{"id":2654,"date":"2024-10-23T12:18:48","date_gmt":"2024-10-23T10:18:48","guid":{"rendered":"https:\/\/wordpress-test.app.u-pariscite.fr\/diip\/?p=2654"},"modified":"2024-10-23T12:18:52","modified_gmt":"2024-10-23T10:18:52","slug":"stratos-idreos-self-designing-data-systems-for-the-ai-era","status":"publish","type":"post","link":"https:\/\/wordpress-test.app.u-pariscite.fr\/diip\/stratos-idreos-self-designing-data-systems-for-the-ai-era\/","title":{"rendered":"Stratos Idreos – Self-designing Data Systems for the AI Era"},"content":{"rendered":"

[et_pb_section fb_built=”1″ admin_label=”section” _builder_version=”3.22″][et_pb_row _builder_version=”3.22.1″ border_color_all=”#3255c9″ border_style_all=”groove”][et_pb_column type=”1_2″ _builder_version=”3.22.1″][et_pb_text _builder_version=”3.22.1″ min_height=”11px” custom_margin=”||-25px|||” custom_padding=”||0px|||”]<\/p>\n

Stratos Idreos<\/span><\/p>\n

December 7, 2022, at 4 PM<\/span><\/p>\n

Online (Zoom)<\/span><\/p>\n

 <\/p>\n

[\/et_pb_text][\/et_pb_column][et_pb_column type=”1_2″ _builder_version=”3.22.1″][\/et_pb_column][\/et_pb_row][et_pb_row custom_padding=”44px|||||” custom_margin=”80px||80px” _builder_version=”3.22.1″][et_pb_column type=”2_3″ _builder_version=”3.22.1″][et_pb_text _builder_version=”3.22.1″ custom_margin=”-51px|||||” custom_padding=”0px|||||”]<\/p>\n

Abstract<\/strong><\/h3>\n

 <\/p>\n

Data systems are everywhere. A data system is a collection of data structures and algorithms working together to achieve complex data processing tasks. For example, with data systems that utilize the correct data structure design for the problem at hand, we can reduce the monthly bill of large-scale data applications on the cloud by hundreds of thousands of dollars. We can accelerate data science tasks by dramatically speeding up the computation of statistics over large amounts of data. We can train drastically more neural networks within a given time budget, improving accuracy. However, knowing the right data system design for any given scenario is a notoriously hard problem; there is a massive space of possible designs, while no single design is perfect across all data, AI models, and hardware contexts. In addition, building a new system may take several years for any given (fixed) design.<\/p>\n

We will discuss our quest for the first principles of AI system design. We will show that it is possible to reason about this massive design space. This allows us to create a self-designing system that can take drastically different shapes to optimize for the workload, hardware, and available cloud budget using a grammar for systems. These shapes include designs that are discovered automatically and do not (always) exist in the literature or industry, yet they can be more than 10x faster for modern AI and big data applications. We will discuss examples from diverse AI areas, including image storage and classification, neural networks, statistics, and big data systems.<\/p>\n

[\/et_pb_text][\/et_pb_column][et_pb_column type=”1_3″ _builder_version=”3.22.1″][et_pb_video_slider _builder_version=”3.22.1″][et_pb_video_slider_item _builder_version=”3.22.1″ show_image_overlay=”off” src=”https:\/\/www.youtube.com\/watch?v=0fvFmmDe4nE” src_webm=”https:\/\/www.youtube.com\/watch?v=0fvFmmDe4nE”][\/et_pb_video_slider_item][\/et_pb_video_slider][\/et_pb_column][\/et_pb_row][\/et_pb_section][et_pb_section fb_built=”1″ _builder_version=”3.22.1″][et_pb_row _builder_version=”3.22.1″][et_pb_column type=”1_3″ _builder_version=”3.22.1″][et_pb_image src=”https:\/\/wordpress-test.app.u-pariscite.fr\/diip\/wp-content\/uploads\/sites\/27\/2022\/11\/StratosIdreosPhoto.jpeg” align=”center” _builder_version=”3.22.1″ custom_margin=”20px|125px||||”][\/et_pb_image][\/et_pb_column][et_pb_column type=”2_3″ _builder_version=”3.22.1″][et_pb_text _builder_version=”3.22.1″ custom_padding=”0px|||||”]<\/p>\n

Prof. Stratos Idreos
<\/strong>(Harvard University)
<\/strong>

<\/strong><\/h3>\n

Stratos Idreos is an associate professor of Computer Science at Harvard University, where he leads the Data Systems Laboratory. For his Ph.D. thesis on adaptive indexing, Stratos was awarded the 2011 ACM\u00a0SIGMOD Jim Gray Doctoral Dissertation award and the 2011 ERCIM Cor Baayen award from the European Research Council on Informatics\u00a0and Mathematics. In 2015 he was awarded the IEEE TCDE Rising Star Award from the IEEE Technical Committee on Data Engineering for his\u00a0work on adaptive data systems, and in 2022 he received the ACM SIGMOD Test of Time award for the NoDB concept. \u00a0Stratos is also a\u00a0recipient of the National Science Foundation Career award and the Department of Energy Early Career award. Stratos was PC Chair of ACM\u00a0SIGMOD 2021 and IEEE ICDE 2022, he is the founding editor of the ACM\/IMS Journal of Data Science and the chair of the ACM SoCC\u00a0Steering Committee.\u00a0Finally,\u00a0Stratos received the\u00a02020 ACM SIGMOD Contributions award for his work on\u00a0reproducible research.<\/p>\n

[\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row custom_margin=”120px||” _builder_version=”3.22.1″ locked=”off”][et_pb_column type=”4_4″ _builder_version=”3.0.47″][et_pb_divider _builder_version=”3.22.1″][\/et_pb_divider][et_pb_text admin_label=”\u00c0 lire aussi” _builder_version=”3.22.1″ z_index_tablet=”500″]<\/p>\n

Other distinguished lectures
<\/span><\/h2>\n

[\/et_pb_text][et_pb_blog posts_number=”4″ include_categories=”65″ show_author=”off” show_date=”off” show_pagination=”off” module_id=”page_type_blog” _builder_version=”3.22.1″ header_level=”h4″ border_width_bottom_fullwidth=”1px” border_color_bottom_fullwidth=”rgba(51,51,51,0.18)” custom_padding=”||50px|” z_index_tablet=”500″][\/et_pb_blog][\/et_pb_column][\/et_pb_row][\/et_pb_section]<\/p>\n","protected":false},"excerpt":{"rendered":"

Stratos Idreos December 7, 2022, at 4 PM Online (Zoom)   Abstract   Data systems are everywhere. A data system is a collection of data structures and algorithms working together to achieve complex data processing tasks. For example, with data systems that utilize the correct data structure design for the problem at hand, we can… Lire la suite Stratos Idreos – Self-designing Data Systems for the AI Era<\/span><\/a><\/p>\n","protected":false},"author":560,"featured_media":1150,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_et_pb_use_builder":"on","_et_pb_old_content":"","_et_gb_content_width":"","footnotes":""},"categories":[53,1,65],"tags":[],"class_list":["post-2654","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-53","category-diip","category-distinguished-lectures"],"_links":{"self":[{"href":"https:\/\/wordpress-test.app.u-pariscite.fr\/diip\/wp-json\/wp\/v2\/posts\/2654","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/wordpress-test.app.u-pariscite.fr\/diip\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/wordpress-test.app.u-pariscite.fr\/diip\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/wordpress-test.app.u-pariscite.fr\/diip\/wp-json\/wp\/v2\/users\/560"}],"replies":[{"embeddable":true,"href":"https:\/\/wordpress-test.app.u-pariscite.fr\/diip\/wp-json\/wp\/v2\/comments?post=2654"}],"version-history":[{"count":2,"href":"https:\/\/wordpress-test.app.u-pariscite.fr\/diip\/wp-json\/wp\/v2\/posts\/2654\/revisions"}],"predecessor-version":[{"id":2657,"href":"https:\/\/wordpress-test.app.u-pariscite.fr\/diip\/wp-json\/wp\/v2\/posts\/2654\/revisions\/2657"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/wordpress-test.app.u-pariscite.fr\/diip\/wp-json\/wp\/v2\/media\/1150"}],"wp:attachment":[{"href":"https:\/\/wordpress-test.app.u-pariscite.fr\/diip\/wp-json\/wp\/v2\/media?parent=2654"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/wordpress-test.app.u-pariscite.fr\/diip\/wp-json\/wp\/v2\/categories?post=2654"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/wordpress-test.app.u-pariscite.fr\/diip\/wp-json\/wp\/v2\/tags?post=2654"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}