BayesOpt 2017

BayesOpt 2013
Bayesian Optimization in Theory and Practice

There have been many recent advances in the development of machine learning approaches for active decision making and optimization. These advances have occurred in seemingly disparate communities, each referring to the problem using different terminology: Bayesian optimization, experimental design, bandits, active sensing, automatic algorithm configuration, personalized recommender systems, etc. Recently, significant progress has been made in improving the methodologies used to solve high-dimensional problems and applying these techniques to challenging optimization tasks with limited and noisy feedback. This progress is particularly apparent in areas that seek to automate machine learning algorithms and website analytics. Applying these approaches to increasingly harder problems has also revealed new challenges and opened up many interesting research directions both in developing theory and in practical application.

Following on last year’s NIPS workshop, “Bayesian Optimization & Decision Making”, the goal of this workshop is to bring together researchers and practitioners from these diverse subject areas to facilitate cross-fertilization by discussing challenges, findings, and sharing data. This year we plan to focus on the intersection of “Theory and Practice”. Specifically, we would like to carefully examine the types of problems where Bayesian optimization performs well and ask what theoretical guarantees can be made to explain this performance? Where is the theory lacking? What are the most pressing challenges? In what way can this empirical performance be used to guide the development of new theory?

Invited speakers and panelists

The workshop has confirmed the following invited speakers:

• Ryan Adams (Harvard University)
• Sébastien Bubeck (Princeton University)
• Philipp Hennig (MPI Tübingen)

and in addition, along with our speakers we will also host a panel discussion on “The intersection of theory and practice” as it relates to Bayesian optimization. Our additional panelists include:

• Andreas Krause (ETH Zurich)
• Rémi Munos (INRIA Lille)

Organizers

• Nando de Freitas (Oxford University)
• Matthew Hoffman (University of Cambridge)
• Michael Osborne (Oxford University)
• Jasper Snoek (University of Toronto)

Program committee

We would like to thank our program committee for their outstanding help in reviewing the papers submitted to the workshop!

Ryan Adams, Shipra Agrawal, Javad Azimi, Rémi Bardenet, Marc Deisenroth, Misha Denil, David Duvenaud, Mohammad Ghavamzadeh, Roman Garnett, Philipp Hennig, Holger Hoos, Ferenc Huszar, Frank Hutter, Emilie Kaufmann, Alessandro Lazaric, Lihong Li, Dan Lizotte, Ruben Martinez-Cantin, Kevin Swersky, Csaba Szepesvári, Ziyu Wang.

Accepted papers

Below is a list of the papers accepted at BayesOpt 2013:

• Bayesian Optimisation for Informative Continuous Path Planning;
  Roman Marchant and Fabio Ramos
• Mental Rotation as Bayesian Quadrature;
  Jessica B. Hamrick and Thomas L. Griffiths
• A New UCB-Like Algorithm for Permutation Bandit Problem;
  Ryo Watanabe, Atsuyoshi Nakamura, and Mineichi Kudo
• Implicitly Optimistic Exploration via Posterior Sampling;
  Dan Russo and Benjamin Van Roy
• Bayesian Global Optimization with a Stopping Policy;
  Shunan Zhang and Angela J. Yu
• Extending the use of message passing algorithms to problems with unknown structure;
  Roberto Santana, Alexander Mendiburu, and Jose A. Lozano
• An Experimental Evaluation of Bayesian Optimization on Bipedal Locomotion;
  Roberto Calandra, Jan Peters, Andre Seyfarth, Marc Deisenroth
• An Optimistic Posterior Sampling Strategy for Bayesian Reinforcement Learning;
  Raphael Fonteneau, Nathan Korda, and Remi Munos
• Bayesian Optimization using Student-t Processes;
  Amar Shah, Andrew Gordon Wilson, and Zoubin Ghahramani
• Active Learning in Linear Stochastic Bandits;
  Marta Soare, Alessandro Lazaric, and Remi Munos
• Raiders of the Lost Architecture: Kernels for Bayesian Optimization in Conditional Parameter Spaces;
  Kevin Swersky, David Duvenaud, Jasper Snoek, Frank Hutter, and Mike Osborne
• Towards an Empirical Foundation for Assessing Bayesian Optimization of Hyperparameters;
  Katharina Eggensperger, Matthias Feurer, Frank Hutter, James Bergstra, Jasper Snoek, Holger H. Hoos, and Kevin Leyton-Brown
• An Efficient Approach for Assessing Parameter Importance in Bayesian Optimization;
  Frank Hutter, Holger H. Hoos, and Kevin Leyton-Brown
• Bounded-horizon Bayesian optimization;
  Matthew W. Hoffman, Bobak Shahriari, and Nando de Freitas