Over the past 10+ years, online companies large and small have adopted widespread A/B testing as a robust data-based method for evaluating potential product improvements. In online experimentation, it is straightforward to measure the short-term effect, i.e., the impact observed during the experiment. However, the short-term effect is not always predictive of the long-term effect, i.e., the final impact once the product has fully launched and users have changed their behavior in response. Thus, the challenge is how to determine the long-term user impact while still being able to make decisions in a timely manner.

At Google, experimentation is practically a mantra; we evaluate almost every change that potentially affects what our users experience. Such changes include not only obvious user-visible changes such as modifications to a user interface, but also more subtle changes such as different machine learning algorithms that might affect ranking or content selection. Our insatiable appetite for experimentation has led us to tackle the problems of how to run more experiments, how to run experiments that produce better decisions, and how to run them faster. In this paper, we describe Google's overlapping experiment infrastructure that is a key component to solving these problems. In addition, because an experiment infrastructure alone is insufficient, we also discuss the associated tools and educational processes required to use it effectively. We conclude by describing trends that show the success of this overall experimental environment. While the paper specifically describes the experiment system and experimental processes we have in place at Google, we believe they can be generalized and applied by any entity interested in using experimentation to improve search engines and other web applications.

Most analysts start with an overview of the data before gradually refining their view to be more focused and detailed. Multiscale pan-and-zoom systems are effective because they directly support this approach. However, generating abstract overviews of large data sets is difficult and most systems take advantage of only one type of abstraction: visual abstraction. Furthermore, these existing systems limit the analyst to a single zooming path on their data and thus to a single set of abstract views. This paper presents: 1) a formalism for describing multiscale visualizations of data cubes with both data and visual abstraction and 2) a method for independently zooming along one or more dimensions by traversing a zoom graph with nodes at different levels of detail. As an example of how to design multiscale visualizations using our system, we describe four design patterns using our formalism. These design patterns show the effectiveness of multiscale visualization of general relational databases.

... in a variety of applications such as corporate data warehouses and scientific computing. To support interactive analysis, many of these databases are augmented with hierarchical structures that provide meaningful levels of abstraction that can be leveraged by both the computer and analyst. This hierarchical structure generates many challenges and opportunities in the design of systems for the query, analysis, and visualization of these databases. In this

In the last several years, large multidimensional databases have become common in a variety of applications, such as data warehousing and scientific computing. Analysis and exploration tasks place significant demands on the interfaces to these databases. Because of the size of the data sets, dense graphical representations are more effective for exploration than spreadsheets and charts. Furthermore, because of the exploratory nature of the analysis, it must be possible for the analysts to change visualizations rapidly as they pursue a cycle involving first hypothesis and then experimentation. In this paper, we present Polaris, an interface for exploring large multidimensional databases that extends the well-known pivot table interface. The novel features of Polaris include an interface for constructing visual specifications of table-based graphical displays and the ability to generate a precise set of relational queries from the visual specifications. The visual specifications can be rapidly and incrementally developed, giving the analyst visual feedback as he constructs complex queries and visualizations.

To understand better how users take advantage of wireless networks, we examine a twelve-week trace of a building-wide local-area wireless network. We analyze the network for overall user behavior (when and how intensively people use the network and how much they move around), overall network traffic and load characteristics (observed throughput and symmetry of incoming and outgoing traffic), and traffic characteristics from a user point of view (observed mix of applications and number of hosts connected to by users).

Article Analysis of a metropolitan-area wireless network Share on Authors: Diane Tang Stanford University, Gates 4A, Stanford Stanford University, Gates 4A, StanfordView Profile , Mary Baker Stanford University, Gates 4A, Stanford, CA Stanford University, Gates 4A, Stanford, CAView Profile Authors Info & Claims MobiCom '99: Proceedings of the 5th annual ACM/IEEE international conference on Mobile computing and networkingAugust 1999 Pages 13–23https://doi.org/10.1145/313451.313460Online:01 August 1999Publication History 75citation615DownloadsMetricsTotal Citations75Total Downloads615Last 12 Months10Last 6 weeks0 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

Abstract Animators frequently choreograph complex motions for multiple objects that interact through collision and obstruction. In such situations, the use of physically based dynamics to confer visual realism creates challenging computational problems. Typically forward simulation is well understood, but the inverse problem of motion synthesis—that of synthesizing motions consistent both with physical law and with the animator's requirements—is generally tedious and sometimes intractable. We show how N‐body inverse problems can be formulated as optimization tasks. We present a simply stated, but combinatorially formidable example that exhibits all of the essential sources of complexity common to N‐body motion synthesis, and show how it can be solved approximately using heuristic methods based on evolutionary computation.