Timezone: »
In this paper we propose an approximated learning framework for large scale graphical models and derive message passing algorithms for learning their parameters efficiently. We first relate CRFs and structured SVMs and show that in the CRF's primal a variant of the log-partition function, known as soft-max, smoothly approximates the hinge loss function of structured SVMs. We then propose an intuitive approximation for structured prediction problems using Fenchel duality based on a local entropy approximation that computes the exact gradients of the approximated problem and is guaranteed to converge. Unlike existing approaches, this allow us to learn graphical models with cycles and very large number of parameters efficiently. We demonstrate the effectiveness of our approach in an image denoising task. This task was previously solved by sharing parameters across cliques. In contrast, our algorithm is able to efficiently learn large number of parameters resulting in orders of magnitude better prediction.
Author Information
Tamir Hazan (Technion)
Raquel Urtasun (University of Toronto)
More from the Same Authors
-
2021 Spotlight: Learning Generalized Gumbel-max Causal Mechanisms »
Guy Lorberbom · Daniel D. Johnson · Chris Maddison · Daniel Tarlow · Tamir Hazan -
2023 Poster: Neural Lighting Simulation for Urban Scenes »
Ava Pun · Gary Sun · Jingkang Wang · Yun Chen · Ze Yang · Sivabalan Manivasagam · Wei-Chiu Ma · Raquel Urtasun -
2022 Poster: On the Importance of Gradient Norm in PAC-Bayesian Bounds »
Itai Gat · Yossi Adi · Alex Schwing · Tamir Hazan -
2021 Poster: Learning Generalized Gumbel-max Causal Mechanisms »
Guy Lorberbom · Daniel D. Johnson · Chris Maddison · Daniel Tarlow · Tamir Hazan -
2020 Poster: Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies »
Itai Gat · Idan Schwartz · Alex Schwing · Tamir Hazan -
2020 Poster: Direct Policy Gradients: Direct Optimization of Policies in Discrete Action Spaces »
Guy Lorberbom · Chris Maddison · Nicolas Heess · Tamir Hazan · Danny Tarlow -
2019 : Carl Doersch, Raquel Urtasun, Sanja Fidler moderated by Natalia Neverova »
Raquel Urtasun · Sanja Fidler · Natalia Neverova · Ilija Radosavovic · Carl Doersch -
2019 : Raquel Urtasun - Science and Engineering for Self-driving »
Raquel Urtasun -
2019 Poster: Direct Optimization through $\arg \max$ for Discrete Variational Auto-Encoder »
Guy Lorberbom · Andreea Gane · Tommi Jaakkola · Tamir Hazan -
2018 Poster: Neural Guided Constraint Logic Programming for Program Synthesis »
Lisa Zhang · Gregory Rosenblatt · Ethan Fetaya · Renjie Liao · William Byrd · Matthew Might · Raquel Urtasun · Richard Zemel -
2017 : Machine Learning for Self-Driving Cars, Raquel Urtasun, Uber ATG and University of Toronto »
Raquel Urtasun -
2017 : Raquel Urtasun: Deep Learning for Self-Driving Cars »
Raquel Urtasun -
2017 Poster: The Reversible Residual Network: Backpropagation Without Storing Activations »
Aidan Gomez · Mengye Ren · Raquel Urtasun · Roger Grosse -
2017 Poster: Few-Shot Learning Through an Information Retrieval Lens »
Eleni Triantafillou · Richard Zemel · Raquel Urtasun -
2017 Poster: High-Order Attention Models for Visual Question Answering »
Idan Schwartz · Alex Schwing · Tamir Hazan -
2016 : Raquel Urtasun »
Raquel Urtasun -
2016 : Invited Talk - TorontoCity Benchmark: Towards Building Large Scale 3D Models of the World »
Raquel Urtasun -
2016 : Invited Talk: Towards Affordable Self-driving Cars (Raquel Urtasun, University of Toronto) »
Raquel Urtasun -
2016 Poster: Proximal Deep Structured Models »
Shenlong Wang · Sanja Fidler · Raquel Urtasun -
2016 Poster: Understanding the Effective Receptive Field in Deep Convolutional Neural Networks »
Wenjie Luo · Yujia Li · Raquel Urtasun · Richard Zemel -
2016 Poster: Constraints Based Convex Belief Propagation »
Yaniv Tenzer · Alex Schwing · Kevin Gimpel · Tamir Hazan -
2016 Poster: Learning Deep Parsimonious Representations »
Renjie Liao · Alex Schwing · Richard Zemel · 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 -
2014 Workshop: Perturbations, Optimization, and Statistics »
Tamir Hazan · George Papandreou · Danny Tarlow -
2014 Poster: Efficient Inference of Continuous Markov Random Fields with Polynomial Potentials »
Shenlong Wang · Alex Schwing · Raquel Urtasun -
2014 Poster: Message Passing Inference for Large Scale Graphical Models with High Order Potentials »
Jian Zhang · Alex Schwing · Raquel Urtasun -
2013 Workshop: Perturbations, Optimization, and Statistics »
Tamir Hazan · George Papandreou · Sasha Rakhlin · Danny Tarlow -
2013 Poster: Learning Efficient Random Maximum A-Posteriori Predictors with Non-Decomposable Loss Functions »
Tamir Hazan · Subhransu Maji · Joseph Keshet · Tommi Jaakkola -
2013 Poster: Latent Structured Active Learning »
Wenjie Luo · Alex Schwing · Raquel Urtasun -
2013 Poster: On Sampling from the Gibbs Distribution with Random Maximum A-Posteriori Perturbations »
Tamir Hazan · Subhransu Maji · Tommi Jaakkola -
2012 Workshop: Perturbations, Optimization, and Statistics »
Tamir Hazan · George Papandreou · Danny Tarlow -
2012 Poster: 3D Object Detection and Viewpoint Estimation with a Deformable 3D Cuboid Model »
Sanja Fidler · Sven Dickinson · Raquel Urtasun -
2012 Poster: Globally Convergent Dual MAP LP Relaxation Solvers using Fenchel-Young Margins »
Alex Schwing · Tamir Hazan · Marc Pollefeys · Raquel Urtasun -
2012 Spotlight: 3D Object Detection and Viewpoint Estimation with a Deformable 3D Cuboid Model »
Sanja Fidler · Sven Dickinson · Raquel Urtasun -
2012 Session: Oral Session 1 »
Raquel Urtasun -
2011 Session: Spotlight Session 5 »
Raquel Urtasun -
2011 Session: Oral Session 6 »
Raquel Urtasun -
2011 Poster: Learning Probabilistic Non-Linear Latent Variable Models for Tracking Complex Activities »
Angela Yao · Juergen Gall · Luc V Gool · Raquel Urtasun -
2011 Poster: Joint 3D Estimation of Objects and Scene Layout »
Andreas Geiger · Christian Wojek · Raquel Urtasun -
2010 Poster: Sparse Coding for Learning Interpretable Spatio-Temporal Primitives »
Taehwan Kim · Greg Shakhnarovich · Raquel Urtasun -
2010 Session: Spotlights Session 6 »
Raquel Urtasun -
2010 Session: Oral Session 7 »
Raquel Urtasun -
2010 Poster: Implicitly Constrained Gaussian Process Regression for Monocular Non-Rigid Pose Estimation »
Mathieu Salzmann · Raquel Urtasun -
2010 Poster: Direct Loss Minimization for Structured Prediction »
David A McAllester · Tamir Hazan · Joseph Keshet