Consider the problem of learning input/output mappings through exploration, e.g. If actions are expensive and computation is cheap, then we should explore by selecting a trajectory through the in(cid:173) put space which gives us the most amount of information in the fewest number of steps. I discuss how results from the field of opti(cid:173) mal experiment design may be used to guide such exploration, and demonstrate its use on a simple kinematics problem.

By automating scientific processes and introducing artificial intelligence for decision-making, TRI's new closed-loop research platforms free up scientists' time for more creative tasks. When I first started graduate school almost 10 years ago, I was mixing ingredients by hand, writing down reaction conditions on a piece of paper, and grabbing a quick lunch in between lab sessions. At that time, the idea of a robot doing my experiments -- or using machine learning to predict the outcomes of my reactions -- would have never occurred to me. I accepted a future as a scientist where I would only be able to explore a tiny fraction of the billions of possible materials in the universe by hand. If lucky, a scientific discovery might arrive serendipitously as I became better at making "educated guesses."

This entry is a part of the NYU Center for Data Science blog's recurring guest editorial series. Irina Espejo Morales is a CDS Ph.D. student in data science and also a DeepMind fellow. Kyle Cranmer is a CDS professor of data science and professor of physics at the NYU College of Arts & Science. Lukas Heinrich is a staff scientist at CERN working with the ATLAS experiment at the LHC and former NYU graduate student. Gilles Louppe is an associate professor in artificial intelligence and deep learning at the University of Liège (Belgium) and former Moore Sloan fellow.

A model-based optimal experiment design (OED) of nonlinear systems is studied. OED represents a methodology for optimizing the geometry of the parametric joint-confidence regions (CRs), which are obtained in an a posteriori analysis of the least-squares parameter estimates. The optimal design is achieved by using the available (experimental) degrees of freedom such that more informative measurements are obtained. Unlike the commonly used approaches, which base the OED procedure upon the linearized CRs, we explore a path where we explicitly consider the exact CRs in the OED framework. We use a methodology for a finite parametrization of the exact CRs within the OED problem and we introduce a novel approximation technique of the exact CRs using inner-and outer-approximating ellipsoids as a computationally less demanding alternative. The employed techniques give the OED problem as a finite-dimensional mathematical program of bilevel nature. We use two small-scale illustrative case studies to study various OED criteria and compare the resulting optimal designs with the commonly used linearization-based approach. We also assess the performance of two simple heuristic numerical schemes for bilevel optimization within the studied problems. Introduction At present, advanced industrial engineering and management strive for resource-and energy-efficient design and operation of systems, plants, and processes. Here a use of the model-based techniques is a leading paradigm. The employed models, whether mechanistic or data-based, include a finite number of parameters, whose values are related to the particular natural and system-wide phenomena and are thus commonly only known to belong to some interval or unknown completely.

We study the problem of causal structure learning over a set of random variables when the experimenter is allowed to perform at most $M$ experiments in a non-adaptive manner. We consider the optimal learning strategy in terms of minimizing the portions of the structure that remains unknown given the limited number of experiments in both Bayesian and minimax setting. We characterize the theoretical optimal solution and propose an algorithm, which designs the experiments efficiently in terms of time complexity. We show that for bounded degree graphs, in the minimax case and in the Bayesian case with uniform priors, our proposed algorithm is a $\rho$-approximation algorithm, where $\rho$ is independent of the order of the underlying graph. Simulations on both synthetic and real data show that the performance of our algorithm is very close to the optimal solution.

With cloud computing environments such as Amazon EC2, users typically have a large number of choices in terms of the instance types and number of instances they can run their jobs on. Not surprisingly, the amount of memory per core, storage media, and the number of instances are crucial chocies that determine the running time and thus indirectly the cost of running a given job. Ernest takes on the challenge of predicting the most efficient configuration for large advanced analytics applications in a heterogeneous multi-tenant environments. It might be that you have a certain budget, and want to minimize the running time given that budget, or perhaps you have a time limit, and want to complete the job as cheaply as possible within that time limit. Either way, exhaustively trying all of the combinations to find out which work the best isn't really feasible.

Consider the problem of learning input/output mappings through exploration, e.g.

Consider the problem of learning input/output mappings through exploration, e.g.

Consider the problem of learning input/output mappings through exploration, e.g.