Timezone: »
Although machine learning models trained on massive data have led to breakthroughs in several areas, their deployment in privacy-sensitive domains remains limited due to restricted access to data. Generative models trained with privacy constraints on private data can sidestep this challenge, providing indirect access to private data instead. We propose DP-Sinkhorn, a novel optimal transport-based generative method for learning data distributions from private data with differential privacy. DP-Sinkhorn minimizes the Sinkhorn divergence, a computationally efficient approximation to the exact optimal transport distance, between the model and data in a differentially private manner and uses a novel technique for controlling the bias-variance trade-off of gradient estimates. Unlike existing approaches for training differentially private generative models, which are mostly based on generative adversarial networks, we do not rely on adversarial objectives, which are notoriously difficult to optimize, especially in the presence of noise imposed by privacy constraints. Hence, DP-Sinkhorn is easy to train and deploy. Experimentally, we improve upon the state-of-the-art on multiple image modeling benchmarks and show differentially private synthesis of informative RGB images.
Author Information
Tianshi Cao (University of Toronto)
Alex Bie (University of Waterloo)
Arash Vahdat (NVIDIA Research)
Sanja Fidler (University of Toronto)
Karsten Kreis (NVIDIA)
More from the Same Authors
-
2020 : Differentially Private Generative Models Through Optimal Transport »
Karsten Kreis -
2022 : Latent Space Diffusion Models of Cryo-EM Structures »
Karsten Kreis · Tim Dockhorn · Zihao Li · Ellen Zhong -
2022 : How many trained neural networks are needed for influence estimation in modern deep learning? »
Sasha (Alexandre) Doubov · Tianshi Cao · David Acuna · Sanja Fidler -
2023 Poster: Private Distribution Learning with Public Data: The View from Sample Compression »
Shai Ben-David · Alex Bie · Clément L Canonne · Gautam Kamath · Vikrant Singhal -
2023 Poster: Distribution Learnability and Robustness »
Shai Ben-David · Alex Bie · Gautam Kamath · Tosca Lechner -
2023 Tutorial: Latent Diffusion Models: Is the Generative AI Revolution Happening in Latent Space? »
· Arash Vahdat · Karsten Kreis -
2022 : Latent Space Diffusion Models of Cryo-EM Structures »
Karsten Kreis · Tim Dockhorn · Zihao Li · Ellen Zhong -
2022 : Private GANs, Revisited »
Alex Bie · Gautam Kamath · Guojun Zhang -
2022 : Invited talk: Karsten Kreis »
Karsten Kreis -
2022 Poster: Private Estimation with Public Data »
Alex Bie · Gautam Kamath · Vikrant Singhal -
2021 Poster: Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis »
Tianchang Shen · Jun Gao · Kangxue Yin · Ming-Yu Liu · Sanja Fidler -
2021 Poster: Scalable Neural Data Server: A Data Recommender for Transfer Learning »
Tianshi Cao · Sasha (Alexandre) Doubov · David Acuna · Sanja Fidler -
2021 Poster: DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderer »
Wenzheng Chen · Joey Litalien · Jun Gao · Zian Wang · Clement Fuji Tsang · Sameh Khamis · Or Litany · Sanja Fidler -
2021 Poster: A Contrastive Learning Approach for Training Variational Autoencoder Priors »
Jyoti Aneja · Alex Schwing · Jan Kautz · Arash Vahdat -
2021 Poster: EditGAN: High-Precision Semantic Image Editing »
Huan Ling · Karsten Kreis · Daiqing Li · Seung Wook Kim · Antonio Torralba · Sanja Fidler -
2021 Poster: Score-based Generative Modeling in Latent Space »
Arash Vahdat · Karsten Kreis · Jan Kautz -
2021 Poster: Controllable and Compositional Generation with Latent-Space Energy-Based Models »
Weili Nie · Arash Vahdat · Anima Anandkumar -
2021 Poster: ATISS: Autoregressive Transformers for Indoor Scene Synthesis »
Despoina Paschalidou · Amlan Kar · Maria Shugrina · Karsten Kreis · Andreas Geiger · Sanja Fidler -
2021 Poster: Towards Optimal Strategies for Training Self-Driving Perception Models in Simulation »
David Acuna · Jonah Philion · Sanja Fidler -
2020 : Sanja Fidler »
Sanja Fidler -
2020 Poster: Variational Amodal Object Completion »
Huan Ling · David Acuna · Karsten Kreis · Seung Wook Kim · Sanja Fidler -
2020 Poster: Learning Deformable Tetrahedral Meshes for 3D Reconstruction »
Jun Gao · Wenzheng Chen · Tommy Xiang · Alec Jacobson · Morgan McGuire · Sanja Fidler -
2019 : Carl Doersch, Raquel Urtasun, Sanja Fidler moderated by Natalia Neverova »
Raquel Urtasun · Sanja Fidler · Natalia Neverova · Ilija Radosavovic · Carl Doersch -
2019 : Sanja Fidler - TBA »
Sanja Fidler -
2019 : Panel »
Sanja Fidler · Josh Tenenbaum · Tatiana López-Guevara · Danilo Jimenez Rezende · Niloy Mitra -
2019 : Sanja Fidler »
Sanja Fidler -
2019 Poster: Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer »
Wenzheng Chen · Huan Ling · Jun Gao · Edward Smith · Jaakko Lehtinen · Alec Jacobson · Sanja Fidler -
2019 Demonstration: Toronto Annotation Suite »
Amlan Kar · Sanja Fidler · Jun Gao · Seung Wook Kim · Huan Ling -
2018 Poster: A Neural Compositional Paradigm for Image Captioning »
Bo Dai · Sanja Fidler · Dahua Lin -
2017 : Panel Discussion »
Felix Hill · Olivier Pietquin · Jack Gallant · Raymond Mooney · Sanja Fidler · Chen Yu · Devi Parikh -
2017 : Connecting high-level semantics with low-level vision »
Sanja Fidler -
2017 Poster: Teaching Machines to Describe Images with Natural Language Feedback »
Huan Ling · Sanja Fidler -
2017 Poster: Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks »
Arash Vahdat -
2016 Poster: Proximal Deep Structured Models »
Shenlong Wang · Sanja Fidler · Raquel Urtasun -
2015 Poster: Skip-Thought Vectors »
Jamie Kiros · Yukun Zhu · Russ Salakhutdinov · Richard Zemel · Raquel Urtasun · Antonio Torralba · Sanja Fidler -
2015 Poster: 3D Object Proposals for Accurate Object Class Detection »
Xiaozhi Chen · Kaustav Kundu · Yukun Zhu · Andrew G Berneshawi · Huimin Ma · Sanja Fidler · Raquel Urtasun -
2012 Poster: 3D Object Detection and Viewpoint Estimation with a Deformable 3D Cuboid Model »
Sanja Fidler · Sven Dickinson · Raquel Urtasun -
2012 Spotlight: 3D Object Detection and Viewpoint Estimation with a Deformable 3D Cuboid Model »
Sanja Fidler · Sven Dickinson · Raquel Urtasun -
2009 Poster: Evaluating multi-class learning strategies in a generative hierarchical framework for object detection »
Sanja Fidler · Marko Boben · Ales Leonardis