Timezone: »
Poster
Minimax Time Series Prediction
Wouter Koolen · Alan Malek · Peter Bartlett · Yasin Abbasi Yadkori
We consider an adversarial formulation of the problem ofpredicting a time series with square loss. The aim is to predictan arbitrary sequence of vectors almost as well as the bestsmooth comparator sequence in retrospect. Our approach allowsnatural measures of smoothness such as the squared norm ofincrements. More generally, we consider a linear time seriesmodel and penalize the comparator sequence through the energy ofthe implied driving noise terms. We derive the minimax strategyfor all problems of this type and show that it can be implementedefficiently. The optimal predictions are linear in the previousobservations. We obtain an explicit expression for the regret interms of the parameters defining the problem. For typical,simple definitions of smoothness, the computation of the optimalpredictions involves only sparse matrices. In the case ofnorm-constrained data, where the smoothness is defined in termsof the squared norm of the comparator's increments, we show thatthe regret grows as $T/\sqrt{\lambda_T}$, where $T$ is the lengthof the game and $\lambda_T$ is an increasing limit on comparatorsmoothness.
Author Information
Wouter Koolen (Centrum Wiskunde & Informatica)
Alan Malek (UC Berkeley)
Peter Bartlett (UC Berkeley)
Yasin Abbasi Yadkori (Queensland University of Technology)
More from the Same Authors
-
2021 : Regret Minimization in Heavy-Tailed Bandits »
Shubhada Agrawal · Sandeep Juneja · Wouter Koolen -
2023 Poster: The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks »
Spencer Frei · Gal Vardi · Peter Bartlett · Nati Srebro -
2023 Poster: Transportability for Bandits with Data from Different Environments »
Alexis Bellot · Alan Malek · Silvia Chiappa -
2023 Poster: Towards Characterizing the First-order Query Complexity of Learning (Approximate) Nash Equilibria in Zero-sum Matrix Games »
Hedi Hadiji · Sarah Sachs · Tim van Erven · Wouter Koolen -
2023 Poster: Context-lumpable stochastic bandits »
Chung-Wei Lee · Qinghua Liu · Yasin Abbasi Yadkori · Chi Jin · Tor Lattimore · Csaba Szepesvari -
2022 Poster: Luckiness in Multiscale Online Learning »
Wouter Koolen · Muriel F. Pérez-Ortiz -
2022 Poster: Anytime-Valid Inference For Multinomial Count Data »
Michael Lindon · Alan Malek -
2021 Poster: Near Optimal Policy Optimization via REPS »
Aldo Pacchiano · Jonathan N Lee · Peter Bartlett · Ofir Nachum -
2021 Poster: On the Theory of Reinforcement Learning with Once-per-Episode Feedback »
Niladri Chatterji · Aldo Pacchiano · Peter Bartlett · Michael Jordan -
2021 Invited Talk: Benign Overfitting »
Peter Bartlett -
2021 Poster: A/B/n Testing with Control in the Presence of Subpopulations »
Yoan Russac · Christina Katsimerou · Dennis Bohle · Olivier Cappé · Aurélien Garivier · Wouter Koolen -
2021 Poster: Adversarial Examples in Multi-Layer Random ReLU Networks »
Peter Bartlett · Sebastien Bubeck · Yeshwanth Cherapanamjeri -
2021 Poster: Optimal Best-Arm Identification Methods for Tail-Risk Measures »
Shubhada Agrawal · Wouter Koolen · Sandeep Juneja -
2021 Poster: Asymptotically Best Causal Effect Identification with Multi-Armed Bandits »
Alan Malek · Silvia Chiappa -
2020 Poster: Model Selection in Contextual Stochastic Bandit Problems »
Aldo Pacchiano · My Phan · Yasin Abbasi Yadkori · Anup Rao · Julian Zimmert · Tor Lattimore · Csaba Szepesvari -
2020 Poster: Preference learning along multiple criteria: A game-theoretic perspective »
Kush Bhatia · Ashwin Pananjady · Peter Bartlett · Anca Dragan · Martin Wainwright -
2019 Poster: Thompson Sampling and Approximate Inference »
My Phan · Yasin Abbasi Yadkori · Justin Domke -
2019 Poster: Bootstrapping Upper Confidence Bound »
Botao Hao · Yasin Abbasi Yadkori · Zheng Wen · Guang Cheng -
2019 Poster: Pure Exploration with Multiple Correct Answers »
Rémy Degenne · Wouter Koolen -
2019 Poster: Non-Asymptotic Pure Exploration by Solving Games »
Rémy Degenne · Wouter Koolen · Pierre Ménard -
2018 Poster: Sequential Test for the Lowest Mean: From Thompson to Murphy Sampling »
Emilie Kaufmann · Wouter Koolen · Aurélien Garivier -
2018 Poster: Gen-Oja: Simple & Efficient Algorithm for Streaming Generalized Eigenvector Computation »
Kush Bhatia · Aldo Pacchiano · Nicolas Flammarion · Peter Bartlett · Michael Jordan -
2018 Poster: Horizon-Independent Minimax Linear Regression »
Alan Malek · Peter Bartlett -
2018 Poster: Scalar Posterior Sampling with Applications »
Georgios Theocharous · Zheng Wen · Yasin Abbasi Yadkori · Nikos Vlassis -
2017 Poster: Near Minimax Optimal Players for the Finite-Time 3-Expert Prediction Problem »
Yasin Abbasi Yadkori · Peter Bartlett · Victor Gabillon -
2017 Poster: Conservative Contextual Linear Bandits »
Abbas Kazerouni · Mohammad Ghavamzadeh · Yasin Abbasi · Benjamin Van Roy -
2017 Poster: Random Permutation Online Isotonic Regression »
Wojciech Kotlowski · Wouter Koolen · Alan Malek -
2017 Poster: Spectrally-normalized margin bounds for neural networks »
Peter Bartlett · Dylan J Foster · Matus Telgarsky -
2017 Spotlight: Spectrally-normalized margin bounds for neural networks »
Peter Bartlett · Dylan J Foster · Matus Telgarsky -
2017 Poster: Alternating minimization for dictionary learning with random initialization »
Niladri Chatterji · Peter Bartlett -
2017 Poster: Monte-Carlo Tree Search by Best Arm Identification »
Emilie Kaufmann · Wouter Koolen -
2017 Poster: Acceleration and Averaging in Stochastic Descent Dynamics »
Walid Krichene · Peter Bartlett -
2017 Spotlight: Monte-Carlo Tree Search by Best Arm Identification »
Emilie Kaufmann · Wouter Koolen -
2017 Spotlight: Acceleration and Averaging in Stochastic Descent Dynamics »
Walid Krichene · Peter Bartlett -
2016 Poster: Adaptive Averaging in Accelerated Descent Dynamics »
Walid Krichene · Alexandre Bayen · Peter Bartlett -
2016 Poster: Combining Adversarial Guarantees and Stochastic Fast Rates in Online Learning »
Wouter Koolen · Peter Grünwald · Tim van Erven -
2016 Poster: MetaGrad: Multiple Learning Rates in Online Learning »
Tim van Erven · Wouter Koolen -
2016 Oral: MetaGrad: Multiple Learning Rates in Online Learning »
Tim van Erven · Wouter Koolen -
2015 Workshop: Machine Learning From and For Adaptive User Technologies: From Active Learning & Experimentation to Optimization & Personalization »
Joseph Jay Williams · Yasin Abbasi Yadkori · Finale Doshi-Velez -
2015 : Discussion Panel »
Tim van Erven · Wouter Koolen · Peter Grünwald · Shai Ben-David · Dylan Foster · Satyen Kale · Gergely Neu -
2015 Workshop: Learning Faster from Easy Data II »
Tim van Erven · Wouter Koolen -
2015 Poster: Accelerated Mirror Descent in Continuous and Discrete Time »
Walid Krichene · Alexandre Bayen · Peter Bartlett -
2015 Spotlight: Accelerated Mirror Descent in Continuous and Discrete Time »
Walid Krichene · Alexandre Bayen · Peter Bartlett -
2014 Workshop: Large-scale reinforcement learning and Markov decision problems »
Benjamin Van Roy · Mohammad Ghavamzadeh · Peter Bartlett · Yasin Abbasi Yadkori · Ambuj Tewari -
2014 Poster: Large-Margin Convex Polytope Machine »
Alex Kantchelian · Michael C Tschantz · Ling Huang · Peter Bartlett · Anthony D Joseph · J. D. Tygar -
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: Resource-Efficient Machine Learning »
Yevgeny Seldin · Yasin Abbasi Yadkori · Yacov Crammer · Ralf Herbrich · Peter Bartlett -
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 -
2013 Poster: How to Hedge an Option Against an Adversary: Black-Scholes Pricing is Minimax Optimal »
Jacob D Abernethy · Peter Bartlett · Rafael Frongillo · Andre Wibisono -
2013 Spotlight: How to Hedge an Option Against an Adversary: Black-Scholes Pricing is Minimax Optimal »
Jacob D Abernethy · Peter Bartlett · Rafael Frongillo · Andre Wibisono -
2013 Poster: Online Learning in Markov Decision Processes with Adversarially Chosen Transition Probability Distributions »
Yasin Abbasi Yadkori · Peter Bartlett · Varun Kanade · Yevgeny Seldin · Csaba Szepesvari -
2012 Workshop: Multi-Trade-offs in Machine Learning »
Yevgeny Seldin · Guy Lever · John Shawe-Taylor · Nicolò Cesa-Bianchi · Yacov Crammer · Francois Laviolette · Gabor Lugosi · Peter Bartlett -
2012 Poster: Putting Bayes to sleep »
Wouter M Koolen · Dmitri Adamskiy · Manfred K. Warmuth -
2012 Spotlight: Putting Bayes to sleep »
Wouter M Koolen · Dmitri Adamskiy · Manfred K. Warmuth -
2011 Poster: Improved Algorithms for Linear Stochastic Bandits »
Yasin Abbasi Yadkori · David Pal · Csaba Szepesvari -
2011 Spotlight: Improved Algorithms for Linear Stochastic Bandits »
Yasin Abbasi Yadkori · David Pal · Csaba Szepesvari -
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 -
2011 Session: Opening Remarks and Awards »
Terrence Sejnowski · Peter Bartlett · Fernando Pereira -
2009 Poster: Information-theoretic lower bounds on the oracle complexity of convex optimization »
Alekh Agarwal · Peter Bartlett · Pradeep Ravikumar · Martin J Wainwright -
2009 Spotlight: Information-theoretic lower bounds on the oracle complexity of convex optimization »
Alekh Agarwal · Peter Bartlett · Pradeep Ravikumar · Martin J Wainwright -
2007 Oral: Adaptive Online Gradient Descent »
Peter Bartlett · Elad Hazan · Sasha Rakhlin -
2007 Poster: Adaptive Online Gradient Descent »
Peter Bartlett · Elad Hazan · Sasha Rakhlin -
2007 Poster: Optimistic Linear Programming gives Logarithmic Regret for Irreducible MDPs »
Ambuj Tewari · Peter Bartlett -
2006 Poster: Shifting, One-Inclusion Mistake Bounds and Tight Multiclass Expected Risk Bounds »
Benjamin Rubinstein · Peter Bartlett · J. Hyam Rubinstein -
2006 Poster: Sample Complexity of Policy Search with Known Dynamics »
Peter Bartlett · Ambuj Tewari -
2006 Poster: AdaBoost is Consistent »
Peter Bartlett · Mikhail Traskin