Timezone: »
We consider sequential prediction algorithms that are given the predictions from a set of models as inputs. If the nature of the data is changing over time in that different models predict well on different segments of the data, then adaptivity is typically achieved by mixing into the weights in each round a bit of the initial prior (kind of like a weak restart). However, what if the favored models in each segment are from a small subset, i.e. the data is likely to be predicted well by models that predicted well before? Curiously, fitting such ''sparse composite models'' is achieved by mixing in a bit of all the past posteriors. This self-referential updating method is rather peculiar, but it is efficient and gives superior performance on many natural data sets. Also it is important because it introduces a long-term memory: any model that has done well in the past can be recovered quickly. While Bayesian interpretations can be found for mixing in a bit of the initial prior, no Bayesian interpretation is known for mixing in past posteriors. We build atop the ''specialist'' framework from the online learning literature to give the Mixing Past Posteriors update a proper Bayesian foundation. We apply our method to a well-studied multitask learning problem and obtain a new intriguing efficient update that achieves a significantly better bound.
Author Information
Wouter M Koolen (Centrum Wiskunde & Informatica, Amsterdam)
Dmitri Adamskiy (Royal Holloway, University of London)
Manfred K. Warmuth (Google Brain)
Related Events (a corresponding poster, oral, or spotlight)
-
2012 Poster: Putting Bayes to sleep »
Wed. Dec 5th through Tue the 4th Room Harrah’s Special Events Center 2nd Floor
More from the Same Authors
-
2020 Poster: Reparameterizing Mirror Descent as Gradient Descent »
Ehsan Amid · Manfred K. Warmuth -
2019 Workshop: Minding the Gap: Between Fairness and Ethics »
Igor Rubinov · Risi Kondor · Jack Poulson · Manfred K. Warmuth · Emanuel Moss · Alexa Hagerty -
2019 : Opening Remarks »
Jack Poulson · Manfred K. Warmuth -
2019 Poster: Robust Bi-Tempered Logistic Loss Based on Bregman Divergences »
Ehsan Amid · Manfred K. Warmuth · Rohan Anil · Tomer Koren -
2018 Poster: Leveraged volume sampling for linear regression »
Michal Derezinski · Manfred K. Warmuth · Daniel Hsu -
2018 Spotlight: Leveraged volume sampling for linear regression »
Michal Derezinski · Manfred K. Warmuth · Daniel Hsu -
2017 Poster: Online Dynamic Programming »
Holakou Rahmanian · Manfred K. Warmuth -
2017 Poster: Unbiased estimates for linear regression via volume sampling »
Michal Derezinski · Manfred K. Warmuth -
2017 Spotlight: Unbiased estimates for linear regression via volume sampling »
Michal Derezinski · Manfred K. Warmuth -
2014 Poster: The limits of squared Euclidean distance regularization »
Michal Derezinski · Manfred K. Warmuth -
2014 Spotlight: The limits of squared Euclidean distance regularization »
Michal Derezinski · Manfred K. Warmuth -
2014 Poster: Efficient Minimax Strategies for Square Loss Games »
Wouter M Koolen · Alan Malek · Peter Bartlett -
2014 Poster: Learning the Learning Rate for Prediction with Expert Advice »
Wouter M Koolen · Tim van Erven · Peter Grünwald -
2013 Workshop: Learning Faster From Easy Data »
Peter Grünwald · Wouter M Koolen · Sasha Rakhlin · Nati Srebro · Alekh Agarwal · Karthik Sridharan · Tim van Erven · Sebastien Bubeck -
2013 Workshop: Large Scale Matrix Analysis and Inference »
Reza Zadeh · Gunnar Carlsson · Michael Mahoney · Manfred K. Warmuth · Wouter M Koolen · Nati Srebro · Satyen Kale · Malik Magdon-Ismail · Ashish Goel · Matei A Zaharia · David Woodruff · Ioannis Koutis · Benjamin Recht -
2013 Poster: The Pareto Regret Frontier »
Wouter M Koolen -
2011 Poster: Adaptive Hedge »
Tim van Erven · Peter Grünwald · Wouter M Koolen · Steven D Rooij -
2011 Poster: Learning Eigenvectors for Free »
Wouter M Koolen · Wojciech Kotlowski · Manfred K. Warmuth -
2010 Poster: Repeated Games against Budgeted Adversaries »
Jacob D Abernethy · Manfred K. Warmuth -
2007 Spotlight: Boosting Algorithms for Maximizing the Soft Margin »
Manfred K. Warmuth · Karen Glocer · Gunnar Rätsch -
2007 Poster: Boosting Algorithms for Maximizing the Soft Margin »
Manfred K. Warmuth · Karen Glocer · Gunnar Rätsch -
2006 Poster: Randomized PCA Algorithms with Regret Bounds that are Logarithmic in the Dimension »
Manfred K. Warmuth · Dima Kuzmin