Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Fred Roosta

Fred Roosta

Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes

Oct 14, 2022
Liam Hodgkinson, Chris van der Heide, Fred Roosta, Michael W. Mahoney

Figure 1 for Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes

Figure 2 for Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes

Figure 3 for Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes

Figure 4 for Monotonicity and Double Descent in Uncertainty Estimation with Gaussian Processes

* 40 pages, 20 figures

Access Paper or Ask Questions

Stochastic Normalizing Flows

Feb 25, 2020
Liam Hodgkinson, Chris van der Heide, Fred Roosta, Michael W. Mahoney

Figure 1 for Stochastic Normalizing Flows

Figure 2 for Stochastic Normalizing Flows

Figure 3 for Stochastic Normalizing Flows

Figure 4 for Stochastic Normalizing Flows

* 17 pages, 4 figures

Access Paper or Ask Questions

Avoiding Kernel Fixed Points: Computing with ELU and GELU Infinite Networks

Feb 22, 2020
Russell Tsuchida, Tim Pearce, Christopher van der Heide, Fred Roosta, Marcus Gallagher

Figure 1 for Avoiding Kernel Fixed Points: Computing with ELU and GELU Infinite Networks

Figure 2 for Avoiding Kernel Fixed Points: Computing with ELU and GELU Infinite Networks

Figure 3 for Avoiding Kernel Fixed Points: Computing with ELU and GELU Infinite Networks

Figure 4 for Avoiding Kernel Fixed Points: Computing with ELU and GELU Infinite Networks

* 18 pages, 9 figures, 2 tables. Corrected name particle capitalisation and formatting

Access Paper or Ask Questions

The reproducing Stein kernel approach for post-hoc corrected sampling

Jan 25, 2020
Liam Hodgkinson, Robert Salomone, Fred Roosta

Figure 1 for The reproducing Stein kernel approach for post-hoc corrected sampling

Figure 2 for The reproducing Stein kernel approach for post-hoc corrected sampling

Figure 3 for The reproducing Stein kernel approach for post-hoc corrected sampling

* 29 pages, 3 figures

Access Paper or Ask Questions

LSAR: Efficient Leverage Score Sampling Algorithm for the Analysis of Big Time Series Data

Dec 26, 2019
Ali Eshragh, Fred Roosta, Asef Nazari, Michael W. Mahoney

Figure 1 for LSAR: Efficient Leverage Score Sampling Algorithm for the Analysis of Big Time Series Data

Figure 2 for LSAR: Efficient Leverage Score Sampling Algorithm for the Analysis of Big Time Series Data

Figure 3 for LSAR: Efficient Leverage Score Sampling Algorithm for the Analysis of Big Time Series Data

Figure 4 for LSAR: Efficient Leverage Score Sampling Algorithm for the Analysis of Big Time Series Data

* 38 pages, 8 figures

Access Paper or Ask Questions