Timezone: »
Estimating and optimizing Mutual Information (MI) is core to many problems in machine learning, but bounding MI in high dimensions is challenging. To establish tractable and scalable objectives, recent work has turned to variational bounds parameterized by neural networks. However, the relationships and tradeoffs between these bounds remains unclear. In this work, we unify these recent developments in a single framework. We find that the existing variational lower bounds degrade when the MI is large, exhibiting either high bias or high variance. To address this problem, we introduce a continuum of lower bounds that encompasses previous bounds and flexibly trades off bias and variance. On high-dimensional, controlled problems, we empirically characterize the bias and variance of the bounds and their gradients and demonstrate the effectiveness of these new bounds for estimation and representation learning.
Author Information
Ben Poole (Google Brain)
Sherjil Ozair (University of Montreal)
Aäron van den Oord (Google Deepmind)
Alexander Alemi (Google)
George Tucker (Google Brain)
Related Events (a corresponding poster, oral, or spotlight)
-
2019 Oral: On Variational Bounds of Mutual Information »
Thu. Jun 13th through Fri the 14th Room Grand Ballroom
More from the Same Authors
-
2021 : A Closer Look at the Adversarial Robustness of Information Bottleneck Models »
Iryna Korshunova · David Stutz · Alexander Alemi · Olivia Wiles · Sven Gowal -
2021 : Improved Estimator Selection for Off-Policy Evaluation »
George Tucker -
2021 : Value-Based Deep Reinforcement Learning Requires Explicit Regularization »
Aviral Kumar · Rishabh Agarwal · Aaron Courville · Tengyu Ma · George Tucker · Sergey Levine -
2021 : Pretrained Encoders are All You Need »
Mina Khan · Advait Rane · Srivatsa P · Shriram Chenniappa · Rishabh Anand · Sherjil Ozair · Patricia Maes -
2021 : Value-Based Deep Reinforcement Learning Requires Explicit Regularization »
Aviral Kumar · Rishabh Agarwal · Aaron Courville · Tengyu Ma · George Tucker · Sergey Levine -
2021 : Value-Based Deep Reinforcement Learning Requires Explicit Regularization »
Aviral Kumar · Rishabh Agarwal · Aaron Courville · Tengyu Ma · George Tucker · Sergey Levine -
2023 : Guided Evolution with Binary Predictors for ML Program Search »
John Co-Reyes · Yingjie Miao · George Tucker · Aleksandra Faust · Esteban Real -
2022 Poster: Model Selection in Batch Policy Optimization »
Jonathan Lee · George Tucker · Ofir Nachum · Bo Dai -
2022 Spotlight: Model Selection in Batch Policy Optimization »
Jonathan Lee · George Tucker · Ofir Nachum · Bo Dai -
2022 Poster: Bayesian Imitation Learning for End-to-End Mobile Manipulation »
Yuqing Du · Daniel Ho · Alexander Alemi · Eric Jang · Mohi Khansari -
2022 Spotlight: Bayesian Imitation Learning for End-to-End Mobile Manipulation »
Yuqing Du · Daniel Ho · Alexander Alemi · Eric Jang · Mohi Khansari -
2021 : Value-Based Deep Reinforcement Learning Requires Explicit Regularization »
Aviral Kumar · Rishabh Agarwal · Aaron Courville · Tengyu Ma · George Tucker · Sergey Levine -
2021 Poster: Vector Quantized Models for Planning »
Sherjil Ozair · Yazhe Li · Ali Razavi · Ioannis Antonoglou · Aäron van den Oord · Oriol Vinyals -
2021 Spotlight: Vector Quantized Models for Planning »
Sherjil Ozair · Yazhe Li · Ali Razavi · Ioannis Antonoglou · Aäron van den Oord · Oriol Vinyals -
2020 : Invited Talk: Contrastive Predictive Coding for audio representation learning »
Aäron van den Oord -
2019 Poster: Guided evolutionary strategies: augmenting random search with surrogate gradients »
Niru Maheswaranathan · Luke Metz · George Tucker · Dami Choi · Jascha Sohl-Dickstein -
2019 Oral: Guided evolutionary strategies: augmenting random search with surrogate gradients »
Niru Maheswaranathan · Luke Metz · George Tucker · Dami Choi · Jascha Sohl-Dickstein -
2018 Poster: Parallel WaveNet: Fast High-Fidelity Speech Synthesis »
Aäron van den Oord · Yazhe Li · Igor Babuschkin · Karen Simonyan · Oriol Vinyals · Koray Kavukcuoglu · George van den Driessche · Edward Lockhart · Luis C Cobo · Florian Stimberg · Norman Casagrande · Dominik Grewe · Seb Noury · Sander Dieleman · Erich Elsen · Nal Kalchbrenner · Heiga Zen · Alex Graves · Helen King · Tom Walters · Dan Belov · Demis Hassabis -
2018 Poster: Efficient Neural Audio Synthesis »
Nal Kalchbrenner · Erich Elsen · Karen Simonyan · Seb Noury · Norman Casagrande · Edward Lockhart · Florian Stimberg · Aäron van den Oord · Sander Dieleman · Koray Kavukcuoglu -
2018 Poster: Mutual Information Neural Estimation »
Mohamed Belghazi · Aristide Baratin · Sai Rajeswar · Sherjil Ozair · Yoshua Bengio · R Devon Hjelm · Aaron Courville -
2018 Oral: Parallel WaveNet: Fast High-Fidelity Speech Synthesis »
Aäron van den Oord · Yazhe Li · Igor Babuschkin · Karen Simonyan · Oriol Vinyals · Koray Kavukcuoglu · George van den Driessche · Edward Lockhart · Luis C Cobo · Florian Stimberg · Norman Casagrande · Dominik Grewe · Seb Noury · Sander Dieleman · Erich Elsen · Nal Kalchbrenner · Heiga Zen · Alex Graves · Helen King · Tom Walters · Dan Belov · Demis Hassabis -
2018 Oral: Efficient Neural Audio Synthesis »
Nal Kalchbrenner · Erich Elsen · Karen Simonyan · Seb Noury · Norman Casagrande · Edward Lockhart · Florian Stimberg · Aäron van den Oord · Sander Dieleman · Koray Kavukcuoglu -
2018 Oral: Mutual Information Neural Estimation »
Mohamed Belghazi · Aristide Baratin · Sai Rajeswar · Sherjil Ozair · Yoshua Bengio · R Devon Hjelm · Aaron Courville -
2018 Poster: Smoothed Action Value Functions for Learning Gaussian Policies »
Ofir Nachum · Mohammad Norouzi · George Tucker · Dale Schuurmans -
2018 Poster: The Mirage of Action-Dependent Baselines in Reinforcement Learning »
George Tucker · Surya Bhupatiraju · Shixiang Gu · Richard E Turner · Zoubin Ghahramani · Sergey Levine -
2018 Oral: Smoothed Action Value Functions for Learning Gaussian Policies »
Ofir Nachum · Mohammad Norouzi · George Tucker · Dale Schuurmans -
2018 Oral: The Mirage of Action-Dependent Baselines in Reinforcement Learning »
George Tucker · Surya Bhupatiraju · Shixiang Gu · Richard E Turner · Zoubin Ghahramani · Sergey Levine -
2018 Poster: Adversarial Risk and the Dangers of Evaluating Against Weak Attacks »
Jonathan Uesato · Brendan O'Donoghue · Pushmeet Kohli · Aäron van den Oord -
2018 Poster: Fixing a Broken ELBO »
Alexander Alemi · Ben Poole · Ian Fischer · Joshua V Dillon · Rif Saurous · Kevin Murphy -
2018 Oral: Adversarial Risk and the Dangers of Evaluating Against Weak Attacks »
Jonathan Uesato · Brendan O'Donoghue · Pushmeet Kohli · Aäron van den Oord -
2018 Oral: Fixing a Broken ELBO »
Alexander Alemi · Ben Poole · Ian Fischer · Joshua V Dillon · Rif Saurous · Kevin Murphy -
2017 Poster: Count-Based Exploration with Neural Density Models »
Georg Ostrovski · Marc Bellemare · Aäron van den Oord · Remi Munos -
2017 Talk: Count-Based Exploration with Neural Density Models »
Georg Ostrovski · Marc Bellemare · Aäron van den Oord · Remi Munos -
2017 Poster: Parallel Multiscale Autoregressive Density Estimation »
Scott Reed · Aäron van den Oord · Nal Kalchbrenner · Sergio Gómez Colmenarejo · Ziyu Wang · Yutian Chen · Dan Belov · Nando de Freitas -
2017 Poster: Video Pixel Networks »
Nal Kalchbrenner · Karen Simonyan · Aäron van den Oord · Ivo Danihelka · Oriol Vinyals · Alex Graves · Koray Kavukcuoglu -
2017 Talk: Video Pixel Networks »
Nal Kalchbrenner · Karen Simonyan · Aäron van den Oord · Ivo Danihelka · Oriol Vinyals · Alex Graves · Koray Kavukcuoglu -
2017 Talk: Parallel Multiscale Autoregressive Density Estimation »
Scott Reed · Aäron van den Oord · Nal Kalchbrenner · Sergio Gómez Colmenarejo · Ziyu Wang · Yutian Chen · Dan Belov · Nando de Freitas