#### Filter Results:

- Full text PDF available (25)

#### Publication Year

2010

2018

- This year (7)
- Last 5 years (23)
- Last 10 years (30)

#### Publication Type

#### Co-author

#### Journals and Conferences

Learn More

- David K. Duvenaud, Dougal Maclaurin, +4 authors Ryan P. Adams
- NIPS
- 2015

Predicting properties of molecules requires functions that take graphs as inputs. Molecular graphs are usually preprocessed using hash-based functions to produce fixed-size fingerprint vectors, whichâ€¦ (More)

Despite its importance, choosing the structural form of the kernel in nonparametric regression remains a black art. We define a space of kernel structures which are built compositionally by addingâ€¦ (More)

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

Tuning hyperparameters of learning algorithms is hard because gradients are usually unavailable. We compute exact gradients of cross-validation performance with respect to all hyperparameters byâ€¦ (More)

- Rafael GÃ³mez-Bombarelli, David K. Duvenaud, +4 authors AlÃ¡n Aspuru-Guzik
- ACS central science
- 2018

We report a method to convert discrete representations of molecules to and from a multidimensional continuous representation. This model allows us to generate new molecules for efficient explorationâ€¦ (More)

- Tian Qi Chen, Xuechen Li, Roger B. Grosse, David K. Duvenaud
- NeurIPS
- 2018

We decompose the evidence lower bound to show the existence of a term measuring the total correlation between latent variables. We use this to motivate the Î²-TCVAE (Total Correlation Variationalâ€¦ (More)

- Will Grathwohl, Dami Choi, Yuhuai Wu, Geoffrey Roeder, David K. Duvenaud
- ArXiv
- 2017

Gradient-based optimization is the foundation of deep learning and reinforcement learning, but is difficult to apply when the mechanism being optimized is unknown or not differentiable. We introduceâ€¦ (More)

+ optimal local factor â€“ expensive for general obs. + exploit conj. graph structure + arbitrary inference queries + natural gradients â€“ suboptimal local factor + fast for general obs. â€“ does allâ€¦ (More)

This paper presents the beginnings of an automatic statistician, focusing on regression problems. Our system explores an open-ended space of statistical models to discover a good explanation of aâ€¦ (More)

We introduce a Gaussian process model of functions which are additive. An additive function is one which decomposes into a sum of low-dimensional functions, each depending on only a subset of theâ€¦ (More)

Numerical integration is a key component of many problems in sc entific computing, statistical modelling, and machine learning. Bayesia n Quadrature is a modelbased method for numerical integrationâ€¦ (More)