Olympus: a benchmarking framework for noisy optimization and experiment planning

  title={Olympus: a benchmarking framework for noisy optimization and experiment planning},
  author={Florian Hase and Matteo Aldeghi and Riley J. Hickman and L. Roch and M. Christensen and Elena Liles and J. Hein and Al{\'a}n Aspuru-Guzik},
  journal={Machine Learning: Science and Technology},
Research challenges encountered across science, engineering, and economics can frequently be formulated as optimization tasks. In chemistry and materials science, recent growth in laboratory digitization and automation has sparked interest in optimization-guided autonomous discovery and closed-loop experimentation. Experiment planning strategies based on off-the-shelf optimization algorithms can be employed in fully autonomous research platforms to achieve desired experimentation goals with the… Expand
Data-Driven Strategies for Accelerated Materials Design
The most recent contributions of this group in this thriving field of machine learning for material science are reviewed, focusing on small molecules as organic electronic materials and crystalline materials and the data-driven approaches they employed to speed up discovery and derive material design strategies. Expand
Gemini: Dynamic Bias Correction for Autonomous Experimentation and Molecular Simulation
This research presents a novel and scalable approaches called “Smart grids” that can be applied to the rapidly changing environment and provide real-time information about how cells “talk” to one another. Expand
Golem: An algorithm for robust experiment and process optimization
This research presents a state-of-the-art probabilistic simulation of the reinforcement learning system that automates the very labor-intensive and therefore time-heavy and therefore expensive and expensive process of training a neural network. Expand
'FitBenchmarking': an open source 'Python' package comparing data fitting software
This paper helps scientists, mathematicians and numerical software developers, who want to understand the types of problems on which current algorithms do not perform well, and to have a route to expose newly developed methods to users. Expand
Benchmarking the Performance of Bayesian Optimization across Multiple Experimental Materials Science Domains
This paper presents a meta-modelling system that automates the very labor-intensive and therefore expensive and therefore time-heavy and expensive and expensive process of designing and testing artificial intelligence systems. Expand
Nanoparticle synthesis assisted by machine learning
Many properties of nanoparticles are governed by their shape, size, polydispersity and surface chemistry. To apply nanoparticles in chemical sensing, medical diagnostics, catalysis, thermoelectrics,Expand
Data augmentation strategies to improve reaction yield predictions and estimate uncertainty
Chemical reactions describe how precursor molecules react together and transform into products. The reaction yield describes the percentage of the precursors successfully transformed into productsExpand
Gryffin: An algorithm for Bayesian optimization of categorical variables informed by expert knowledge
This research presents a parallel version of the Celada–Seiden cellular automaton that automates the very labor-intensive and therefore time-heavy and expensive and therefore expensive and expensive process of Berkeley’s famed “Black-box” system. Expand


Genetic programming - on the programming of computers by means of natural selection
  • J. Koza
  • Computer Science
  • Complex adaptive systems
  • 1993
This book discusses the evolution of architecture, primitive functions, terminals, sufficiency, and closure, and the role of representation and the lens effect in genetic programming. Expand
Bayesian Approach to Global Optimization: Theory and Applications
1 Global optimization and the Bayesian approach.- 1.1 What is global optimization?.- 1.2 Advantages of the Bayesian approach to global optimization.- 2 The conditions of Bayesian optimality.- 2.1Expand
Optimization-Theory And Applications
Theoretical Equivalence of Mayer, Lagrange, and Bolza Problems of Optimal Control, and the Necessary Conditions and Sufficient Conditions Convexity and Lower Semicontinuity. Expand
The Design of Experiments
AbstractREADERS of “Statistical Methods for Research Workers” will welcome Prof. Fisher's new book, which is partly devoted to a development of the logical ideas underlying the earlier volume andExpand
Automation and Remote Control
The Journal was founded in 1936, being the first special journal in the area of control. At present the scope of the journal is entirely control theory problems and applications. The journalExpand
The master programme in Applied Geology aims to provide comprehensive knowledge based on various branches of Geology, with special focus on Applied geology subjects in the areas of Geomorphology, Structural geology, Hydrogeology, Petroleum Geologists, Mining Geology), Remote Sensing and Environmental geology. Expand
Stream Processing of Healthcare Sensor Data: Studying User Traces to Identify Challenges from a Big Data Perspective
A detailed analysis of traces gathered from a well-known healthcare sport-oriented application is provided in order to illustrate the conclusions from a big data perspective. Expand
1996 IEEE International Conference on Evolutionary Computation Proceedings
From the Publisher: This conference presents a new computing technology with powerful applications that incorporate advances in neural networks and fuzzy logic. Expand
however (for it was the literal soul of the life of the Redeemer, John xv. io), is the peculiar token of fellowship with the Redeemer. That love to God (what is meant here is not God’s love to men)Expand
What are “ A ” and “ B ” ?
Direct fabrication of large micropatterned single crystals. p1205 21 Feb 2003. (news): Academy plucks best biophysicists from a sea of mediocrity. p994 14 Feb 2003.