Publications

Last Updated: Oct. 2022.
An up to date list of all publications can be found on my Google Scholar profile.

Filter: Selected Papers Compression, Equivariance, Extrapolation, Generalization, Information Theory, Invariance, Meta Learning, NLP, Representation Learning, Robustness, Self-Supervised Learning, Time Series, Uncertainty, Vision

2022

Is a Caption Worth a Thousand Images? A Controlled Study for Representation Learning

S. Santurkar, Y. Dubois, R. Taori, P. Liang, T. Hashimoto

Arxiv

TLDR: Our work performs a systematic investigation into whether additional language supervision (in CLIP) helps models learn more transferrable representations.

NLP, Representation Learning, Self-Supervised Learning, Vision

Learning Instance-Specific Data Augmentations

N. Miao, E. Mathieu, Y. Dubois, T. Rainforth, Y. W. Teh, A. Foster, H. Kim

Arxiv

TLDR: We introduce a method for automatically learning input-specific augmentations from data.

Invariance, Vision

Improving Self-Supervised Learning by Characterizing Idealized Representations

Y. Dubois, T. Hashimoto, S. Ermon, P. Liang

NeurIPS 2022

TLDR: We characterize idealized self-supervised representations, which leads to actionable insights for improving SSL algorithms.

Selected Papers Invariance, Representation Learning, Self-Supervised Learning, Vision

Optimal Representations for Covariate Shifts

Y Ruan*, Y. Dubois*, C. J. Maddison

ICLR 2021

TLDR: We give a simple variational objective whose optima are exactly the set of representations that are robust under covariate shift.

Selected Papers Information Theory, Invariance, Representation Learning, Robustness, Self-Supervised Learning, Vision

2021

Lossy Compression for Lossless Prediction

Y. Dubois, B. Bloem-Reddy, K. Ullrich, C. J. Maddison

NeurIPS 2021 Spotlight Presentation 🎉

TLDR: We formalize compression with respect to ML algorithms rather than human perception.

Selected Papers Compression, Information Theory, Invariance, Representation Learning, Self-Supervised Learning, Vision

2020

Learning Optimal Representations with the Decodable Information Bottleneck

Y. Dubois, D. Kiela, D. J. Schwab, R. Vedantam

NeurIPS 2020 Spotlight Presentation 🎉

TLDR: We characterize and approximate optimal representations for supervised learning.

Selected Papers Generalization, Information Theory, Representation Learning, Vision

Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processes

A. Y. K. Foong*, W. P. Bruinsma*, J. Gordon*, Y. Dubois, J. Requeima, R. E. Turner

NeurIPS 2020

TLDR: We propose a translation equivariant (latent) neural process.

Equivariance, Extrapolation, Meta Learning, Time Series, Uncertainty, Vision

Convolutional Conditional Neural Processes

J. Gordon*, W. P. Bruinsma*, A. Y. K. Foong, J. Requeima,Y. Dubois, R. E. Turner

ICLR 2020 Oral Presentation 🎉

TLDR: We propose a translation equivariant conditional neural process.

Equivariance, Extrapolation, Meta Learning, Time Series, Uncertainty, Vision

Location Attention for Extrapolation to Longer Sequences

Y. Dubois, Gautier Dagan, Dieuwke Hupkes, Elia Bruni

ACL 2020

TLDR: We propose an attention that improves extrapolation capacity of neural NLP models.

Extrapolation, NLP, Robustness

Yann Dubois

Publications

2022

2021

2020