Publications by Tags

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

Selected Papers

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

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

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

Compression

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

Equivariance

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

Extrapolation

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

Generalization

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

Information Theory

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

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

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

Invariance

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

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

Meta Learning

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

NLP

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

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

Representation Learning

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

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

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

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

Robustness

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

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

Self-Supervised Learning

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

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

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

Time Series

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

Uncertainty

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

Vision

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

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

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

Yann Dubois

Publications by Tags

Selected Papers

Compression

Equivariance

Extrapolation

Generalization

Information Theory

Invariance

Meta Learning

NLP

Representation Learning

Robustness

Self-Supervised Learning

Time Series

Uncertainty

Vision