BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CMSA - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://cmsa.fas.harvard.edu
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:20240310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20241103T060000
END:STANDARD
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
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250502T120000
DTEND;TZID=America/New_York:20250502T130000
DTSTAMP:20260606T151916
CREATED:20241211T195435Z
LAST-MODIFIED:20250428T151202Z
UID:10003650-1746187200-1746190800@cmsa.fas.harvard.edu
SUMMARY:Incentives for data sharing in federated learning
DESCRIPTION:Member Seminar \nSpeaker: Han Shao\, Harvard CMSA \nTitle: Incentives for data sharing in federated learning \nAbstract: Federated learning has recently emerged as a powerful approach for enabling collaboration across large populations of learning agents. However\, agents may have incentives to defect from the collaboration—that is\, to withdraw or contribute less data than expected—due to the costs of data curation and privacy concerns. This raises several key questions: What happens when agents defect\, and how can we prevent such defections? \n 
URL:https://cmsa.fas.harvard.edu/event/member-seminar-5225/
LOCATION:CMSA Room G10\, CMSA\, 20 Garden Street\, Cambridge\, MA\, 02138\, United States
CATEGORIES:Member Seminar
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/CMSA-Member-Seminar-5.2.25.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250505T150000
DTEND;TZID=America/New_York:20250505T160000
DTSTAMP:20260606T151916
CREATED:20250226T173940Z
LAST-MODIFIED:20250226T173940Z
UID:10003715-1746457200-1746460800@cmsa.fas.harvard.edu
SUMMARY:Quantum Field Theory and Physical Mathematics
DESCRIPTION:Quantum Field Theory and Physical Mathematics Seminar
URL:https://cmsa.fas.harvard.edu/event/qft_5525/
LOCATION:CMSA Room G10\, CMSA\, 20 Garden Street\, Cambridge\, MA\, 02138\, United States
CATEGORIES:Quantum Field Theory and Physical Mathematics
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250505T163000
DTEND;TZID=America/New_York:20250505T173000
DTSTAMP:20260606T151916
CREATED:20250407T140808Z
LAST-MODIFIED:20250501T134436Z
UID:10003733-1746462600-1746466200@cmsa.fas.harvard.edu
SUMMARY:Thinking Outside the Ballot Box
DESCRIPTION:Colloquium \nSpeaker: Ariel Procaccia\, Harvard University \nTitle: Thinking Outside the Ballot Box \nAbstract: How should one design unprecedented democratic processes capable of handling enormous sets of alternatives like all possible policies\, bills\, or statements? I argue that this challenge can be addressed through a framework called generative social choice\, which fuses the rigor of social choice theory with the flexibility and power of large language models. I then explore an application of generative social choice to the problem of identifying a proportionally representative slate of opinion statements. This includes a discussion of desired properties\, an algorithm that provably achieves them\, an implementation using GPT\, and insights from an end-to-end pilot. By providing guarantees\, generative social choice could alleviate concerns about AI-driven democratic innovation and help unlock its potential.
URL:https://cmsa.fas.harvard.edu/event/colloquium-5525/
LOCATION:CMSA Room G10\, CMSA\, 20 Garden Street\, Cambridge\, MA\, 02138\, United States
CATEGORIES:Colloquium
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/CMSA-Colloquium-5.5.2025.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250506T161500
DTEND;TZID=America/New_York:20250506T181500
DTSTAMP:20260606T151916
CREATED:20250407T174129Z
LAST-MODIFIED:20250407T174129Z
UID:10003738-1746548100-1746555300@cmsa.fas.harvard.edu
SUMMARY:Geometry and Quantum Theory Seminar
DESCRIPTION:Geometry and Quantum Theory Seminar
URL:https://cmsa.fas.harvard.edu/event/quantumgeo_5625/
LOCATION:Science Center 507\, 1 Oxford Street\, Cambridge\, 02138
CATEGORIES:Geometry and Quantum Theory Seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250509T120000
DTEND;TZID=America/New_York:20250509T130000
DTSTAMP:20260606T151916
CREATED:20241211T195446Z
LAST-MODIFIED:20250506T153832Z
UID:10003649-1746792000-1746795600@cmsa.fas.harvard.edu
SUMMARY:Asset pricing with heterogeneous agents
DESCRIPTION:Member Seminar \nSpeaker: Sergiy Verstyuk\, Harvard CMSA \nTitle: Asset pricing with heterogeneous agents \nAbstract: This talk will introduce the basics of continuous-time finance\, discuss important existing theories and models\, as well as present some new asset pricing results in a setting with many heterogeneous investors. (Joint work with Puskar Mondal.) \n 
URL:https://cmsa.fas.harvard.edu/event/member-seminar-5925/
LOCATION:CMSA Room G10\, CMSA\, 20 Garden Street\, Cambridge\, MA\, 02138\, United States
CATEGORIES:Member Seminar
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/CMSA-Member-Seminar-5.9.25.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250512T150000
DTEND;TZID=America/New_York:20250512T160000
DTSTAMP:20260606T151916
CREATED:20250226T174007Z
LAST-MODIFIED:20250605T134144Z
UID:10003716-1747062000-1747065600@cmsa.fas.harvard.edu
SUMMARY:An index for 2d invertible phases of quantum many-body systems
DESCRIPTION:Quantum Field Theory and Physical Mathematics Seminar \nSpeaker: Nikita Sopenko\, IAS \nTitle: An index for 2d invertible phases of quantum many-body systems
URL:https://cmsa.fas.harvard.edu/event/qft_51225/
LOCATION:CMSA Room G10\, CMSA\, 20 Garden Street\, Cambridge\, MA\, 02138\, United States
CATEGORIES:Quantum Field Theory and Physical Mathematics
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/CMSA-QFT-and-Physical-Mathematics-5.12.25-1.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250512T163000
DTEND;TZID=America/New_York:20250512T173000
DTSTAMP:20260606T151916
CREATED:20250407T140851Z
LAST-MODIFIED:20250506T191033Z
UID:10003734-1747067400-1747071000@cmsa.fas.harvard.edu
SUMMARY:Factorizations for data analysis
DESCRIPTION:Colloquium \nSpeaker: Anna Seigal\, Harvard University \nTitle: Factorizations for data analysis \nAbstract: We can find structure in data by factoring it into building blocks\, which should be interpretable for the context at hand. A classical example is principal component analysis (PCA)\, which uses the eigendecomposition of the covariance matrix to find axes of variation in a dataset. Starting from PCA\, I will discuss matrix and tensor factorizations for data analysis\, and the linear and multilinear algebra that underpins their theoretical properties. We will see examples from causal inference\, independent component analysis\, and dimensionality reduction.
URL:https://cmsa.fas.harvard.edu/event/colloquium-51225/
LOCATION:CMSA Room G10\, CMSA\, 20 Garden Street\, Cambridge\, MA\, 02138\, United States
CATEGORIES:Colloquium
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/CMSA-Colloquium-5.12.2025.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250514T120000
DTEND;TZID=America/New_York:20250514T130000
DTSTAMP:20260606T151916
CREATED:20250501T182905Z
LAST-MODIFIED:20250502T173004Z
UID:10003746-1747224000-1747227600@cmsa.fas.harvard.edu
SUMMARY:Report on the Perimeter Institute Theory+AI Workshop
DESCRIPTION:Conference Reports  \nSpeaker: Hugo Cui\, Harvard CMSA \nTitle: Report on the Perimeter Institute Theory+AI Workshop \nAbstract: I will give a survey and brief summary of some of the talks given at the Theory+AI Workshop: Theoretical Physics for AI event organized by Perimeter Institute in April\, on approaches to machine learning theory inspired from physics. \nLink : https://events.perimeterinstitute.ca/event/993/
URL:https://cmsa.fas.harvard.edu/event/confrep_51425/
LOCATION:CMSA 20 Garden Street Cambridge\, Massachusetts 02138 United States
CATEGORIES:Conference Reports
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/CMSA-Conference-Reports-5.14.2025.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250516T120000
DTEND;TZID=America/New_York:20250516T130000
DTSTAMP:20260606T151916
CREATED:20250218T161047Z
LAST-MODIFIED:20250513T152517Z
UID:10003714-1747396800-1747400400@cmsa.fas.harvard.edu
SUMMARY:Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining
DESCRIPTION:Member Seminar \nSpeaker: Samy Jelassi\, CMSA \nTitle: Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining \nAbstract: Reinforcement Learning has become a crucial step in training state-of-the-art language models such as DeepSeek-R1 for solving mathematical problems. In this talk\, I will first review the mechanisms of Reinforcement Learning fine-tuning. Then\, I will present a systematic end-to-end study of RL fine-tuning for mathematical reasoning\, training models entirely from scratch on different mixtures of fully open datasets and fine-tuning them with RL. Doing so allows us to investigate the effects of the pretraining data mixture on the behavior of RL\, and its interaction with the model size and choices of the algorithm hyperparameters. Our study reveals that RL algorithms consistently converge towards a dominant output distribution\, amplifying patterns in the pretraining data. We also find that models of different scales trained on the same data mixture will converge to distinct output distributions\, suggesting that there are scale-dependent biases in model generalization. \nThe second part of the talk is based on a joint work with Rosie Zhao\, Alex Meterez\, Cengiz Pehlevan\, Sham Kakade and Eran Malach: https://arxiv.org/abs/2504.07912 \n 
URL:https://cmsa.fas.harvard.edu/event/member-seminar-51625/
LOCATION:CMSA Room G10\, CMSA\, 20 Garden Street\, Cambridge\, MA\, 02138\, United States
CATEGORIES:Member Seminar
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/CMSA-Member-Seminar-5.16.25.png
END:VEVENT
END:VCALENDAR