BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Information Systems Group - ECPv6.4.0.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Information Systems Group
X-ORIGINAL-URL:https://isg.ics.uci.edu
X-WR-CALDESC:Events for Information Systems Group
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20180311T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20181104T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20190310T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20191103T090000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20191122T130000
DTEND;TZID=America/Los_Angeles:20191122T140000
DTSTAMP:20261015T024208
CREATED:20191115T192950Z
LAST-MODIFIED:20191122T203428Z
UID:1223-1574427600-1574431200@isg.ics.uci.edu
SUMMARY:Texera: Supporting Big Data Analytics for Domain Experts through GUI-based workflows
DESCRIPTION:Speakers:  Avinash Kumar\,  Shengquan Ni\, Zuozhi Wang \n  \nAbstract: Big data analytics is a daunting task for domain experts such as doctors and teachers. Their non-IT background makes it challenging for them to write analytics code and maintain computing infrastructures to efficiently process large amounts of data. Existing data analytics frameworks that offer GUI-based alternatives are mostly limited to a single machine. In light of these facts\, we are developing Texera\, a scalable data-processing system that supports interaction and debugging and is easy to use by non-IT people. One of the challenges of the system is supporting real-time interactions without compromising on scalability. We discuss how we solve the problem in Amber\, the backend engine of Texera. Amber\, built using the actor model\, is a cluster-based distributed engine that can process workflows while supporting interactions. We will show a demonstration of using Texera to analyze social media data.
URL:https://isg.ics.uci.edu/event/amber-a-debuggable-dataflow-system-based-on-theactor-model/
LOCATION:DBH 3011
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20191115T123000
DTEND;TZID=America/Los_Angeles:20191115T140000
DTSTAMP:20261015T024208
CREATED:20191115T192124Z
LAST-MODIFIED:20191115T192124Z
UID:1219-1573821000-1573826400@isg.ics.uci.edu
SUMMARY:Multistage Adaptive Load Balancing in Big Active Data Publish Subscribe Systems
DESCRIPTION:Speaker: Hang\nTime: 12:30pm\nRoom: 3011 \nWe address issues in the design and operation of a Big Active Data Publish Subscribe (BAD Pub/Sub) systems to enable the next generation of enriched notification systems that can scale to societal levels. The proposed BAD Pub/Sub systems aim to ingest massive amounts of data from heterogeneous publishers and sources and deliver customized\, enriched notifications to end users that express interests in these data items via parameterized channels. To support scalability\, we employ a hierarchical architecture that combines a back-end big data cluster (to receive publications and data feeds\, store data and process subscriptions) with a client-facing distributed broker network that manages user subscriptions and scales the delivery process. The skewed distribution of subscribers\, their interests and the dynamic nature of societal scale publications\, create load imbalance in the distributed broker network. We propose a staged approach for broker load balancing that executes in multiple stages — initial placement of brokers to subscribers\, dynamic subscriber migration during operation to handle transient and instantaneous loads and occasional shuffles to re-stabilize the system.  
URL:https://isg.ics.uci.edu/event/multistage-adaptive-load-balancing-in-big-active-data-publish-subscribe-systems/
LOCATION:DBH 3011
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20191108T123000
DTEND;TZID=America/Los_Angeles:20191108T140000
DTSTAMP:20261015T024208
CREATED:20191103T212621Z
LAST-MODIFIED:20191103T212621Z
UID:1215-1573216200-1573221600@isg.ics.uci.edu
SUMMARY:Gift Sinthong: AsterixDB Meets Data Science
DESCRIPTION:Abstract:\nIn the last few years\, Data Science has become an increasingly important use case for data platforms. To support the full Big Data analysis lifecycle\, we have examined one of the most popular exploratory data analytics tools\, Pandas\, which has a serious problem: scalability. Exploratory tools such as Pandas only work well against locally stored data that fits in the memory of a single machine. Our plan is to integrate a Pandas-like user experience with AsterixDB to provide analysts with a familiar working environment while scaling out the evaluation of the analytical operations over a large data cluster to enable Big Data analysis. The two main components that we use to enable such a workflow are the AsterixDB UDF framework and our new Python data analytics library (“AFrame”) that operates against AsterixDB. AFrame allows users to interact with a very large volume of semi-structured data in the same way that Pandas DataFrames work against locally stored tabular data. Influenced by Spark SQL and Spark DataFrames\, our AFrame prototype leverages lazy evaluation and only performs operations once an action is invoked. AFrame operations are incrementally translated into AsterixDB SQL++ queries that are executed only when final results are called for.  In this talk\, we will demonstrate our approach using a restaurant review analytics use case.
URL:https://isg.ics.uci.edu/event/gift-sinthong-asterixdb-meets-data-science/
LOCATION:DBH 4011
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20190809T150000
DTEND;TZID=America/Los_Angeles:20190809T160000
DTSTAMP:20261015T024208
CREATED:20190624T221120Z
LAST-MODIFIED:20190809T003159Z
UID:1187-1565362800-1565366400@isg.ics.uci.edu
SUMMARY:Michal Shmueli-Scheuer : Conversational bots for customer support
DESCRIPTION:Conversational bots for customer support\nMichal Shmueli-Scheuer\, IBM Research – Haifa\n\nAugust 9\, 2019\, Friday\, 3:00 pm – 4:00 pm\, DBH 4011 \n\nAbstract:\nIn this talk\, I’ll cover various aspects of conversational bots\, focusing on the domain of customer support. Often\, human conversations with bots mimic the way humans interact with each other. Moreover\, even when customers know that they are interacting with virtual agents (bots)\, they still expect them to behave like humans. One way to improve interactions with bots is by giving them some human characteristics \,such as emotion and personality. I’ll show how a model of neural response generation can be used to generate bot responses according to a target personality. I’ll then cover a methodology for detecting egregious conversations in a setting using conversational bots by examining behavioral cues from the customer\, patterns in the agents’ responses\, and customer-agent interactions. \nBio:\nMichal Shmueli-Scheuer is a senior researcher in the Language and Retrieval research group (AI Language department) in IBM Research – Haifa\, with over 13 years of industry experience. She holds a Ph.D (2009) degree in Information and Computer Science from the University of California\, Irvine\, USA. Her area of expertise is in the fields of conversational bots\, affective computing\, user modeling\, large scale analytics\, database\, and information systems\, focusing on user behavior analytics and information management on the web. Her current work focuses on computational modeling for users and conversational agents. She has published more than 30 academic papers in leading conferences\, and journals\, and book chapters. She has served as a PC member and a reviewer of numerous leading conferences and journals.
URL:https://isg.ics.uci.edu/event/michal-shmueli-scheuer-conversational-bots-for-customer-support/
LOCATION:DBH 4011
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20190531T150000
DTEND;TZID=America/Los_Angeles:20190531T160000
DTSTAMP:20261015T024208
CREATED:20190415T193502Z
LAST-MODIFIED:20190530T145140Z
UID:1174-1559314800-1559318400@isg.ics.uci.edu
SUMMARY:Pat Helland: There's No Substitute for Interchangeability
DESCRIPTION:Speaker: Pat Helland (Salesforce.com) \nTitle: There’s No Substitute for Interchangeability\nTime: 3-4 PM \nPlace: 3011 DBH \n\n\n\n\n\n\n\n\n\nAbstract:\n\nDistributed systems have many challenges including loosely coupled systems\, long running work\, and distributed workflow.  In addition\,  replication with out-of-order reconciliation is quite difficult\, especially when composed with the other challenges.  In this talk\, we propose data-centric REST-style connectors that allow work to be decoupled in trust\, space\, and time.  These replication connectors support replicated services with eventual consistency.\n\nAs work comes together\, domain specific interchangeability provides the glue and lubrication that empowers work that’s decoupled across boundaries.  We see this in real life with commodities in food and interchangeable parts in manufacturing.  Work domains for the application typically support interchangeable resources like seats on an airplane or king-sided non-smoking rooms.  It is the interchangeability defined by an application domain that allows work to proceed across boundaries.  These boundaries include applications and their trust\, space and time across workflows\, and replicas of any and all of the services comprising the app.\n\nThe ideas presented in this talk are the author’s and are not tied to his work at Salesforce.\n\n\n——————–\n\nBio: \n\n\nPat Helland has been implementing databases\, transaction systems\, multiprocessors\, messaging systems\, app platforms\, and storage systems since 1978.  He studied computer science at UC Irvine from 1973 to 1976.  He currently works at Salesforce.  For recreation\, Pat likes to write papers about random stuff related to distributed computing and data for ACM Queue and Communications of the ACM.
URL:https://isg.ics.uci.edu/event/pat-helland-theres-no-substitute-for-interchangeability/
LOCATION:DBH 3011
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20190321T140000
DTEND;TZID=America/Los_Angeles:20190321T150000
DTSTAMP:20261015T024208
CREATED:20190311T060555Z
LAST-MODIFIED:20190311T060555Z
UID:1144-1553176800-1553180400@isg.ics.uci.edu
SUMMARY:Fatemeh Nargesian: Data Enrichment for Data Science
DESCRIPTION:Data Enrichment for Data Science\nFatemeh Nargesian\, University of Toronto\n\nMarch 21\, Thursday\, 2019\n\n2:00 – 3 pm\, DBH 3011\nRefreshments start at 1:30 pm\n\n\n\n\nData Science is built on the power of data processing and data preparation. In this talk\, I discuss the challenges of data preparation for end-to-end data science. Particularly\, I talk about data enrichment via discovery where the goal is to discover and integrate the right data to solve a given data science problem. I introduce two paradigms of data discovery. In the first paradigm\, the query is a dataset and a data scientist is interested in interactively finding datasets that can be integrated (e.g unioned) with the query. I introduce a probabilistic framework for searching for top-k unionable tables and discuss the need for distribution-aware techniques for data discovery. In the second paradigm\, search does not start with a query\, instead\, it is data-driven. I will talk about data lake organization problem where the goal is to build a directory structure that enables users to most efficiently navigate data lakes. I will present a navigation model of how users interact with a directory structure and introduce a scalable local search algorithm for optimizing data lake organizations.\n\n————————————–\n\nBio:\nFatemeh Nargesian is a PhD candidate in the Data Curation Group of the Department of Computer Science at University of Toronto. Her primary research interests are in the data management challenges of end-to-end data science. A paper she co-authored on data discovery was accorded the Best Demonstration Award at VLDB 2017. While at University of Toronto\, Fatemeh was a joint Research intern at IBM Research-NY. Prior to University of Toronto\, she worked on clinical data management at the Clinical Informatics Research Group at McGill University\, and received M.Sc. degrees in Computer Science at University of Ottawa and Artificial Intelligence at Sharif University of Technology.
URL:https://isg.ics.uci.edu/event/fatemeh-nargesian-data-enrichment-for-data-science/
LOCATION:DBH 3011
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20190318T110000
DTEND;TZID=America/Los_Angeles:20190318T120000
DTSTAMP:20261015T024208
CREATED:20190311T174005Z
LAST-MODIFIED:20190311T174005Z
UID:1146-1552906800-1552910400@isg.ics.uci.edu
SUMMARY:Xiangyao Yu: Transaction Processing at Scale
DESCRIPTION:Abstract: \nOnline transaction processing (OLTP) is critical for applications including finance\, e-commerce\, social networks\, and healthcare. The increasing performance demands of these applications require OLTP to scale massively. Concurrency control is a major scalability bottleneck in such systems. \nThis talk presents three projects that identify and help resolve scalability challenges. First\, I present a scalability study of concurrency control on a simulated 1000-core processor and show the bottlenecks that constrain the scaling of classic algorithms. Then\, I present a new protocol called TicToc that removes the bottleneck of central timestamp allocation on multicore processors. The key technique is data-driven timestamp management that dynamically calculates each transaction’s timestamp based on its data access pattern. Finally\, I present Sundial\, a distributed concurrency control scheme that mitigates the bottleneck of long network latency through a lightweight caching protocol. The talk ends with a vision of transaction processing in the era of cloud computing and internet of things. \nBio: \nXiangyao Yu is a postdoctoral associate at Computer Science and Artificial Intelligence Lab (CSAIL) at Massachusetts Institute of Technology (MIT) under the supervision of Prof. Michael Stonebraker. He acquired his Ph.D. at MIT in 2017 and B.S. at Tsinghua University in 2012. His research interest centers on databases with additional expertise in computer architecture. He won the best Ph.D. thesis award in EECS at MIT and has three best paper awards or nominations. \nhttp://people.csail.mit.edu/yxy \nFor directions/parking information\, please visit: \nhttps://uci.edu/visit/maps.php and http://www.ics.uci.edu/about/visit/index.php
URL:https://isg.ics.uci.edu/event/xiangyao-yu-transaction-processing-at-scale/
LOCATION:DBH 3011
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20190208T150000
DTEND;TZID=America/Los_Angeles:20190208T160000
DTSTAMP:20261015T024208
CREATED:20190125T030748Z
LAST-MODIFIED:20190125T210119Z
UID:1054-1549638000-1549641600@isg.ics.uci.edu
SUMMARY:Prof. Sang-Woo Jun: Lowering the cost of large-scale data analytics via efficient use of flash storage
DESCRIPTION:In this talk\, I present the storage systems aspect of the ongoing work on using relatively cheap solid-state secondary storage to replace expensive DRAM for analytics on large amounts of data\, using as examples graph analytics and the bioinformatics application somatic mutation finding.\nBoth applications are inherently random access intensive\, which is a bad fit with the coarse access granularity of secondary storage.\nIn both cases\, performance impact of random access is addressed in two ways: reorganizing the computation and access pattern to remove random access\, and modifying the internals of the storage device controller to optimize for random accesses.\nIn both cases\, a desktop-class system with secondary storage was able to match the performance of a system with an order of magnitude higher cost.\n\n\n\nBio:\n\nSang-Woo Jun is a faculty member at Donald Bren School of Information and Computer Sciences at the University of California\, Irvine. His research focus is on computer architecture and system design for lowering the cost of handling large amounts of data. Before joining UCI\, Sang-Woo did his Ph.D with Professor Arvind at the Massachusetts Institute of Technology\, and his B.S. at Seoul National University in Korea. His industry experience includes intern at the Big Data Discovery team at Oracle\, and Server/Client developer at Nexon inc.
URL:https://isg.ics.uci.edu/event/prof-sang-woo-jun-lowering-the-cost-of-large-scale-data-analytics-via-efficient-use-of-flash-storage/
LOCATION:DBH 3011
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20190201T110000
DTEND;TZID=America/Los_Angeles:20190201T120000
DTSTAMP:20261015T024208
CREATED:20190125T020959Z
LAST-MODIFIED:20190125T211117Z
UID:1045-1549018800-1549022400@isg.ics.uci.edu
SUMMARY:Prof. Jeff Ullman: Data Science:  Is it Real?
DESCRIPTION:ABSTRACT: \nWe shall discuss the various ways in which data science is approached by different communities\, including the Statistics\, Machine-Learning\, and Database communities.  Each presents a different viewpoint and values different outcomes. Some consequences of these approaches will be discussed. As an example\, of why data science is not machine learning\, we shall sketch two important algorithms not in this class: locality-sensitive hashing and approximate counting. \nBIOGRAPHY: \nJeffrey David Ullman is the Stanford W. Ascherman Professor of Engineering (Emeritus) in the Department of Computer Science at Stanford and CEO of Gradiance Corp.  He received the B.S. degree in Engineering Mathematics from Columbia in 1963 and the PhD in Electrical Engineering from Princeton in 1966. Prior to his appointment at Stanford in 1979\, he was a member of the technical staff of Bell Laboratories from 1966-1969\, and on the faculty of Princeton University between 1969 and 1979.  From 1990-1994\, he was chair of the Stanford Computer Science Department. Prof. Ullman was elected to the US National Academy of Engineering in 1989\, the American Academy of Arts and Sciences in 2012\, and has held Guggenheim and Einstein Fellowships. He has received the Sigmod Contributions Award (1996)\, the ACM Karl V. Karlstrom Outstanding Educator Award (1998)\, the Knuth Prize (2000)\, the Sigmod E. F. Codd Innovations award (2006)\, the IEEE von Neumann medal (2010)\, and the NEC C&C Foundation Prize (2017).  He is the author of 16 books\, including books on database systems\, data mining\, compilers\, automata theory\, and algorithms. \nURL:  i.stanford.edu/~ullman
URL:https://isg.ics.uci.edu/event/prof-jeff-ullman-visit/
LOCATION:DBH 6011
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20190125T150000
DTEND;TZID=America/Los_Angeles:20190125T160000
DTSTAMP:20261015T024208
CREATED:20181221T022339Z
LAST-MODIFIED:20190131T004734Z
UID:827-1548428400-1548432000@isg.ics.uci.edu
SUMMARY:David Lomet (Microsoft Research): How Data Caching Systems Succeed
DESCRIPTION:Data in traditional “caching” data systems resides on secondary storage\, and is read into main memory only when operated on. This limits system performance. Main memory data stores with data always in main memory are much faster. But this performance comes at a cost. In this paper\, we analyze the costs of both in-memory operations and secondary storage operations where data is not “in cache”. We study the performance impact of cache misses on caching system performance. The analysis considers both execution and storage costs. Based on our analysis\, we derive cost/performance results for a data caching system [Deuteronomy and its Bw-tree] and a main memory system [MassTree] to understand where each demonstrates the best cost per operation\, what is driving the cost differences\, and the scale of the differences. This analysis (1) provides insight into why data caching systems continue to dominate the market; (2) points to higher performance that does not rely on simply increasing main memory cache size; and (3) suggests a path to lower costs and hence better cost/performance. \n  \nSpeaker Bio: \nDavid Lomet founded the Database Group at Microsoft Research Redmond in 1995 and managed it for 20 years. His research career began at IBM where\, while on a 1975-76 sabbatical at the University of Newcastle-on-Tyne\, he invented atomic actions (a form of transactions). He later worked at Wang Institute as a faculty member\, and at Digital Equipment Corporation as a software architect and research staff member. He received a Ph.D. in computer science from the University of Pennsylvania. Lomet’s primary focus has been the engineering of database systems\, with a focus on database system kernels. His work on concurrency control and recovery contributed to making DEC’s Rdb and Microsoft’s SQL Server database management systems leaders in cost/performance. His Deuteronomy research project’s latch-free Bw-tree index and log structure store are key elements in Microsoft’s Hekaton main memory database and Azure Cosmos DB cloud data service. Deuteronomy won the Microsoft Research Redmond “2017 Best Research Project” Award. Lomet is an author of over 120 papers and over 60 patents. Lomet has won IEEE awards as well as the ACM SIGMOD Contributions Award for his 25 year tenure as EIC of the IEEE Data Engineering Bulletin. HE has also served as editor of ACM TODS\, VLDB Journal and others\, and has been a member of the VLDB Board. He has been a PC co-chair for ICDE and VLDB. He is a member of the IEEE Computer Society Board of Governors and society Secretary\, and has been First Vice President and Treasurer. He is a fellow of IEEE\, ACM\, and AAAS\, and a member of the National Academy of Engineering. \n  \nDownload slides for this talk \nWatch the video for this talk
URL:https://isg.ics.uci.edu/event/speaker-david-lomet-microsoft-research-cost-performance-in-modern-data-stores-how-data-caching-systems-succeed/
LOCATION:DBH 4011
ATTACH;FMTTYPE=image/png:https://isg.ics.uci.edu/wp-content/uploads/2018/10/Microsoft-logo_rgb_wht.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20181207T150000
DTEND;TZID=America/Los_Angeles:20181207T160000
DTSTAMP:20261015T024208
CREATED:20181222T021251Z
LAST-MODIFIED:20260401T210254Z
UID:838-1544194800-1544198400@isg.ics.uci.edu
SUMMARY:Vinayak Borkar (FireEye Inc.): The X15 Machine Data Management Platform
DESCRIPTION:ABSTRACT: Machine Data (aka Log Data) is continuously produced by applications and devices as a result of human-computer and computer-computer interactions. Although most of this data was initially generated for ad-hoc human consumption to aid with debugging and troubleshooting systems and deployments\, their systematic treatment using well-known data processing techniques can unlock valuable insight about operations within organizations. Log Data may sometimes be the only feasible source of some of this insight. Processing Log Data poses new challenges as compared to traditional data management. Firstly\, Log Data is mostly textual requiring ad-hoc parsing to surface its meaning. Secondly\, Log Data tends to be extremely voluminous and is generated with high velocity posing a unique set of challenges in its acquisition and storage in a cost-effective manner. Lastly\, Log Data requires new query languages and techniques to unlock its full potential. X15 is a scalable purpose-built platform to acquire\, store\, and manage Machine Data. In this talk we will look at X15’s architecture\, some of its design decisions and use cases. \nBIOS: Vinayak Borkar is Vice President of Engineering at FireEye\, Inc. Prior to FireEye’s acquisition of X15\, he was a co-founder and the CTO of X15 Software. Prior to X15\, Vinayak was the CTO and head of engineering at DVO Software and the inventor and lead contributor of Hyracks\, an open-source parallel data processing platform built at UC Irvine. He began his career at BEA Systems\, where he led the development of the first XQuery-based data integration platform. Vinayak was the recipient of the Facebook Fellowship award for his contribution in the area of large-scale data management and holds a BS in Computer Science and Engineering from University of Mumbai and an MS in Computer Science and Engineering from Indian Institute of Technology Bombay\, and a PhD. in Information and Computer Science from the University of California at Irvine.
URL:https://isg.ics.uci.edu/event/vinayak-borkar-fireeye-inc-the-x15-machine-data-management-platform/
LOCATION:DBH 4011
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20181116T150000
DTEND;TZID=America/Los_Angeles:20181116T160000
DTSTAMP:20261015T024208
CREATED:20181222T021505Z
LAST-MODIFIED:20181222T021505Z
UID:842-1542380400-1542384000@isg.ics.uci.edu
SUMMARY:Dr. Andrey Balmin and Mayank Pradhan (Workday): Workday Prism Analytics: Unifying Interactive and Batch Data Processing Using Apache Spark
DESCRIPTION:Abstract: Workday Prism Analytics enables data discovery and interactive Business Intelligence analysis for Workday customers. To prepare data for analysis\, business users can setup data transformation pipelines in an interactive\, self-service\, modern data prep environment. Thus\, Workday Prism Analytics needs to run three types of scalable data processing applications: “always on” query engine and data prep applications\, and on-demand batch execution of transformation pipelines. We standardized on Apache Spark and Spark SQL for all three applications\, due to its scalability\, as well as\, flexibility and extensibility of the Spark’s Catalyst compiler. All applications share much of the compilation and execution code\, except for sampling\, caching\, and result extraction. \n  \nIn this talk we will\, first\, introduce Workday and then Prism Analytics. We will then zoom into Spark-based interactive and batch data processing components of Prism Analytics. We will then describe the data prep transformations\, and their compilation into Spark DataFrames\, through Spark-SQL Catalyst plans\, in both interactive and batch mode. We will focus on some challenges we encountered while compiling and executing complex pipelines and queries. For example\, Spark SQL compilation times exceeded execution time for some low-latency queries. And compiled plans grew dangerously for data prep pipelines with multiple self-joins and self-unions. We will describe caching\, sampling\, and query compilation techniques that allow us to support interactive user experience. This includes a join co-sampling component that improves system usability when joining large datasets. Finally\, we will conclude with an overview of the open challenges that we plan to tackle in the future. \n  \nBios: \nDr. Andrey Balmin is a Sr. Principal Engineer at Workday\, where he is building the self-service Prism Analytics platform\, continuing the work he began at Platfora (which was acquired by Workday in 2016). Prior to this\, he was a Research Staff Member at IBM Almaden Research Center where he focused on search and query processing of semi-structured and graph-structured data in Data Warehousing and\, later\, Big Data platforms. He holds a Ph.D. degree in Computer Science from UC San Diego. \n  \nMayank Pradhan is a Senior Engineering Manager at Workday focused on building Analytics Platform for Workday’s customers. His team develops the backend engines in cloud that run a variety of workloads including\, data ingestion\, interactive data preparation\, and OLAP cubes for large scale\, high volume interactive querying. Prior to Workday\, Mayank worked on industry shifting data processing products like Platfora\, ParAccel (the columnar database technology behind Redshift)\, IBM DB2. He has 18 years of industry experience building distributed databases. He did his M.S in Computer Science from Santa Clara University and BS Computer Science from Pune University India.
URL:https://isg.ics.uci.edu/event/dr-andrey-balmin-and-mayank-pradhan-workday-workday-prism-analytics-unifying-interactive-and-batch-data-processing-using-apache-spark/
LOCATION:DBH 3011
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20181102T110000
DTEND;TZID=America/Los_Angeles:20181102T120000
DTSTAMP:20261015T024208
CREATED:20181024T025814Z
LAST-MODIFIED:20190128T173206Z
UID:793-1541156400-1541160000@isg.ics.uci.edu
SUMMARY:Sushant Jain : Large scale and low latency data distribution from database to servers
DESCRIPTION:Many applications at Google are structured with data stored in a transactional database (source of truth) and same data being required by servers distributed worldwide. For efficient and fast computation servers store this data in memory. Further\, the database is changing continuously and we need to update the in-memory view of these large number of servers in real-time. For example\, in Google Search Ads application we have Advertisers configuration stored in a database and this data is loaded in the memory of various servers to compute Ads in a scalable and fast way. In this talk\, we describe our solution to this data distribution problem and the challenges that we encountered in providing a highly reliable and low latency service. \n  \nSpeaker Bio:  \nSushant Jain is a member of the Ads Quality Infrastructure group at Google Inc. His research interests include distributed systems and network routing. He is currently an engineering director and a lead engineer for multiple products in Ads Quality Infrastructure with a focus on data management and distribution. Many of the systems developed as part of his work at Google (such as WhyHigh\, Bandwidth Enforcer\, B4 Network) are actively deployed at Google and have had significant research impact as well. He is a recipient of the Best Paper Award at ACM SIGCOMM IMC 2011. He received his Ph.D. from the University of Washington in 2005 and a B.Tech. from IIT Delhi in 1999.
URL:https://isg.ics.uci.edu/event/large-scale-and-low-latency-data-distribution-from-database-to-servers/
LOCATION:DBH 6011
ATTACH;FMTTYPE=image/jpeg:https://isg.ics.uci.edu/wp-content/uploads/2018/10/google-datacenter-tech-13.jpg
END:VEVENT
END:VCALENDAR