1 code implementation • 21 Aug 2024 • Xingyou Song, Qiuyi Zhang, Chansoo Lee, Emily Fertig, Tzu-Kuo Huang, Lior Belenki, Greg Kochanski, Setareh Ariafar, Srinivas Vasudevan, Sagi Perel, Daniel Golovin
Google Vizier has performed millions of optimizations and accelerated numerous research and production systems at Google, demonstrating the success of Bayesian optimization as a large-scale service.
no code implementations • 12 Apr 2023 • Daniel Golovin, Gabor Bartok, Eric Chen, Emily Donahue, Tzu-Kuo Huang, Efi Kokiopoulou, Ruoyan Qin, Nikhil Sarda, Justin Sybrandt, Vincent Tjeng
In many software systems, heuristics are used to make decisions - such as cache eviction, task scheduling, and information presentation - that have a significant impact on overall system behavior.
1 code implementation • 27 Jul 2022 • Xingyou Song, Sagi Perel, Chansoo Lee, Greg Kochanski, Daniel Golovin
Vizier is the de-facto blackbox and hyperparameter optimization service across Google, having optimized some of Google's largest products and research efforts.
no code implementations • ICML 2020 • Daniel Golovin, Qiuyi Zhang
Single-objective black box optimization (also known as zeroth-order optimization) is the process of minimizing a scalar objective $f(x)$, given evaluations at adaptively chosen inputs $x$.
no code implementations • ICLR 2020 • Daniel Golovin, John Karro, Greg Kochanski, Chansoo Lee, Xingyou Song, Qiuyi Zhang
Zeroth-order optimization is the process of minimizing an objective $f(x)$, given oracle access to evaluations at adaptively chosen inputs $x$.
1 code implementation • ACM (2017) 2017 • Daniel Golovin, Benjamin Solnik, Subhodeep Moitra, Greg Kochanski, John Karro, D. Sculley
Any sufficiently complex system acts as a black box when it becomes easier to experiment with than to understand.
no code implementations • NeurIPS 2015 • D. Sculley, Gary Holt, Daniel Golovin, Eugene Davydov, Todd Phillips, Dietmar Ebner, Vinay Chaudhary, Michael Young, Jean-François Crespo, Dan Dennison
Machine learning offers a fantastically powerful toolkit for building useful complexprediction systems quickly.
no code implementations • 3 Jul 2014 • Daniel Golovin, Andreas Krause, Matthew Streeter
How should we dynamically rank information sources to maximize the value of the ranking?
no code implementations • NeurIPS 2010 • Daniel Golovin, Andreas Krause, Debajyoti Ray
In the case of noise-free observations, a greedy algorithm called generalized binary search (GBS) is known to perform near-optimally.
no code implementations • 21 Mar 2010 • Daniel Golovin, Andreas Krause
Solving stochastic optimization problems under partial observability, where one needs to adaptively make decisions with uncertain outcomes, is a fundamental but notoriously difficult challenge.
no code implementations • NeurIPS 2009 • Matthew Streeter, Daniel Golovin, Andreas Krause
Which ads should we display in sponsored search in order to maximize our revenue?
no code implementations • NeurIPS 2008 • Matthew Streeter, Daniel Golovin
We present an algorithm for solving a broad class of online resource allocation problems.