Picture for Sebastian Nowozin

Sebastian Nowozin

Microsoft Research Cambridge

Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamics

Add code
Feb 02, 2023
Viaarxiv icon

High-bandwidth Close-Range Information Transport through Light Pipes

Add code
Jan 19, 2023
Viaarxiv icon

Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification

Add code
Jun 20, 2022
Figure 1 for Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification
Figure 2 for Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification
Figure 3 for Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification
Figure 4 for Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification
Viaarxiv icon

FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification

Add code
Jun 17, 2022
Figure 1 for FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification
Figure 2 for FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification
Figure 3 for FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification
Figure 4 for FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification
Viaarxiv icon

Memory Efficient Meta-Learning with Large Images

Add code
Jul 02, 2021
Figure 1 for Memory Efficient Meta-Learning with Large Images
Figure 2 for Memory Efficient Meta-Learning with Large Images
Figure 3 for Memory Efficient Meta-Learning with Large Images
Figure 4 for Memory Efficient Meta-Learning with Large Images
Viaarxiv icon

Precise characterization of the prior predictive distribution of deep ReLU networks

Add code
Jun 11, 2021
Figure 1 for Precise characterization of the prior predictive distribution of deep ReLU networks
Figure 2 for Precise characterization of the prior predictive distribution of deep ReLU networks
Figure 3 for Precise characterization of the prior predictive distribution of deep ReLU networks
Viaarxiv icon

Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect

Add code
Jun 11, 2021
Figure 1 for Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect
Figure 2 for Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect
Figure 3 for Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect
Figure 4 for Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect
Viaarxiv icon

TaskNorm: Rethinking Batch Normalization for Meta-Learning

Add code
Mar 06, 2020
Figure 1 for TaskNorm: Rethinking Batch Normalization for Meta-Learning
Figure 2 for TaskNorm: Rethinking Batch Normalization for Meta-Learning
Figure 3 for TaskNorm: Rethinking Batch Normalization for Meta-Learning
Figure 4 for TaskNorm: Rethinking Batch Normalization for Meta-Learning
Viaarxiv icon

The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks

Add code
Feb 07, 2020
Figure 1 for The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
Figure 2 for The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
Figure 3 for The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
Figure 4 for The k-tied Normal Distribution: A Compact Parameterization of Gaussian Mean Field Posteriors in Bayesian Neural Networks
Viaarxiv icon

How Good is the Bayes Posterior in Deep Neural Networks Really?

Add code
Feb 06, 2020
Figure 1 for How Good is the Bayes Posterior in Deep Neural Networks Really?
Figure 2 for How Good is the Bayes Posterior in Deep Neural Networks Really?
Figure 3 for How Good is the Bayes Posterior in Deep Neural Networks Really?
Figure 4 for How Good is the Bayes Posterior in Deep Neural Networks Really?
Viaarxiv icon