BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CMSA - ECPv6.17.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://live-hu-cmsa-222.pantheonsite.io
X-WR-CALDESC:Events for CMSA
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20250309T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20251102T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20260308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20261101T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20270314T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20271107T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20280312T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20281105T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260903T161500
DTEND;TZID=America/New_York:20260903T173000
DTSTAMP:20260804T134427Z
CREATED:20260803T204031Z
LAST-MODIFIED:20260804T134427Z
UID:10004037-1788452100-1788456600@live-hu-cmsa-222.pantheonsite.io
SUMMARY:Fall CMSA Welcome Event
DESCRIPTION:Fall CMSA Welcome Event \nDate: September 3\, 2026 \nTime: 4:15 pm \nLocation: CMSA Common Room\, 20 Garden Street\, Cambridge MA \n  \nAll CMSA and Math affiliates are invited. \n 
URL:https://live-hu-cmsa-222.pantheonsite.io/event/welcome2026/
LOCATION:CMSA 20 Garden Street Cambridge\, Massachusetts 02138 United States
CATEGORIES:Event
ATTACH;FMTTYPE=image/jpeg:https://live-hu-cmsa-222.pantheonsite.io/media/CMSA_Wwlecome-2023-IMG_9367.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260908T090000
DTEND;TZID=America/New_York:20260911T170000
DTSTAMP:20260902T170935Z
CREATED:20260217T174544Z
LAST-MODIFIED:20260902T170935Z
UID:10003847-1788858000-1789146000@live-hu-cmsa-222.pantheonsite.io
SUMMARY:The Geometry of Machine Learning 2026
DESCRIPTION:The Geometry of Machine Learning 2026 \nDates: September 8–11\, 2026 \nLocation: Harvard CMSA\, Room G10\, 20 Garden Street\, Cambridge MA 02138 & via Zoom Webinar \nRegister to attend in person \nRegister for Zoom Webinar \nLarge language models are presently\, and will increasingly\, be complemented by other dimensions of intelligence: formal verification and energy-based optimizers\, becoming parts of larger ecosystems. Can AIs reason geometrically and can we use geometry to reveal how data is currently processed in NNs? Can AIs reveal the geometry of mathematics\, as well as studying geometry as a subject within math. This conference is intended to continue the discussion of these topics. \nConfirmed Speakers: \n\nNada Amin\, Harvard\nRandall Balestriero\, Brown\nMichael Brenner\, Harvard and Google\nBennet Chow\, UCSD\nSurya Ganguli\, Stanford\nBoris Hanin\, Princeton\nRoi Holtzman\, Oxford\nRobert Koirala\, UCSD\nDmitry Krotov\, Dynamical Mind\nSlava Krushkal\, Virginia\nJared Duker Lichtman\, Stanford\nMike Mulligan\, UCR\, Logical Intelligence\nLuca Pesce\, Harvard\nGabriel Poesia\, U Michigan (via Zoom)\nMathew Vanherreweghe\, Logical Intelligence\nSean Welleck\, CMU (via Zoom)\nMattiew Wyart\, JHU (via Zoom)\n\nOrganizers: Michael R. Douglas (CMSA) and Mike Freedman (CMSA) \n  \nSchedule \nTuesday\, Sep. 8\, 2026 \n8:15–8:45 am\nBreakfast \n8:45–9:30 am\nMike Mulligan\, UCR\, Logical Intelligence\nCompression is all you need: Modeling mathematics\nAbstract: The mathematics humans discover and value (“human math”) is a vanishingly small subset of all valid deductions (“formal math”). I’ll argue that human math is distinguished by its compressibility through hierarchically nested definitions and theorems\, like a polynomial-growth space rather than the exponential-growth space one might expect when proofs are viewed as strings of symbols. The argument combines toy monoid models with an empirical analysis of MathLib\, a large Lean library of formalized mathematics we treat as a proxy for human math. I’ll close with how compression itself can serve as a measure of mathematical interest\, giving agents a sense of direction toward where human math lives. \n9:45–10:30 am\nBoris Hanin\, Princeton \n10:30–11:00 am\nBreak \n11:00–11:45 am\nSlava Krushkal\, University of Virginia \n12:00–12:45 pm\nRobert Koirala and Bennett Chow\, UCSD\nAI for Ricci flow: Discovery and Formalization \n  \nWednesday\, Sep. 9\, 2026 \n8:15–8:45 am\nBreakfast \n8:45–9:30 am\nSurya Ganguli\, Stanford \n9:45–10:30 am\nMathew Vanherreweghe\, Logical Intelligence \n10:30–11:00 am\nBreak \n11:00–11:45 am\nMichael Brenner\, Harvard and Google \n12:00–12:45 pm\nMattiew Wyart\, JHU (via Zoom)\nLearn from your own latents\, not from tokens\nAbstract: Language models need more than a hundred thousand times the data a child does. One explanation is that predicting raw tokens is simply the wrong level: methods like data2vec and JEPA instead train a network to predict its own internal representations\, with strong empirical results but no theory of why. Using a hierarchical grammar that models that language and images have a hidden hierarchical structure\, we quantify the gain exactly. Token-level learning needs a number of examples growing exponentially with the depth of the hierarchy; latent prediction needs a number independent of it. We also show data2vec performs this hierarchical prediction implicitly\, which suggests that explicitly stacking levels – as in H-JEPA – yields little. \n  \nThursday\, Sep. 10\, 2026 \n8:15–8:45 am\nBreakfast \n8:45–9:30 am\nDmitry Krotov\, Dynamical Mind\nDense Associative Memory: Physical systems for novel AI architectures\nAbstract: Dense Associative Memories are recurrent neural networks with fixed-point attractor states that are described by an energy function. In contrast to conventional Hopfield Networks\, which were popular in the 1980s\, Dense Associative Memories have a very large information storage capacity\, making them appealing tools for many problems in AI. In this talk\, I will provide an intuitive understanding and mathematical framework for this class of models and give examples of problems in AI that can be tackled using these new ideas. Specifically\, I will explore the relationship between Dense Associative Memories and transformers. I will present a neural network called the Energy Transformer\, which unifies energy-based modeling\, associative memories\, and transformers in a single architecture. I will demonstrate how Energy Transformers can be used for challenging tasks in image processing\, solve partial differential equations\, and serve as computational modules for energy-based language modeling. I will also discuss an exciting possibility of mapping these models onto analog hardware accelerators\, which could enable much more energy-efficient inference compared to GPUs. \n9:45–10:30 am\nRoi Holtzman\, Oxford \n10:30–11:00 am\nBreak \n11:00–11:45 am\nSean Welleck\, CMU (via Zoom) \n12:00–12:45 pm\nGabriel Poesia\, University of Michigan (via Zoom) \nFriday\, Sep. 11\, 2026 \n8:15–8:45 am\nBreakfast \n8:45–9:30 am\nNada Amin\, Harvard \n9:45–10:30 am\nRandall Balestriero\, Brown University \n10:30–11:00 am\nBreak \n11:00–11:45 am\nLuca Pesce\, Harvard CMSA\nA spiked perspective on feature learning with gradient-based methods\nAbstract: Depth is widely believed to give neural networks a clear computational advantage over shallow models\, and making this belief precise is a central problem in learning theory. We study a controlled high-dimensional setting where this can be done. The targets are hierarchical: the relevant structure is distributed across latent subspaces of decreasing dimension\, so that a shallow model must resolve all of it simultaneously\, while a deep network does not. Each layer forms an intermediate representation\, allowing learning to proceed in stages\, with every stage reducing the effective dimension of the remaining problem. We analyze this staged mechanism through the gradient descent dynamics of a deep network yielding a sharp separation in sample complexity between shallow and deep architectures. The result is a concrete account of why depth allows such functions to be learned from substantially fewer samples than shallow methods require. \n12:00–12:45 pm\nJared Duker Lichtman\, Stanford \n  \nSupport provided by Logical Intelligence. \n \n  \n 
URL:https://live-hu-cmsa-222.pantheonsite.io/event/gml_2026/
LOCATION:CMSA 20 Garden Street Cambridge\, Massachusetts 02138 United States
CATEGORIES:Conference,Event
ATTACH;FMTTYPE=image/jpeg:https://live-hu-cmsa-222.pantheonsite.io/media/GML2026-Poster.4.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260915T090000
DTEND;TZID=America/New_York:20261121T170000
DTSTAMP:20260723T182727Z
CREATED:20251023T141842Z
LAST-MODIFIED:20260723T182727Z
UID:10003825-1789462800-1795280400@live-hu-cmsa-222.pantheonsite.io
SUMMARY:Lagrangian Floer Theory and Applications Program
DESCRIPTION:Lagrangian Floer theory and Applications Program \nDates: September 15–November 21\, 2026 \nLocation: CMSA G10\, 20 Garden St.\, Cambridge MA 02138 \nThis thematic program will focus on recent developments in Lagrangian Floer theory and applications.  These include the development of family Floer theory\, degeneration techniques\, Floer homotopy theory in the Lagrangian case\, Floer theory in prime characteristic\, and applications to problems in singularity theory\, geometry and dynamics. \nA one-week workshop will be held near the start of the program (September 28 – October 2\, 2026)\, with the same title as the thematic program. \nOrganizers: Denis Auroux (Harvard)\, Jonny Evans (Lancaster)\, and Chris Woodward (Rutgers) \n  \nTo express interest in attending the workshop or program\, and to apply for funding if available\, please fill out the form.  \nFunding from the National Science Foundation may be available for US-based graduate students and postdoctoral fellows. \n  \n \nimage: Water Sky Garden\, Vancouver\nDate: 31 January 2010\, 12:57:46\nSource: Studio Echelman\nAuthor: Peter Vanderwarker\, Studio Echelman \n 
URL:https://live-hu-cmsa-222.pantheonsite.io/event/lft2026/
LOCATION:CMSA 20 Garden Street Cambridge\, Massachusetts 02138 United States
CATEGORIES:Programs
ATTACH;FMTTYPE=image/jpeg:https://live-hu-cmsa-222.pantheonsite.io/media/LFT_poster-1.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260928T080000
DTEND;TZID=America/New_York:20261002T170000
DTSTAMP:20260901T190739Z
CREATED:20251027T191925Z
LAST-MODIFIED:20260901T190739Z
UID:10003827-1790582400-1790960400@live-hu-cmsa-222.pantheonsite.io
SUMMARY:Workshop on Lagrangian Floer theory and applications
DESCRIPTION:Workshop on Lagrangian Floer Theory and Applications \nDates: September 28 – October 2\, 2026 \nLocation: CMSA G10\, 20 Garden St.\, Cambridge MA 02138 \nThis  workshop is part of the Lagrangian Floer Theory and Applications Program \nRegistration Form \nSpeakers will include: \n\nMohammed Abouzaid\, Stanford University\nKenneth Blakey\, MIT\nCiprian Bonciocat\, Stanford\nSoham Chanda\, USC\nOctav Cornea\, University of Montréal\nClaire Dai\, Harvard\nIlaria Di Dedda\, University of Edinburgh\nTobias Ekholm\, Uppsala University\nSheel Ganatra\, USC\nSebastian Haney\, Harvard\nAndrew Hanlon\, University of Oregon\nSiu-Cheong Lau\, Boston University\nYanki Lekili\, Imperial College London\nElise LePage\, Columbia\nYin Li\, Uppsala University\nGeorgios Dimitroglou Rizell\, Uppsala University\nPaul Seidel\, MIT\nEgor Shelukhin\, University of Montréal\nVivek Shende\, Berkeley/Syddansk\n\nOrganizers: Denis Auroux (Harvard)\, Jonny Evans (Lancaster)\, and Chris Woodward (Rutgers) \n  \nSchedule outline \nMonday 9/28/26 \n\n\n\n9:00 – 9:30\nBreakfast\n\n\n9:30 – 10:30\nTalk 1\n\n\n10:30 – 11:00\nBreak\n\n\n11:00 – 12:00\nTalk 2\n\n\n12:00 – 1:30\nLunch\n\n\n1:30 – 2:30\nTalk 3\n\n\n2:30 – 3:00\nBreak\n\n\n3:00 – 4:00\nTalk 4\n\n\n\n  \nTuesday 9/29/26 \n\n\n\n9:00 – 9:30\nBreakfast\n\n\n9:30 – 10:30\nTalk 5\n\n\n10:30 – 11:00\nBreak\n\n\n11:00 – 12:00\nTalk 6\n\n\n12:00 – 1:30\nLunch\n\n\n1:30 – 2:30\nTalk 7\n\n\n2:30 – 3:00\nBreak\n\n\n3:00 – 4:00\nTalk 8\n\n\n\n  \nWednesday 9/30/26 \n\n\n\n9:00 – 9:30\nBreakfast\n\n\n9:30 – 10:30\nTalk 9\n\n\n10:30 – 11:00\nBreak\n\n\n11:00 – 12:00\nTalk 10\n\n\n12:00 – 1:30\nLunch\n\n\n1:30 – 2:30\nTalk 11\n\n\n2:30 – 3:00\nBreak\n\n\n3:00 – 4:00\nTalk 12\n\n\n\n  \nThursday 10/1/26 \n\n\n\n9:00 – 9:30\nBreakfast\n\n\n9:30 – 10:30\nTalk 13\n\n\n10:30 – 11:00\nBreak\n\n\n11:00 – 12:00\nTalk 14\n\n\n12:00 – 1:30\nLunch\n\n\n1:30 – 2:30\nTalk 15\n\n\n2:30 – 3:00\nBreak\n\n\n3:00 – 4:00\nTalk 16\n\n\n6:30\nDinner\n\n\n\n  \nFriday 10/2/26 \n\n\n\n9:00 – 9:30\nBreakfast\n\n\n9:30 – 10:30\nTalk 17\n\n\n10:30 – 11:00\nBreak\n\n\n11:00 – 12:00\nTalk 18\n\n\n12:00 – 1:30\nLunch\n\n\n1:30 – 2:30\nTalk 19\n\n\n2:30 – 3:00\nBreak\n\n\n3:00 – 4:00\nTalk 20\n\n\n\n  \n\n 
URL:https://live-hu-cmsa-222.pantheonsite.io/event/lftworkshop/
LOCATION:CMSA 20 Garden Street Cambridge\, Massachusetts 02138 United States
CATEGORIES:Workshop
ATTACH;FMTTYPE=image/jpeg:https://live-hu-cmsa-222.pantheonsite.io/media/Lagrangian-Workshop.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;VALUE=DATE:20270405
DTEND;VALUE=DATE:20270410
DTSTAMP:20260724T164228Z
CREATED:20260713T150638Z
LAST-MODIFIED:20260724T164228Z
UID:10003973-1806883200-1807315199@live-hu-cmsa-222.pantheonsite.io
SUMMARY:The Conformal Bootstrap and Mathematics
DESCRIPTION:The Conformal Bootstrap and Mathematics \nThe conformal bootstrap is a method originating in physics that seeks to define and study conformal quantum field theories in two and higher dimensions. In recent years\, surprising connections have emerged between the conformal bootstrap and several areas of mathematics\, including the spectral theory of automorphic forms\, the sphere packing problem\, and related questions in geometry\, analysis\, and number theory. These developments suggest both that the conformal bootstrap “knows” a remarkable amount of mathematics\, and that these mathematical structures can offer new ways of understanding quantum field theory. \nThis workshop will bring together experts from conformal field theory\, number theory\, spectral geometry\, discrete geometry\, and related fields to explore these emerging connections. One goal is to investigate how ideas and techniques from the conformal bootstrap can lead to new advances in mathematics. A complementary goal is to use insights from these mathematical disciplines to sharpen our understanding of conformal field theory and quantum field theory more broadly. \nOrganizers: James Bonifacio\, University of Mississippi; Henry Cohn\, MIT; Dalimil Mazáč\, Institute of Theoretical Physics\, Saclay; and Peter Sarnak\, IAS
URL:https://live-hu-cmsa-222.pantheonsite.io/event/bootstrap27/
LOCATION:CMSA 20 Garden Street Cambridge\, Massachusetts 02138 United States
CATEGORIES:Event,Workshop
ATTACH;FMTTYPE=image/png:https://live-hu-cmsa-222.pantheonsite.io/media/bootstrap_disk_v2_reduced.png
END:VEVENT
END:VCALENDAR