Timezone: »
Poster
Max-value Entropy Search for Efficient Bayesian Optimization
Zi Wang · Stefanie Jegelka
Entropy Search (ES) and Predictive Entropy Search (PES) are popular and empirically successful Bayesian Optimization techniques. Both rely on a compelling information-theoretic motivation, and maximize the information gained about the $\arg\max$ of the unknown function; yet, both are plagued by the expensive computation for estimating entropies. We propose a new criterion, Max-value Entropy Search (MES), that instead uses the information about the maximum function value. We show relations of MES to other Bayesian optimization methods, and establish a regret bound. We observe that MES maintains or improves the good empirical performance of ES/PES, while tremendously lightening the computational burden. In particular, MES is much more robust to the number of samples used for computing the entropy, and hence more efficient for higher dimensional problems.
Author Information
Zi Wang (MIT)
Stefanie Jegelka (MIT)
Related Events (a corresponding poster, oral, or spotlight)
-
2017 Talk: Max-value Entropy Search for Efficient Bayesian Optimization »
Wed. Aug 9th 12:48 -- 01:06 AM Room C4.1
More from the Same Authors
-
2021 Town Hall: Town Hall »
John Langford · Marina Meila · Tong Zhang · Le Song · Stefanie Jegelka · Csaba Szepesvari -
2020 : Negative Dependence and Sampling »
Stefanie Jegelka -
2020 Poster: Strength from Weakness: Fast Learning Using Weak Supervision »
Joshua Robinson · Stefanie Jegelka · Suvrit Sra -
2019 Poster: Learning Generative Models across Incomparable Spaces »
Charlotte Bunne · David Alvarez-Melis · Andreas Krause · Stefanie Jegelka -
2019 Oral: Learning Generative Models across Incomparable Spaces »
Charlotte Bunne · David Alvarez-Melis · Andreas Krause · Stefanie Jegelka -
2018 Poster: Representation Learning on Graphs with Jumping Knowledge Networks »
Keyulu Xu · Chengtao Li · Yonglong Tian · Tomohiro Sonobe · Ken-ichi Kawarabayashi · Stefanie Jegelka -
2018 Oral: Representation Learning on Graphs with Jumping Knowledge Networks »
Keyulu Xu · Chengtao Li · Yonglong Tian · Tomohiro Sonobe · Ken-ichi Kawarabayashi · Stefanie Jegelka -
2017 Poster: Robust Budget Allocation via Continuous Submodular Functions »
Matthew J Staib · Stefanie Jegelka -
2017 Talk: Robust Budget Allocation via Continuous Submodular Functions »
Matthew J Staib · Stefanie Jegelka -
2017 Poster: Batched High-dimensional Bayesian Optimization via Structural Kernel Learning »
Zi Wang · Chengtao Li · Stefanie Jegelka · Pushmeet Kohli -
2017 Talk: Batched High-dimensional Bayesian Optimization via Structural Kernel Learning »
Zi Wang · Chengtao Li · Stefanie Jegelka · Pushmeet Kohli