BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Europe/Zurich BEGIN:DAYLIGHT DTSTART:20260329T030000 TZOFFSETFROM:+0100 TZOFFSETTO:+0200 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3 TZNAME:CEST END:DAYLIGHT BEGIN:STANDARD DTSTART:20251026T020000 TZOFFSETFROM:+0200 TZOFFSETTO:+0100 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10 TZNAME:CET END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20251031T155032Z UID:B0F8ADDF-176B-4C72-B910-9398E46DCE74 DTSTART;TZID=Europe/Zurich:20251031T140000 DTEND;TZID=Europe/Zurich:20251031T150000 DESCRIPTION:We are delighted to invite you to a seminar by Mr. Pangiotis Gr ontas\, the [recipient of the IEEE CSS Swiss Chapter Young Author Best Jou rnal Paper Award 2025](https://enotice.mmsend.com/link.cfm?r=5iypwKdLFQXui xwBc5XTug~~&pe=6_f0jz23nqoNOqaMqNPa_UWOBSLtvAcYsuj7AkvtB8NTQYhYg0vLBYGOxUy vSEOZsMrtpm7cKEGOOvQbsKv30w~~&t=gwUT5MRE-uEavrrC6tcDcg~~)\, who will prese nt his award-winning research.\n\nThe seminar can be followed in room ME C 2 405 of the EPFL ME building and on [Zoom](https://epfl.zoom.us/j/6300188 2786?pwd=G5ulqpMfWHZC8fbnFZwJf6uKI9hGBa.1). #control #data-driven #learnin g #systems #optimization\nAbstract:\nHierarchical decision-making problems \, such as bilevel programs and Stackelberg games\, are attracting increas ing interest in both the engineering and machine learning communities. Yet \, existing solution methods lack either convergence guarantees or computa tional efficiency\, due to the absence of smoothness and convexity. In thi s work\, we bridge this gap by designing BIG Hype\, a first-order hypergra dient-based algorithm for Stackelberg games\, and mathematically establish ing its convergence using tools from nonsmooth analysis. To evaluate the h ypergradient\, namely\, the gradient of the upper-level objective\, we dev elop an online scheme that simultaneously computes the lower-level equilib rium and its Jacobian. We demonstrate BIG Hype’s potential by deploying it on various large-scale bilevel problems\, such as demand response\, tra ffic routing\, and recommender systems.\n\nBio sketch:\nPanagiotis Grontas is a doctoral student in the Automatic Control Laboratory (IfA) at ETH Z ürich\, supervised by John Lygeros. He received an M.Sc. degree with dist inction in Robotics\, Systems\, and Controls from ETH Zürich\, and a Dipl oma degree in Mechanical Engineering from the National Technical Universit y of Athens. He is a recipient of the ETH Medal for outstanding Master’s theses and the IEEE CSS Swiss Chapter Young Author Best Journal Paper Awa rd 2025. His research is focused on the broad intersection of optimization \, machine learning\, and control.\n\nSpeaker(s): Panagiotis Grontas\n\nRo om: ME C2 405\, Bldg: MEC building\, EPFL\, Station 9\, Lausanne\, Switzer land\, Switzerland\, 1015\, Virtual: https://events.vtools.ieee.org/m/5077 53 LOCATION:Room: ME C2 405\, Bldg: MEC building\, EPFL\, Station 9\, Lausanne \, Switzerland\, Switzerland\, 1015\, Virtual: https://events.vtools.ieee. org/m/507753 ORGANIZER:giancarlo.ferraritrecate@epfl.ch SEQUENCE:58 SUMMARY:IEEE SWISS CSS SEMINAR - BIG Hype: Best Intervention in Games via D istributed Hypergradient Descent URL;VALUE=URI:https://events.vtools.ieee.org/m/507753 X-ALT-DESC:Description: <br /><div class="elementToProof">\n<p style="caret -color: rgb(0\, 0\, 0)\; color: rgb(0\, 0\, 0)\; font-family: Helvetica\; font-size: 14px\; font-style: normal\; font-variant-caps: normal\; font-we ight: 400\; letter-spacing: normal\; orphans: auto\; text-align: start\; t ext-indent: 0px\; text-transform: none\; white-space: normal\; widows: aut o\; word-spacing: 0px\; -webkit-text-stroke-width: 0px\; text-decoration: none\;"><span style="font-size: 12pt\;"><span style="caret-color: rgb(0\, 0\, 0)\; color: rgb(0\, 0\, 0)\; font-family: 'Open Sans'\, formata\, Verd ana\, sans-serif\; font-style: normal\; font-variant-caps: normal\; font-w eight: 400\; letter-spacing: normal\; text-align: start\; text-indent: 0px \; text-transform: none\; white-space: normal\; word-spacing: 0px\; -webki t-text-stroke-width: 0px\; background-color: rgb(255\, 255\, 255)\; text-d ecoration: none\; float: none\; display: inline !important\;"><span style= "caret-color: rgb(0\, 0\, 0)\; color: rgb(0\, 0\, 0)\; font-family: 'Open Sans'\, formata\, Verdana\, sans-serif\; font-style: normal\; font-variant -caps: normal\; font-weight: 400\; letter-spacing: normal\; text-align: st art\; text-indent: 0px\; text-transform: none\; white-space: normal\; word -spacing: 0px\; -webkit-text-stroke-width: 0px\; background-color: rgb(255 \, 255\, 255)\; text-decoration: none\; float: none\; display: inline !imp ortant\;">We are delighted to invite you to a seminar by Mr. Pangiotis Gro ntas\, the <a href="https://enotice.mmsend.com/link.cfm?r=5iypwKdLFQXuixwB c5XTug~~&amp\;pe=6_f0jz23nqoNOqaMqNPa_UWOBSLtvAcYsuj7AkvtB8NTQYhYg0vLBYGOx UyvSEOZsMrtpm7cKEGOOvQbsKv30w~~&amp\;t=gwUT5MRE-uEavrrC6tcDcg~~">recipient of the IEEE CSS Swiss Chapter Young Author Best Journal Paper Award 2025< /a>\, who will present his award-winning research.</span></span></span></p >\n<p style="caret-color: rgb(0\, 0\, 0)\; color: rgb(0\, 0\, 0)\; font-fa mily: Helvetica\; font-size: 14px\; font-style: normal\; font-variant-caps : normal\; font-weight: 400\; letter-spacing: normal\; orphans: auto\; tex t-align: start\; text-indent: 0px\; text-transform: none\; white-space: no rmal\; widows: auto\; word-spacing: 0px\; -webkit-text-stroke-width: 0px\; text-decoration: none\;"><span style="font-size: 12pt\;"><span style="car et-color: rgb(0\, 0\, 0)\; color: rgb(0\, 0\, 0)\; font-family: 'Open Sans '\, formata\, Verdana\, sans-serif\; font-style: normal\; font-variant-cap s: normal\; font-weight: 400\; letter-spacing: normal\; text-align: start\ ; text-indent: 0px\; text-transform: none\; white-space: normal\; word-spa cing: 0px\; -webkit-text-stroke-width: 0px\; background-color: rgb(255\, 2 55\, 255)\; text-decoration: none\; float: none\; display: inline !importa nt\;">The seminar can be followed in room ME C2 405&nbsp\; of the EPFL ME building and on <a href="https://epfl.zoom.us/j/63001882786?pwd=G5ulqpMfWH ZC8fbnFZwJf6uKI9hGBa.1">Zoom</a>.</span></span> #control #data-driven #lea rning #systems #optimization&nbsp\;</p>\nAbstract:&nbsp\;</div>\n<div clas s="elementToProof">Hierarchical decision-making problems\, such as bilevel programs and Stackelberg games\, are attracting increasing interest in bo th the engineering and machine learning communities. Yet\, existing soluti on methods lack either convergence guarantees or computational efficiency\ , due to the absence of smoothness and convexity. In this work\, we bridge this gap by designing BIG Hype\, a first-order hypergradient-based algori thm for Stackelberg games\, and mathematically establishing its convergenc e using tools from nonsmooth analysis. To evaluate the hypergradient\, nam ely\, the gradient of the upper-level objective\, we develop an online sch eme that simultaneously computes the lower-level equilibrium and its Jacob ian. We demonstrate BIG Hype&rsquo\;s potential by deploying it on various large-scale bilevel problems\, such as demand response\, traffic routing\ , and recommender systems.</div>\n<div class="elementToProof">&nbsp\;</div >\n<div class="elementToProof">Bio sketch:</div>\n<div class="elementToPro of">Panagiotis Grontas is a doctoral student in the Automatic Control Labo ratory (IfA) at ETH Z&uuml\;rich\, supervised by John Lygeros. He received an M.Sc. degree with distinction in Robotics\, Systems\, and Controls fro m ETH Z&uuml\;rich\, and a Diploma degree in Mechanical Engineering from t he National Technical University of Athens. He is a recipient of the ETH M edal for outstanding Master&rsquo\;s theses and the IEEE CSS Swiss Chapter Young Author Best Journal Paper Award 2025. His research is focused on th e broad intersection of optimization\, machine learning\, and control.</di v> END:VEVENT END:VCALENDAR