Timezone: »
Deep learning and Bayesian learning are considered two entirely different fields often used in complementary settings. It is clear that combining ideas from the two fields would be beneficial, but how can we achieve this given their fundamental differences?
This tutorial will introduce modern Bayesian principles to bridge this gap. Using these principles, we can derive a range of learning-algorithms as special cases, e.g., from classical algorithms, such as linear regression and forward-backward algorithms, to modern deep-learning algorithms, such as SGD, RMSprop and Adam. This view then enables new ways to improve aspects of deep learning, e.g., with uncertainty, robustness, and interpretation. It also enables the design of new methods to tackle challenging problems, such as those arising in active learning, continual learning, reinforcement learning, etc.
Overall, our goal is to bring Bayesians and deep-learners closer than ever before, and motivate them to work together to solve challenging real-world problems by combining their strengths.
Author Information
Mohammad Emtiyaz Khan (RIKEN)
Emtiyaz Khan (also known as Emti) is a team leader at the RIKEN center for Advanced Intelligence Project (AIP) in Tokyo where he leads the Approximate Bayesian Inference Team. He is also a visiting professor at the Tokyo University of Agriculture and Technology (TUAT). Previously, he was a postdoc and then a scientist at Ecole Polytechnique Fédérale de Lausanne (EPFL), where he also taught two large machine learning courses and received a teaching award. He finished his PhD in machine learning from University of British Columbia in 2012. The main goal of Emti’s research is to understand the principles of learning from data and use them to develop algorithms that can learn like living beings. For the past 10 years, his work has focused on developing Bayesian methods that could lead to such fundamental principles. The approximate Bayesian inference team now continues to use these principles, as well as derive new ones, to solve real-world problems.
More from the Same Authors
-
2021 : Beyond Target Networks: Improving Deep $Q$-learning with Functional Regularization »
Alexandre Piche · Joseph Marino · Gian Maria Marconi · Valentin Thomas · Chris Pal · Mohammad Emtiyaz Khan -
2022 : Can Calibration Improve Sample Prioritization? »
Ganesh Tata · Gautham Krishna Gudur · Gopinath Chennupati · Mohammad Emtiyaz Khan -
2022 : Practical Structured Riemannian Optimization with Momentum by using Generalized Normal Coordinates »
Wu Lin · Valentin Duruisseaux · Melvin Leok · Frank Nielsen · Mohammad Emtiyaz Khan · Mark Schmidt -
2022 : Invited Keynote 2 »
Mohammad Emtiyaz Khan · Mohammad Emtiyaz Khan -
2021 Poster: Dual Parameterization of Sparse Variational Gaussian Processes »
Vincent ADAM · Paul Chang · Mohammad Emtiyaz Khan · Arno Solin -
2021 Poster: Knowledge-Adaptation Priors »
Mohammad Emtiyaz Khan · Siddharth Swaroop -
2019 Poster: Approximate Inference Turns Deep Networks into Gaussian Processes »
Mohammad Emtiyaz Khan · Alexander Immer · Ehsan Abedi · Maciej Korzepa -
2019 Poster: Practical Deep Learning with Bayesian Principles »
Kazuki Osawa · Siddharth Swaroop · Mohammad Emtiyaz Khan · Anirudh Jain · Runa Eschenhagen · Richard Turner · Rio Yokota -
2015 Poster: Kullback-Leibler Proximal Variational Inference »
Mohammad Emtiyaz Khan · Pierre Baque · François Fleuret · Pascal Fua -
2014 Poster: Decoupled Variational Gaussian Inference »
Mohammad Emtiyaz Khan -
2012 Poster: Fast Bayesian Inference for Non-Conjugate Gaussian Process Regression »
Mohammad Emtiyaz Khan · Shakir Mohamed · Kevin Murphy -
2010 Poster: Variational bounds for mixed-data factor analysis »
Mohammad Emtiyaz Khan · Benjamin Marlin · Guillaume Bouchard · Kevin Murphy -
2009 Oral: Accelerating Bayesian Structural Inference for Non-Decomposable Gaussian Graphical Models »
Baback Moghaddam · Benjamin Marlin · Mohammad Emtiyaz Khan · Kevin Murphy -
2009 Poster: Accelerating Bayesian Structural Inference for Non-Decomposable Gaussian Graphical Models »
Baback Moghaddam · Benjamin Marlin · Mohammad Emtiyaz Khan · Kevin Murphy