D. Duvenaud

发表

Invertible Residual Networks

David Duvenaud, Jorn-Henrik Jacobsen, Jens Behrmann, 2018, ICML.

Sticking the Landing: An Asymptotically Zero-Variance Gradient Estimator for Variational Inference pdf

David Duvenaud, Geoffrey Roeder, Yuhuai Wu, 2017, ArXiv.

FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models pdf

David Duvenaud, Ilya Sutskever, Ricky T. Q. Chen, 2018, ICLR.

Raiders of the Lost Architecture: Kernels for Bayesian Optimization in Conditional Parameter Spaces

Michael A. Osborne, F. Hutter, D. Duvenaud, 2014, 1409.4011.

Gradient-based Hyperparameter Optimization through Reversible Learning

Ryan P. Adams, David Duvenaud, Dougal Maclaurin, 2015, ICML.

Avoiding pathologies in very deep networks

Ryan P. Adams, Zoubin Ghahramani, David Duvenaud, 2014, AISTATS.

Cutting out the Middle-Man: Training and Evaluating Energy-Based Models without Sampling pdf

Richard Zemel, David Duvenaud, Jorn-Henrik Jacobsen, 2020, ICML 2020.

Probabilistic ODE Solvers with Runge-Kutta Means

David Duvenaud, Philipp Hennig, Michael Schober, 2014, NIPS.

Optimally-Weighted Herding is Bayesian Quadrature

David Duvenaud, Ferenc Huszar, D. Duvenaud, 2012, UAI.

Stochastic Gradient Langevin dynamics that Exploit Neural Network Structure

Jasper Snoek, Roger B. Grosse, David Duvenaud, 2018, ICLR.

Convolutional Networks on Graphs for Learning Molecular Fingerprints

Alán Aspuru-Guzik, Ryan P. Adams, David Duvenaud, 2015, NIPS.

Active Learning of Model Evidence Using Bayesian Quadrature

Carl E. Rasmussen, Roman Garnett, Zoubin Ghahramani, 2012, NIPS.

Additive Gaussian Processes

Carl E. Rasmussen, Hannes Nickisch, David Duvenaud, 2011, NIPS.

ChordRipple: Recommending Chords to Help Novice Composers Go Beyond the Ordinary

Krzysztof Z. Gajos, Cheng-Zhi Anna Huang, David Duvenaud, 2016, IUI.

Causal learning without DAGs

Mark W. Schmidt, Kevin P. Murphy, David Duvenaud, 2008, NIPS Causality: Objectives and Assessment.

Latent‐space Dynamics for Reduced Deformable Simulation

David I. W. Levin, David Duvenaud, Alec Jacobson, 2019, Comput. Graph. Forum.

Neural Networks for the Prediction of Organic Chemistry Reactions

Alán Aspuru-Guzik, David Duvenaud, Jennifer N. Wei, 2016, ACS central science.

Automatic Construction and Natural-Language Description of Nonparametric Regression Models

Joshua B. Tenenbaum, Zoubin Ghahramani, Roger B. Grosse, 2014, AAAI.

Probing the Compositionality of Intuitive Functions

Joshua B. Tenenbaum, David Duvenaud, Samuel Gershman, 2016, NIPS.

Warped Mixtures for Nonparametric Cluster Shapes pdf

Tomoharu Iwata, Zoubin Ghahramani, David Duvenaud, 2012, UAI.

Explaining Image Classifiers by Counterfactual Generation

David Duvenaud, Chun-Hao Chang, Elliot Creager, 2018, ICLR.

Active learning of intuitive control knobs for synthesizers using gaussian processes

Krzysztof Z. Gajos, Cheng-Zhi Anna Huang, David Duvenaud, 2014, IUI.

Generating and designing DNA with deep generative models pdf

Brendan J. Frey, Nathan Killoran, David Duvenaud, 2017, ArXiv.

Scalable Gradients for Stochastic Differential Equations pdf

David Duvenaud, Ricky T. Q. Chen, Xuechen Li, 2020, AISTATS.

Latent Ordinary Differential Equations for Irregularly-Sampled Time Series

David Duvenaud, Tian Qi Chen, Yulia Rubanova, 2019, NeurIPS.

Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions pdf

Roger B. Grosse, David Duvenaud, Paul Vicol, 2019, ICLR.

What went wrong and when? Instance-wise Feature Importance for Time-series Models pdf

David Duvenaud, Shalmali Joshi, Anna Goldenberg, 2020, ArXiv.

Towards Understanding Linear Word Analogies

Graeme Hirst, David Duvenaud, Kawin Ethayarajh, 2018, ACL.

Compositional Inductive Biases in Function Learning

Samuel J. Gershman, Joshua B. Tenenbaum, David Duvenaud, 2016, bioRxiv.

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

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

Design of efficient molecular organic light-emitting diodes by a high-throughput virtual screening and experimental approach.

Ryan P. Adams, D. Duvenaud, D. Maclaurin, 2016, Nature materials.

Reinterpreting Importance-Weighted Autoencoders

David Duvenaud, Quaid Morris, Chris Cremer, 2017, ICLR.

Stochastic Hyperparameter Optimization through Hypernetworks pdf

David Duvenaud, Jonathan Lorraine, D. Duvenaud, 2018, ArXiv.

Compositional inductive biases in function learning

Samuel J. Gershman, Joshua B. Tenenbaum, David Duvenaud, 2016, Cognitive Psychology.

Neural Networks with Cheap Differential Operators

David Duvenaud, Ricky T. Q. Chen, D. Duvenaud, 2019, NeurIPS.

SUMO: Unbiased Estimation of Log Marginal Probability for Latent Variable Models pdf

Ryan P. Adams, Mohammad Norouzi, David Duvenaud, 2020, ICLR.

Understanding Undesirable Word Embedding Associations pdf

Graeme Hirst, David Duvenaud, Kawin Ethayarajh, 2019, ACL.

cDeepbind: A context sensitive deep learning model of RNA-protein binding

Brendan J. Frey, David Duvenaud, Leo J. Lee, 2018, bioRxiv.

Efficient Graph Generation with Graph Recurrent Attention Networks pdf

Renjie Liao, Raquel Urtasun, Richard S. Zemel, 2019, NeurIPS.

Automatic model construction with Gaussian processes

David Duvenaud, D. Duvenaud, 2014 .

Structure Discovery in Nonparametric Regression through Compositional Kernel Search pdf

Joshua B. Tenenbaum, Zoubin Ghahramani, Roger B. Grosse, 2013, ICML.

Invertible Residual Networks

Ricky T. Q. Chen, Jens Behrmann, D. Duvenaud, 2019 .

SOLATING S OURCES OF D ISENTANGLEMENT IN V ARIATIONAL A UTOENCODERS

Roger B. Grosse, Xuechen Li, D. Duvenaud, 2018 .

Design of e cient molecular organic light-emitting diodes by a high-throughput virtual screening and experimental approach

Ryan P. Adams, D. Duvenaud, D. Maclaurin, 2016 .

Teaching with Commentaries

Geoffrey E. Hinton, D. Duvenaud, Simon Kornblith, 2020, ICLR.

Implicit Regularization in Overparameterized Bilevel Optimization

Roger B. Grosse, D. Duvenaud, Paul Vicol, 2021 .

Few-shot Learning for Free by Modelling Global Class Structure

R. Zemel, D. Duvenaud, Will Grathwohl, 2018 .

Cutting out the Middle-Man: Training and Evaluating Energy-Based Models without Sampling

R. Zemel, D. Duvenaud, J. Jacobsen, 2020, ICML 2020.

ChordRipple: Recommending Chords to Help Novice Composers Go Beyond the Ordinary

Cheng-Zhi Anna Huang, Krzysztof Z Gajos, D. Duvenaud, 2016, IUI.

Learning Differential Equations that are Easy to Solve

Matthew J. Johnson, D. Duvenaud, J. Bettencourt, 2020, NeurIPS.

Joint Importance Sampling for Variational Inference

David Duvenaud, Jack Klys, Jesse Bettencourt, 2018 .

What went wrong and when? Instance-wise feature importance for time-series black-box models

David Duvenaud, Shalmali Joshi, Sana Tonekaboni, 2020, NeurIPS.

Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations pdf

David Duvenaud, Ricky T. Q. Chen, Winnie Xu, 2021, ArXiv.

On Implicit Bias in Overparameterized Bilevel Optimization

D. Duvenaud, Fabian Pedregosa, Paul Vicol, 2022, ICML.

Explaining Time Series by Counterfactuals

D. Duvenaud, A. Goldenberg, S. Tonekaboni, 2019 .

Neural Ordinary Differential Equations

David Duvenaud, Tian Qi Chen, Jesse Bettencourt, 2018, NeurIPS.

Complex Momentum for Optimization in Games

D. Duvenaud, David Acuna, Paul Vicol, 2021, AISTATS.

Complex Momentum for Learning in Games pdf

David Duvenaud, David Acuna, Paul Vicol, 2021, ArXiv.

Optimizing Millions of Hyperparameters by Implicit Differentiation pdf

David Duvenaud, Paul Vicol, Jonathan Lorraine, 2019, AISTATS.

Early Stopping as Nonparametric Variational Inference pdf

Ryan P. Adams, David Duvenaud, Dougal Maclaurin, 2015, AISTATS.

Isolating Sources of Disentanglement in Variational Autoencoders

Roger B. Grosse, David Duvenaud, Xuechen Li, 2018, NeurIPS.

Isolating Sources of Disentanglement in VAEs

David Duvenaud, Ricky T. Q. Chen, Xuechen Li, 2018, 1802.04942.

Inference Suboptimality in Variational Autoencoders pdf

David Duvenaud, Xuechen Li, Chris Cremer, 2018, ICML.

Residual Flows for Invertible Generative Modeling

David Duvenaud, Jorn-Henrik Jacobsen, Ricky T. Q. Chen, 2019, NeurIPS.

Self-Tuning Stochastic Optimization with Curvature-Aware Gradient Filtering pdf

David Duvenaud, Philipp Hennig, Ricky T. Q. Chen, 2020, ICBINB@NeurIPS.

Noisy Natural Gradient as Variational Inference

Guodong Zhang, Roger B. Grosse, Shengyang Sun, 2017, ICML.

Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inference

David Duvenaud, Geoffrey Roeder, Yuhuai Wu, 2017, NIPS.

Composing graphical models with neural networks for structured representations and fast inference

Ryan P. Adams, Matthew J. Johnson, David Duvenaud, 2016, NIPS.

Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling

Richard Zemel, David Duvenaud, Will Grathwohl, 2020, ICML.

No MCMC for me: Amortized sampling for fast and stable training of energy-based models

D. Duvenaud, Will Grathwohl, Mohammad Norouzi, 2020, ICLR.

Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One pdf

Mohammad Norouzi, David Duvenaud, Jorn-Henrik Jacobsen, 2019, ICLR.

Backpropagation through the Void: Optimizing control variates for black-box gradient estimation pdf

David Duvenaud, Will Grathwohl, Geoffrey Roeder, 2017, ICLR.

Getting to the point: index sets and parallelism-preserving autodiff for pointful array programming

Daniel D. Johnson, Matthew J. Johnson, D. Duvenaud, 2021, Proc. ACM Program. Lang..

Oops I Took A Gradient: Scalable Sampling for Discrete Distributions pdf

David Duvenaud, Chris J. Maddison, Kevin Swersky, 2021, ICML.

Latent ODEs for Irregularly-Sampled Time Series pdf

David Duvenaud, Ricky T. Q. Chen, Yulia Rubanova, 2019, ArXiv.

Scalable Gradients and Variational Inference for Stochastic Differential Equations

Ricky T. Q. Chen, Xuechen Li, Ting-Kam Leonard Wong, 2019, AABI.

Structured VAEs: Composing Probabilistic Graphical Models and Variational Autoencoders

Ryan P. Adams, Matthew J. Johnson, David Duvenaud, 2016 .

Taylor-Mode Automatic Differentiation for Higher-Order Derivatives in JAX

Matthew J. Johnson, David Duvenaud, Jesse Bettencourt, 2019 .

Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations

Ricky T. Q. Chen, D. Duvenaud, Xuechen Li, 2021, AISTATS.

Explaining Image Classifiers by Adaptive Dropout and Generative In-filling pdf

David Duvenaud, Anna Goldenberg, Chun-Hao Chang, 2018, ArXiv.

Invertible Residual Networks

Jens Behrmann, D. Duvenaud, J. Jacobsen, 2018, ICML.

A Study of Gradient Variance in Deep Learning pdf

David J. Fleet, David Duvenaud, Jimmy Ba, 2020, ArXiv.

Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions

D. Duvenaud, M. Mackay, Paul Vicol, 2019, ICLR.

Meta-Learning to Improve Pre-Training pdf

David Duvenaud, Matthew McDermott, Aniruddh Raghu, 2021, NeurIPS.

Isolating Sources of Disentanglement in Variational Autoencoders

D. Duvenaud, Xuechen Li, T. Chen, 2018, NeurIPS.

Tools for Verifying Neural Models' Training Data

D. Duvenaud, Dami Choi, Yonadav Shavit, 2023, ArXiv.

Gradient-based Hyperparameter Optimization through Reversible Learning

Ryan P. Adams, D. Duvenaud, D. Maclaurin, 2015, International Conference on Machine Learning.

ING STRUCTURED BEST-RESPONSE FUNCTIONS

D. Duvenaud, M. Mackay, Paul Vicol, 2019 .

Additive Gaussian Processes

D. Duvenaud, C. Rasmussen, H. Nickisch, 2011, NIPS.

Towards Understanding Sycophancy in Language Models

D. Duvenaud, Sam McCandlish, Esin Durmus, 2023, ArXiv.

Getting to the point: index sets and parallelism-preserving autodiff for pointful array programming

Daniel D. Johnson, Matthew J. Johnson, D. Duvenaud, 2021, Proc. ACM Program. Lang..

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Daniel M. Ziegler, D. Duvenaud, P. Christiano, 2024, ArXiv.