Timezone: »
Self-Supervised Learning (SSL) surmises that inputs and pairwise positive relationships are enough to learn meaningful representations. Although SSL has recently reached a milestone: outperforming supervised methods in many modalities\dots the theoretical foundations are limited, method-specific, and fail to provide principled design guidelines to practitioners. In this paper, we propose a unifying framework under the helm of spectral manifold learning. Through the course of this study, we will demonstrate that VICReg, SimCLR, BarlowTwins et al. correspond to eponymous spectral methods such as Laplacian Eigenmaps, ISOMAP et al.From this unified viewpoint, we obtain (i) the close-form optimal representation, (ii) the close-form optimal network parameters in the linear regime, (iii) the impact of the pairwise relations used during training on each of those quantities and on downstream task performances, and most importantly, (iv) the first theoretical bridge between contrastive and non-contrastive methods to global and local spectral methods respectively hinting at the benefits and limitations of each. For example, if the pairwise relation is aligned with the downstream task, all SSL methods produce optimal representations for that downstream task.
Author Information
Randall Balestriero (Meta AI, FAIR)
Yann LeCun (Facebook)
Yann LeCun is Director of AI Research at Facebook, and Silver Professor of Data Science, Computer Science, Neural Science, and Electrical Engineering at New York University. He received the Electrical Engineer Diploma from ESIEE, Paris in 1983, and a PhD in Computer Science from Université Pierre et Marie Curie (Paris) in 1987. After a postdoc at the University of Toronto, he joined AT&T Bell Laboratories in Holmdel, NJ in 1988. He became head of the Image Processing Research Department at AT&T Labs-Research in 1996, and joined NYU as a professor in 2003, after a brief period as a Fellow of the NEC Research Institute in Princeton. From 2012 to 2014 he directed NYU's initiative in data science and became the founding director of the NYU Center for Data Science. He was named Director of AI Research at Facebook in late 2013 and retains a part-time position on the NYU faculty. His current interests include AI, machine learning, computer perception, mobile robotics, and computational neuroscience. He has published over 180 technical papers and book chapters on these topics as well as on neural networks, handwriting recognition, image processing and compression, and on dedicated circuits for computer perception.
More from the Same Authors
-
2022 : Exact Visualization of Deep Neural Network Geometry and Decision Boundary »
Ahmed Imtiaz Humayun · Randall Balestriero · Richard Baraniuk -
2023 Poster: Understanding the detrimental class-level effects of data augmentation »
Polina Kirichenko · Mark Ibrahim · Randall Balestriero · Diane Bouchacourt · Shanmukha Ramakrishna Vedantam · Hamed Firooz · Andrew Wilson -
2023 Poster: Self-Supervised Learning with Lie Symmetries for Partial Differential Equations »
Grégoire Mialon · Quentin Garrido · Hannah Lawrence · Danyal Rehman · Bobak Kiani · Yann LeCun -
2023 Poster: Reverse Engineering Self-Supervised Learning »
Ido Ben-Shaul · Ravid Shwartz-Ziv · Tomer Galanti · Shai Dekel · Yann LeCun -
2023 Poster: An Information Theory Perspective on Variance-Invariance-Covariance Regularization »
Ravid Shwartz-Ziv · Randall Balestriero · Kenji Kawaguchi · Tim G. J. Rudner · Yann LeCun -
2022 Poster: The Effects of Regularization and Data Augmentation are Class Dependent »
Randall Balestriero · Leon Bottou · Yann LeCun -
2022 Poster: VICRegL: Self-Supervised Learning of Local Visual Features »
Adrien Bardes · Jean Ponce · Yann LeCun -
2022 Poster: Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone »
Zi-Yi Dou · Aishwarya Kamath · Zhe Gan · Pengchuan Zhang · Jianfeng Wang · Linjie Li · Zicheng Liu · Ce Liu · Yann LeCun · Nanyun Peng · Jianfeng Gao · Lijuan Wang -
2022 Poster: Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors »
Ravid Shwartz-Ziv · Micah Goldblum · Hossein Souri · Sanyam Kapoor · Chen Zhu · Yann LeCun · Andrew Wilson -
2022 Poster: A Data-Augmentation Is Worth A Thousand Samples: Analytical Moments And Sampling-Free Training »
Randall Balestriero · Ishan Misra · Yann LeCun -
2022 Poster: projUNN: efficient method for training deep networks with unitary matrices »
Bobak Kiani · Randall Balestriero · Yann LeCun · Seth Lloyd -
2020 : Panel Discussion & Closing »
Yejin Choi · Alexei Efros · Chelsea Finn · Kristen Grauman · Quoc V Le · Yann LeCun · Ruslan Salakhutdinov · Eric Xing -
2020 : QA: Yann LeCun »
Yann LeCun -
2020 : Invited Talk: Yann LeCun »
Yann LeCun -
2020 Poster: Analytical Probability Distributions and Exact Expectation-Maximization for Deep Generative Networks »
Randall Balestriero · Sebastien PARIS · Richard Baraniuk -
2019 : TBD »
Yann LeCun -
2019 Poster: The Geometry of Deep Networks: Power Diagram Subdivision »
Randall Balestriero · Romain Cosentino · Behnaam Aazhang · Richard Baraniuk -
2017 : Panel Session »
Neil Lawrence · Finale Doshi-Velez · Zoubin Ghahramani · Yann LeCun · Max Welling · Yee Whye Teh · Ole Winther -
2017 Tutorial: Geometric Deep Learning on Graphs and Manifolds »
Michael Bronstein · Joan Bruna · arthur szlam · Xavier Bresson · Yann LeCun -
2016 : Discussion panel »
Ian Goodfellow · Soumith Chintala · Arthur Gretton · Sebastian Nowozin · Aaron Courville · Yann LeCun · Emily Denton -
2016 : Energy-Based Adversarial Training and Video Prediction »
Yann LeCun -
2016 Symposium: Deep Learning Symposium »
Yoshua Bengio · Yann LeCun · Navdeep Jaitly · Roger Grosse -
2015 Poster: Learning to Linearize Under Uncertainty »
Ross Goroshin · Michael Mathieu · Yann LeCun -
2015 Poster: Character-level Convolutional Networks for Text Classification »
Xiang Zhang · Junbo (Jake) Zhao · Yann LeCun -
2015 Poster: Deep learning with Elastic Averaging SGD »
Sixin Zhang · Anna Choromanska · Yann LeCun -
2015 Spotlight: Deep learning with Elastic Averaging SGD »
Sixin Zhang · Anna Choromanska · Yann LeCun -
2015 Tutorial: Deep Learning »
Geoffrey E Hinton · Yoshua Bengio · Yann LeCun