geometry. CoRR abs/1909.11459 (2019) - [i22]Erik A. Daxberger, José Miguel Hernández-Lobato:
Bayesian Variational Autoencoders for Unsupervised Out-of-Distribution Detection. CoRR abs/1912.05651 (2019) - 2018
- [c40]Stefan Depeweg, José Miguel Hernández-Lobato, Steffen Udluft, Thomas A. Runkler:
Sensitivity analysis for predictive uncertainty. ESANN 2018 - [c39]David Janz, Jos van der Westhuizen, Brooks Paige, Matt J. Kusner, José Miguel Hernández-Lobato:
Learning a Generative Model for Validity in Complex Discrete Structures. ICLR (Poster) 2018 - [c38]Stefan Depeweg, José Miguel Hernández-Lobato, Finale Doshi-Velez, Steffen Udluft:
Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning. ICML 2018: 1192-1201 - [c37]Marton Havasi, José Miguel Hernández-Lobato, Juan José Murillo-Fuentes:
Inference in Deep Gaussian Processes using Stochastic Gradient Hamiltonian Monte Carlo. NeurIPS 2018: 7517-7527 - [c36]Moritz August, José Miguel Hernández-Lobato:
Taking Gradients Through Experiments: LSTMs and Memory Proximal Policy Optimization for Black-Box Quantum Control. ISC Workshops 2018: 591-613 - [i21]Moritz August, José Miguel Hernández-Lobato:
Taking gradients through experiments: LSTMs and memory proximal policy optimization for black-box quantum control. CoRR abs/1802.04063 (2018) - [i20]Yichuan Zhang, José Miguel Hernández-Lobato, Zoubin Ghahramani:
Variational Measure Preserving Flows. CoRR abs/1805.10377 (2018) - [i19]John Bradshaw, Matt J. Kusner, Brooks Paige, Marwin H. S. Segler, José Miguel Hernández-Lobato:
Predicting Electron Paths. CoRR abs/1805.10970 (2018) - [i18]Chao Ma, Yingzhen Li, José Miguel Hernández-Lobato:
Variational Implicit Processes. CoRR abs/1806.02390 (2018) - [i17]Wenbo Gong, Yingzhen Li, José Miguel Hernández-Lobato:
Meta-Learning for Stochastic Gradient MCMC. CoRR abs/1806.04522 (2018) - [i16]Marton Havasi, José Miguel Hernández-Lobato, Juan José Murillo-Fuentes:
Inference in Deep Gaussian Processes using Stochastic Gradient Hamiltonian Monte Carlo. CoRR abs/1806.05490 (2018) - [i15]Chao Ma, Sebastian Tschiatschek, Konstantina Palla, José Miguel Hernández-Lobato, Sebastian Nowozin, Cheng Zhang:
EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE. CoRR abs/1809.11142 (2018) - [i14]