David W. Romero

According to our database, David W. Romero authored at least 19 papers between 2020 and 2024.

Collaborative distances:

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

2024

Wavelet Networks: Scale-Translation Equivariant Learning From Raw Time-Series.

David W. Romero, Erik J. Bekkers, Jakub M. Tomczak, Mark Hoogendoorn

Trans. Mach. Learn. Res., 2024

Fast, Expressive SE(n) Equivariant Networks through Weight-Sharing in Position-Orientation Space.

Erik J. Bekkers, Sharvaree P. Vadgama, Rob Hesselink, Putri A. van der Linden, David W. Romero

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Self-Supervised Detection of Perfect and Partial Input-Dependent Symmetries.

Alonso Urbano, David W. Romero

CoRR, 2023

DNArch: Learning Convolutional Neural Architectures by Backpropagation.

David W. Romero, Neil Zeghidour

CoRR, 2023

Learned Gridification for Efficient Point Cloud Processing.

Putri A. van der Linden, David W. Romero, Erik J. Bekkers

Proceedings of the Topological, 2023

Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions.

Stefano Massaroli, Michael Poli, Daniel Y. Fu, Hermann Kumbong, Rom N. Parnichkun, David W. Romero, Aman Timalsina, Quinn McIntyre, Beidi Chen, Atri Rudra, Ce Zhang, Christopher Ré, Stefano Ermon, Yoshua Bengio

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Modelling Long Range Dependencies in $N$D: From Task-Specific to a General Purpose CNN.

David M. Knigge, David W. Romero, Albert Gu, Efstratios Gavves, Erik J. Bekkers, Jakub Mikolaj Tomczak, Mark Hoogendoorn, Jan-Jakob Sonke

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Towards a General Purpose CNN for Long Range Dependencies in ND.

David W. Romero, David M. Knigge, Albert Gu, Erik J. Bekkers, Efstratios Gavves, Jakub M. Tomczak, Mark Hoogendoorn

CoRR, 2022

Learning Partial Equivariances From Data.

David W. Romero, Suhas Lohit

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Relaxing Equivariance Constraints with Non-stationary Continuous Filters.

Tycho F. A. van der Ouderaa, David W. Romero, Mark van der Wilk

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups.

David M. Knigge, David W. Romero, Erik J. Bekkers

Proceedings of the International Conference on Machine Learning, 2022

CKConv: Continuous Kernel Convolution For Sequential Data.

David W. Romero, Anna Kuzina, Erik J. Bekkers, Jakub Mikolaj Tomczak, Mark Hoogendoorn

Proceedings of the Tenth International Conference on Learning Representations, 2022

FlexConv: Continuous Kernel Convolutions With Differentiable Kernel Sizes.

David W. Romero, Robert-Jan Bruintjes, Jakub Mikolaj Tomczak, Erik J. Bekkers, Mark Hoogendoorn, Jan van Gemert

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Learning Equivariances and Partial Equivariances from Data.

David W. Romero, Suhas Lohit

CoRR, 2021

Group Equivariant Stand-Alone Self-Attention For Vision.

David W. Romero, Jean-Baptiste Cordonnier

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

2020

Wavelet Networks: Scale Equivariant Learning From Raw Waveforms.

David W. Romero, Erik J. Bekkers, Jakub M. Tomczak, Mark Hoogendoorn

CoRR, 2020

Generative Fourier-Based Auto-encoders: Preliminary Results.

Alessandro Zonta, Ali el Hassouni, David W. Romero, Jakub M. Tomczak

Proceedings of the Machine Learning, Optimization, and Data Science, 2020

Attentive Group Equivariant Convolutional Networks.

David W. Romero, Erik J. Bekkers, Jakub M. Tomczak, Mark Hoogendoorn

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

Co-Attentive Equivariant Neural Networks: Focusing Equivariance On Transformations Co-Occurring in Data.

David W. Romero, Mark Hoogendoorn

Proceedings of the 8th International Conference on Learning Representations, 2020