Timezone: »
We derive information theoretic generalization bounds for supervised learning algorithms based on a new measure of leave-one-out conditional mutual information (loo-CMI). In contrast to other CMI bounds, which may be hard to evaluate in practice, our loo-CMI bounds are easier to compute and can be interpreted in connection to other notions such as classical leave-one-out cross-validation, stability of the optimization algorithm, and the geometry of the loss-landscape. It applies both to the output of training algorithms as well as their predictions. We empirically validate the quality of the bound by evaluating its predicted generalization gap in scenarios for deep learning. In particular, our bounds are non-vacuous on image-classification tasks.
Author Information
Mohamad Rida Rammal (University of California, Los Angeles)
Alessandro Achille (AWS)
Aditya Golatkar (University of California, Los Angeles)
Suhas Diggavi (UCLA)
Stefano Soatto (UCLA)
Stefano Soatto received his Ph.D. in Control and Dynamical Systems from the California Institute of Technology in 1996; he joined UCLA in 2000 after being Assistant and then Associate Professor of Electrical Engineering and Biomedical Engineering at Washington University, and Research Associate in Applied Sciences at Harvard University. Between 1995 and 1998 he was also Ricercatore in the Department of Mathematics and Computer Science at the University of Udine - Italy. He received his D.Ing. degree (highest honors) from the University of Padova- Italy in 1992. His general research interests are in Computer Vision and Nonlinear Estimation and Control Theory. In particular, he is interested in ways for computers to use sensory information to interact with humans and the environment. Dr. Soatto is the recipient of the David Marr Prize for work on Euclidean reconstruction and reprojection up to subgroups. He also received the Siemens Prize with the Outstanding Paper Award from the IEEE Computer Society for his work on optimal structure from motion. He received the National Science Foundation Career Award and the Okawa Foundation Grant. He is a Member of the Editorial Board of the International Journal of Computer Vision (IJCV) and Foundations and Trends in Computer Graphics and Vision. He is the founder and director of the UCLA Vision Lab; more information is available at http://vision.ucla.edu
More from the Same Authors
-
2021 Spotlight: Uniform Sampling over Episode Difficulty »
Sébastien Arnold · Guneet Dhillon · Avinash Ravichandran · Stefano Soatto -
2021 Spotlight: Long Short-Term Transformer for Online Action Detection »
Mingze Xu · Yuanjun Xiong · Hao Chen · Xinyu Li · Wei Xia · Zhuowen Tu · Stefano Soatto -
2022 : Evaluating Worst Case Adversarial Weather Perturbations Robustness »
Yihan Wang · Yunhao Ba · Howard Zhang · Huan Zhang · Achuta Kadambi · Stefano Soatto · Alex Wong · Cho-Jui Hsieh -
2023 Poster: FOCAL: Contrastive Learning for Multimodal Time-Series Sensing Signals in Factorized Orthogonal Latent Space »
Shengzhong Liu · Tomoyoshi Kimura · Dongxin Liu · Ruijie Wang · Jinyang Li · Suhas Diggavi · Mani Srivastava · Tarek Abdelzaher -
2023 Poster: Gacs-Korner Common Information Variational Autoencoder »
Michael Kleinman · Alessandro Achille · Stefano Soatto · Jonathan Kao -
2023 Poster: Your representations are in the network: composable and parallel adaptation for large scale models »
Yonatan Dukler · Alessandro Achille · Hao Yang · Varsha Vivek · Luca Zancato · Benjamin Bowman · Avinash Ravichandran · Charless Fowlkes · Ashwin Swaminathan · Stefano Soatto -
2023 Poster: Leveraging sparse and shared feature activations for disentangled representation learning »
Marco Fumero · Florian Wenzel · Luca Zancato · Alessandro Achille · Emanuele Rodolà · Stefano Soatto · Bernhard Schölkopf · Francesco Locatello -
2022 Poster: Semi-supervised Vision Transformers at Scale »
Zhaowei Cai · Avinash Ravichandran · Paolo Favaro · Manchen Wang · Davide Modolo · Rahul Bhotika · Zhuowen Tu · Stefano Soatto -
2021 Poster: Uniform Sampling over Episode Difficulty »
Sébastien Arnold · Guneet Dhillon · Avinash Ravichandran · Stefano Soatto -
2021 Poster: Long Short-Term Transformer for Online Action Detection »
Mingze Xu · Yuanjun Xiong · Hao Chen · Xinyu Li · Wei Xia · Zhuowen Tu · Stefano Soatto -
2021 Poster: Renyi Differential Privacy of The Subsampled Shuffle Model In Distributed Learning »
Antonious Girgis · Deepesh Data · Suhas Diggavi -
2021 Poster: QuPeD: Quantized Personalization via Distillation with Applications to Federated Learning »
Kaan Ozkara · Navjot Singh · Deepesh Data · Suhas Diggavi -
2019 : Invited Talk: Stefano Soatto and Alessandro Achille »
Stefano Soatto · Alessandro Achille -
2019 Poster: Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence »
Aditya Sharad Golatkar · Alessandro Achille · Stefano Soatto -
2019 Poster: Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification and Local Computations »
Debraj Basu · Deepesh Data · Can Karakus · Suhas Diggavi -
2018 : Plenary Talk 3 »
Stefano Soatto -
2018 Poster: Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies »
Alessandro Achille · Tom Eccles · Loic Matthey · Chris Burgess · Nicholas Watters · Alexander Lerchner · Irina Higgins -
2018 Spotlight: Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies »
Alessandro Achille · Tom Eccles · Loic Matthey · Chris Burgess · Nicholas Watters · Alexander Lerchner · Irina Higgins -
2017 Poster: Straggler Mitigation in Distributed Optimization Through Data Encoding »
Can Karakus · Yifan Sun · Suhas Diggavi · Wotao Yin -
2017 Spotlight: Straggler Mitigation in Distributed Optimization Through Data Encoding »
Can Karakus · Yifan Sun · Suhas Diggavi · Wotao Yin -
2011 Poster: Randomized Algorithms for Comparison-based Search »
Dominique Tschopp · Suhas Diggavi · Payam Delgosha · Soheil Mohajer -
2010 Tutorial: Vision-Based Control, Control-Based Vision, and the Information Knot That Ties Them »
Stefano Soatto -
2010 Poster: Occlusion Detection and Motion Estimation with Convex Optimization »
Alper Ayvaci · Michalis Raptis · Stefano Soatto -
2006 Poster: Detecting Humans via Their Pose »
Alessandro Bissacco · Ming-Hsuan Yang · Stefano Soatto