BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Ashoka University - ECPv6.17.4//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://www.ashoka.edu.in
X-WR-CALDESC:Events for Ashoka University
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Asia/Kolkata
BEGIN:STANDARD
TZOFFSETFROM:+0530
TZOFFSETTO:+0530
TZNAME:IST
DTSTART:20240101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Asia/Kolkata:20250130T170000
DTEND;TZID=Asia/Kolkata:20250204T200000
DTSTAMP:20241221T044113Z
CREATED:20241202T011739Z
LAST-MODIFIED:20241221T044113Z
UID:68684-1738256400-1738699200@www.ashoka.edu.in
SUMMARY:CWC Winter School 2025 (Application Deadline Extended Till 07 Jan 2025)
DESCRIPTION:The Centre for Writing and Communication is delighted to solicit applications for its \nWinter School 2025 \nIn 2025\, we are offering three schools simultaneously: \n i. The Winter School for Research Writing in the Humanities and Social Sciences (for PhD\, Masters and ASP students at Ashoka University) \nii. Professional Communication in English (for Ashoka University Staff and Students) \niii. The Art of Scientific Writing (for Ashoka University students in the Sciences). \nAdditionally\, we are offering optional workshops covering niche areas in research and critical thinking in the humanities and social sciences.  \n \nFor details and information on how to apply\, please have a look at the course catalogue. \nApplications are open for Ashoka University Students and Staff. The deadline for receiving applications is extended till 07 January 2025. All classes (except for the optional workshops) will be held at the Ashoka University campus. In case you have any questions\, please contact us at cwc@ashoka.edu.in
URL:https://www.ashoka.edu.in/event/cwc-winter-school-2025-application-deadline-extended-till-07-jan-2025/
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Kolkata:20250204T133000
DTEND;TZID=Asia/Kolkata:20250204T150000
DTSTAMP:20250128T054304Z
CREATED:20250127T060047Z
LAST-MODIFIED:20250128T054304Z
UID:72510-1738675800-1738681200@www.ashoka.edu.in
SUMMARY:Semi-Bandit Learning for Monotone Stochastic Optimization by Arpit Agarwal
DESCRIPTION: Technical seminar series announcement\n“Semi-Bandit Learning for Monotone Stochastic Optimization”\nby Arpit Agarwal \n \nAssistant Professor\nComputer Science & Engineering\nIndian Institute of Technology Bombay \n\nArpit Agarwal is an Assistant Professor in the Department of Computer Science and Engineering at IIT Bombay. Prior to joining IIT Bombay\, he was a postdoctoral researcher at FAIR Labs (Meta)\, where he worked with Max Nickel on socially responsible recommendation systems. Before that\, he was a postdoctoral fellow at the Data Science Institute at Columbia University\, hosted by Prof. Yash Kanoria and Prof. Tim Roughgarden. He completed his PhD in the Department of Computer & Information Science at the University of Pennsylvania\, under the guidance of Prof. Shivani Agarwal. Arpit’s research lies in the field of machine learning (ML) and artificial intelligence (AI)\, with a specific focus on the interaction between humans and ML/AI systems. His work spans topics such as learning from implicit\, strategic\, and heterogeneous human feedback; understanding the dynamics of human-AI interactions and their long-term influences; and designing AI systems responsibly to mitigate undesired consequences for individuals and society. \nAbstract: Stochastic optimization is a widely used approach for optimization under uncertainty\, where uncertain input parameters are modeled by random variables. Exact or approximation algorithms have been obtained for several fundamental problems in this area. However\, a significant limitation of this approach is that it requires full knowledge of the underlying probability distributions. Can we still get good (approximation) algorithms if these distributions are unknown\, and the algorithm needs to learn them through repeated interactions? In this paper\, we resolve this question for a large class of “monotone” stochastic problems\, by providing a generic online learning algorithm with √ T log T regret relative to the best approximation algorithm (under known distributions). Importantly\, our online algorithm works in a semi-bandit setting\, where in each period\, the algorithm only observes samples from the r.v.s that were actually probed. Our framework applies to several fundamental problems in stochastic optimization such as prophet inequality\, Pandora’s box\, stochastic knapsack\, stochastic matchings and stochastic submodular optimization. \n\nDate: Tuesday\, February 04\, 2025\nTime: 1:30 PM IST\nVenue: AC-02-LR-206-207\nFor details: ashoka-cdlds@ashoka.edu.in or call: +91-9136857558\nZoom link: https://zoom.us/j/93578528184?pwd=pHITcwwcPOvMLCw44M6WzWf4D7Zj3G.1
URL:https://www.ashoka.edu.in/event/scdlds-ts01/
LOCATION:AC-02-LR-206-207\, Ashoka University\, Sonipat\, Haryāna\, 131029\, India
CATEGORIES:Offline
ATTACH;FMTTYPE=image/png:https://www.ashoka.edu.in/wp-content/uploads/2025/01/TS1_arpit.png
ORGANIZER;CN="SCDLDS":MAILTO:ashoka-cdlds@ashoka.edu.in
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Kolkata:20250204T133000
DTEND;TZID=Asia/Kolkata:20250204T154500
DTSTAMP:20250128T054638Z
CREATED:20250127T235923Z
LAST-MODIFIED:20250128T054638Z
UID:72592-1738675800-1738683900@www.ashoka.edu.in
SUMMARY:SCDLDS Talk
DESCRIPTION: Technical seminar series announcement\n"Semi-Bandit Learning for Monotone Stochastic Optimization"\nby Arpit Agarwal \n \n \n \n \n \n \nAssistant Professor\nComputer Science & Engineering\nIndian Institute of Technology Bombay \nArpit Agarwal is an Assistant Professor at the CSE Department at IIT Bombay. His research lies in the area of machine learning (ML) and artificial intelligence (AI). His focus is on human-centered AI which includes learning from human feedback\, understanding AI impact on individuals and society\, and designing socially responsible AI. Prior to joining IIT Bombay\, he was a researcher at FAIR Labs (Meta). Before that he was a postdoctoral fellow at the Data Science Institute at Columbia University. He completed his PhD from the CIS Department at University of Pennsylvania\, and masters from CSA Department at IISc Bangalore where he was the recipient of the Computer Society of India Medal. \nAbstract: Stochastic optimization is a widely used approach for optimization under uncertainty\, where uncertain input parameters are modeled by random variables. Exact or approximation algorithms have been obtained for several fundamental problems in this area. However\, a significant limitation of this approach is that it requires full knowledge of the underlying probability distributions. Can we still get good (approximation) algorithms if these distributions are unknown\, and the algorithm needs to learn them through repeated interactions? Particularly\, can we design an online learning algorithm whose performance smoothly approaches the performance of an (offline) optimal algorithm which has knowledge of these distributions? \nIn this work\, we resolve this question for a large class of “monotone” stochastic problems\, by providing a generic online learning algorithm with \\sqrt{T log T} regret relative to the best approximation algorithm (under known distributions). Importantly\, our online algorithm works in a semi-bandit setting\, where in each period\, the algorithm only observes samples from the r.v.s that were actually probed. Our framework applies to several fundamental problems in stochastic optimization such as prophet inequality\, Pandora’s box\, stochastic knapsack\, stochastic matchings and stochastic submodular optimization. \nIn this talk\, I will first introduce the multi-armed bandits framework and describe the popular algorithmic principle of "optimism in the face of uncertainty". I will then give a brief introduction to stochastic optimization. Finally\, I will describe our result on conversion from offline to online semi-bandit algorithms for stochastic optimization. \nThis talk is based on a FOCS'24 paper with Rohan Ghuge and Viswanath Nagarajan- https://arxiv.org/pdf/2312.15427. \n\nDate: Tuesday\, February 04\, 2025\nTime: 1:30 PM IST\nVenue: AC-02-LR-206-207 \nFor details: ashoka-cdlds@ashoka.edu.in or call: +91-9136857558\nZoom link: https://zoom.us/j/93578528184?pwd=pHITcwwcPOvMLCw44M6WzWf4D7Zj3G.1
URL:https://www.ashoka.edu.in/event/scdlds-talk/
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Kolkata:20250204T170000
DTEND;TZID=Asia/Kolkata:20250204T181500
DTSTAMP:20250204T033721Z
CREATED:20250204T033721Z
LAST-MODIFIED:20250204T033721Z
UID:72913-1738688400-1738692900@www.ashoka.edu.in
SUMMARY:Masterclass with Kunal Upadhyay
DESCRIPTION:We are excited to invite you to an insightful Master class with Kunal Upadhyay\, Co-founder of Bharat Innovation Fund and IIMA Ventures\, and Senior Investment Advisor at ADB Ventures. He will be joining as a guest speaker in Shridhar Sethuram's class on "Demystifying Investments: Private Equity and Venture Capital."\nJoin us to learn from Kunal's extensive experience in leading India-focused climate-tech\, deep-tech\, and impact funds managing over $100mn in assets. As a recognized leader in the investment space and an ET40 under Forty awardee\, Kunal brings valuable insights from his journey of building and managing various successful fund initiatives. \nEvent Details:\nSession 1 (Open for All Including Staff)\nDate: 4th February\, Tuesday\nTime: 5:00 PM – 6:15 PM\nVenue: ACO2 LR 007 \nRegister for the Session here: https://docs.google.com/forms/d/e/1FAIpQLSfVMGjvv1B45dPfkCjhpuU4yDlceoLHb4m2WBaCXn4PNcM7gA/viewform \nSession 2 (Exclusive for Ashoka Student / Alum Entrepreneurs) \nDate: 4th February\, Tuesday\nTime: 6:45 PM – 7:30 PM\nVenue: CFE\, Admin Block (5th Floor) \nLooking forward to your presence!
URL:https://www.ashoka.edu.in/event/masterclass-with-kunal-upadhyay/
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Kolkata:20250204T183000
DTEND;TZID=Asia/Kolkata:20250204T200000
DTSTAMP:20250202T205738Z
CREATED:20250128T213437Z
LAST-MODIFIED:20250202T205738Z
UID:72740-1738693800-1738699200@www.ashoka.edu.in
SUMMARY:Environmental Studies Colloquium
DESCRIPTION:Dear Ashokan\, \nDepartment of Environmental Studies cordially invites you to the first colloquium in the Spring Colloquium Series 2025. \nTitle of the Talk- Narrating and Navigating Transformation through Food Networks in Bengaluru and California \nBio of the Speaker- Camille Frazier is Agricultural Land Equity Program Lead at the California Strategic Growth Council in the Governor’s Office of Land Use and Climate Innovation. She has a PhD in sociocultural anthropology from the University of California\, Los Angeles and is the author of Cultivating Livability: Food\, Class\, and the Urban Future in Bengaluru (University of Minnesota Press\, 2024). \nMode- ONLINE \nZOOM LINK- https://zoom.us/j/94767057831?pwd=klIUw0c5SZqrCsOxagnfXet1V62EsS.1 \nWe look forward to seeing you there. \n  \nWarm Regards\, \nDepartment of Environmental Studies
URL:https://www.ashoka.edu.in/event/environmental-studies-colloquium/
END:VEVENT
END:VCALENDAR