Samuel L. Smith

According to our database, Samuel L. Smith authored at least 26 papers between 2016 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models.

Soham De, Samuel L. Smith, Anushan Fernando, Aleksandar Botev, George-Cristian Muraru, Albert Gu, Ruba Haroun, Leonard Berrada, Yutian Chen, Srivatsan Srinivasan, Guillaume Desjardins, Arnaud Doucet, David Budden, Yee Whye Teh, Razvan Pascanu, Nando de Freitas, Çaglar Gülçehre

CoRR, 2024

2023

ConvNets Match Vision Transformers at Scale.

Samuel L. Smith, Andrew Brock, Leonard Berrada, Soham De

CoRR, 2023

Unlocking Accuracy and Fairness in Differentially Private Image Classification.

Leonard Berrada, Soham De, Judy Hanwen Shen, Jamie Hayes, Robert Stanforth, David Stutz, Pushmeet Kohli, Samuel L. Smith, Borja Balle

CoRR, 2023

On the Universality of Linear Recurrences Followed by Nonlinear Projections.

Antonio Orvieto, Soham De, Çaglar Gülçehre, Razvan Pascanu, Samuel L. Smith

CoRR, 2023

Differentially Private Diffusion Models Generate Useful Synthetic Images.

Sahra Ghalebikesabi, Leonard Berrada, Sven Gowal, Ira Ktena, Robert Stanforth, Jamie Hayes, Soham De, Samuel L. Smith, Olivia Wiles, Borja Balle

CoRR, 2023

Resurrecting Recurrent Neural Networks for Long Sequences.

Antonio Orvieto, Samuel L. Smith, Albert Gu, Anushan Fernando, Çaglar Gülçehre, Razvan Pascanu, Soham De

Proceedings of the International Conference on Machine Learning, 2023

Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation.

Bobby He, James Martens, Guodong Zhang, Aleksandar Botev, Andrew Brock, Samuel L. Smith, Yee Whye Teh

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Unlocking High-Accuracy Differentially Private Image Classification through Scale.

Soham De, Leonard Berrada, Jamie Hayes, Samuel L. Smith, Borja Balle

CoRR, 2022

2021

A study on the plasticity of neural networks.

Tudor Berariu, Wojciech Czarnecki, Soham De, Jörg Bornschein, Samuel L. Smith, Razvan Pascanu, Claudia Clopath

CoRR, 2021

Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error.

Stanislav Fort, Andrew Brock, Razvan Pascanu, Soham De, Samuel L. Smith

CoRR, 2021

High-Performance Large-Scale Image Recognition Without Normalization.

Andy Brock, Soham De, Samuel L. Smith, Karen Simonyan

Proceedings of the 38th International Conference on Machine Learning, 2021

On the Origin of Implicit Regularization in Stochastic Gradient Descent.

Samuel L. Smith, Benoit Dherin, David G. T. Barrett, Soham De

Proceedings of the 9th International Conference on Learning Representations, 2021

Characterizing signal propagation to close the performance gap in unnormalized ResNets.

Andrew Brock, Soham De, Samuel L. Smith

Proceedings of the 9th International Conference on Learning Representations, 2021

2020

BYOL works even without batch statistics.

Pierre H. Richemond, Jean-Bastien Grill, Florent Altché, Corentin Tallec, Florian Strub, Andrew Brock, Samuel L. Smith, Soham De, Razvan Pascanu, Bilal Piot, Michal Valko

CoRR, 2020

Cold Posteriors and Aleatoric Uncertainty.

Ben Adlam, Jasper Snoek, Samuel L. Smith

CoRR, 2020

Batch Normalization Biases Deep Residual Networks Towards Shallow Paths.

Soham De, Samuel L. Smith

CoRR, 2020

Batch Normalization Biases Residual Blocks Towards the Identity Function in Deep Networks.

Soham De, Samuel L. Smith

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

On the Generalization Benefit of Noise in Stochastic Gradient Descent.

Samuel L. Smith, Erich Elsen, Soham De

Proceedings of the 37th International Conference on Machine Learning, 2020

2019

The Effect of Network Width on Stochastic Gradient Descent and Generalization: an Empirical Study.

Daniel S. Park, Jascha Sohl-Dickstein, Quoc V. Le, Samuel L. Smith

Proceedings of the 36th International Conference on Machine Learning, 2019

2018

Stochastic natural gradient descent draws posterior samples in function space.

Samuel L. Smith, Daniel Duckworth, Quoc V. Le, Jascha Sohl-Dickstein

CoRR, 2018

Decoding Decoders: Finding Optimal Representation Spaces for Unsupervised Similarity Tasks.

Vitalii Zhelezniak, Dan Busbridge, April Shen, Samuel L. Smith, Nils Y. Hammerla

Proceedings of the 6th International Conference on Learning Representations, 2018

A Bayesian Perspective on Generalization and Stochastic Gradient Descent.

Samuel L. Smith, Quoc V. Le

Proceedings of the 6th International Conference on Learning Representations, 2018

Don't Decay the Learning Rate, Increase the Batch Size.

Samuel L. Smith, Pieter-Jan Kindermans, Chris Ying, Quoc V. Le

Proceedings of the 6th International Conference on Learning Representations, 2018

2017

Don't Decay the Learning Rate, Increase the Batch Size.

Samuel L. Smith, Pieter-Jan Kindermans, Quoc V. Le

CoRR, 2017

Offline bilingual word vectors, orthogonal transformations and the inverted softmax.

Samuel L. Smith, David H. P. Turban, Steven Hamblin, Nils Y. Hammerla

Proceedings of the 5th International Conference on Learning Representations, 2017

2016

Monte Carlo Sort for unreliable human comparisons.

Samuel L. Smith

CoRR, 2016