Alert button
Picture for David Janz

David Janz

Alert button

Ensemble sampling for linear bandits: small ensembles suffice

Nov 14, 2023
David Janz, Alexander E. Litvak, Csaba Szepesvári

Viaarxiv icon

Exploration via linearly perturbed loss minimisation

Nov 13, 2023
David Janz, Shuai Liu, Alex Ayoub, Csaba Szepesvári

Figure 1 for Exploration via linearly perturbed loss minimisation
Figure 2 for Exploration via linearly perturbed loss minimisation
Viaarxiv icon

Stochastic Gradient Descent for Gaussian Processes Done Right

Oct 31, 2023
Jihao Andreas Lin, Shreyas Padhy, Javier Antorán, Austin Tripp, Alexander Terenin, Csaba Szepesvári, José Miguel Hernández-Lobato, David Janz

Viaarxiv icon

Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent

Jun 20, 2023
Jihao Andreas Lin, Javier Antorán, Shreyas Padhy, David Janz, José Miguel Hernández-Lobato, Alexander Terenin

Viaarxiv icon

Sampling-based inference for large linear models, with application to linearised Laplace

Oct 10, 2022
Javier Antorán, Shreyas Padhy, Riccardo Barbano, Eric Nalisnick, David Janz, José Miguel Hernández-Lobato

Figure 1 for Sampling-based inference for large linear models, with application to linearised Laplace
Figure 2 for Sampling-based inference for large linear models, with application to linearised Laplace
Figure 3 for Sampling-based inference for large linear models, with application to linearised Laplace
Figure 4 for Sampling-based inference for large linear models, with application to linearised Laplace
Viaarxiv icon

Adapting the Linearised Laplace Model Evidence for Modern Deep Learning

Jun 17, 2022
Javier Antorán, David Janz, James Urquhart Allingham, Erik Daxberger, Riccardo Barbano, Eric Nalisnick, José Miguel Hernández-Lobato

Figure 1 for Adapting the Linearised Laplace Model Evidence for Modern Deep Learning
Figure 2 for Adapting the Linearised Laplace Model Evidence for Modern Deep Learning
Figure 3 for Adapting the Linearised Laplace Model Evidence for Modern Deep Learning
Figure 4 for Adapting the Linearised Laplace Model Evidence for Modern Deep Learning
Viaarxiv icon

Bandit optimisation of functions in the Matérn kernel RKHS

Mar 02, 2020
David Janz, David R. Burt, Javier González

Figure 1 for Bandit optimisation of functions in the Matérn kernel RKHS
Figure 2 for Bandit optimisation of functions in the Matérn kernel RKHS
Viaarxiv icon

Learning a Generative Model for Validity in Complex Discrete Structures

Nov 02, 2018
David Janz, Jos van der Westhuizen, Brooks Paige, Matt J. Kusner, José Miguel Hernández-Lobato

Figure 1 for Learning a Generative Model for Validity in Complex Discrete Structures
Figure 2 for Learning a Generative Model for Validity in Complex Discrete Structures
Figure 3 for Learning a Generative Model for Validity in Complex Discrete Structures
Figure 4 for Learning a Generative Model for Validity in Complex Discrete Structures
Viaarxiv icon

Successor Uncertainties: exploration and uncertainty in temporal difference learning

Oct 15, 2018
David Janz, Jiri Hron, José Miguel Hernández-Lobato, Katja Hofmann, Sebastian Tschiatschek

Figure 1 for Successor Uncertainties: exploration and uncertainty in temporal difference learning
Figure 2 for Successor Uncertainties: exploration and uncertainty in temporal difference learning
Figure 3 for Successor Uncertainties: exploration and uncertainty in temporal difference learning
Figure 4 for Successor Uncertainties: exploration and uncertainty in temporal difference learning
Viaarxiv icon