BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv6.8.15//EN
X-ORIGINAL-URL:https://stage.utoronto.ca/
X-WR-CALNAME:CANSSI Ontario STAGE
X-WR-CALDESC:
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-PUBLISHED-TTL:PT1H
X-MS-OLK-FORCEINSPECTOROPEN:TRUE
BEGIN:VEVENT
CLASS:PUBLIC
UID:MEC-c8ee2cce3e6bc0a3db40dd08ebcb1b58@stage.utoronto.ca
DTSTART:20260504T090000Z
DTEND:20260508T170000Z
DTSTAMP:20260318T185400Z
CREATED:20260318
LAST-MODIFIED:20260506
PRIORITY:5
SEQUENCE:22
TRANSP:OPAQUE
SUMMARY:Ivado Bootcamp: Statistical Insights into Modern AI Systems
DESCRIPTION:\nThe goal of this bootcamp is to equip statisticians with a working command of advanced AI tools, especially large language models (LLMs), deep learning, reinforcement learning, agents, and AI alignment. Specific topics going to be covered:\n\n\n\nAI alignment statistically framed: turn safety/helpfulness/non-toxicity into measurable quantities (hypothesis tests, risk bounds, selective prediction/abstention); practice red-teaming and auditing with error control.Deep learning through a statistical lens: generalization under shift, robustness, calibration and when bounds meaningfully predict deployment behavior.Large language models (LLMs)AI agents: decision loops with uncertainty and feedback; risk-aware policies, auditable logs, and monitoring.Causal reasoning with LLMs: distinguishing predictive vs. causal targets; sensitivity analyses; documenting assumptions for defensible decisions.Reinforcement learning: statistically principled exploration, off-policy evaluation, confidence sets, and safety/fairness implications.\n\n\n\nConfirmed Speakers\n\n\n\nBang Liu (Université de Montréal)\n\n\n\nJiancong Xiao (University of Pennsylvania)\n\n\n\nMarouane Idrissi (UQAM)\n\n\n\nYanxun Xu (Johns Hopkins University)\n\n\n\nAmirhossein Kazemnejad (Mila).\n\n\n\n\n
URL:https://stage.utoronto.ca/events/ivado-bootcamp/
LOCATION:2920 Chemin de la tour, Room 5357 Montréal (Québec) H3T 1J4
ATTACH;FMTTYPE=image/png:https://stage.utoronto.ca/wp-content/uploads/2026/03/Screenshot-2026-03-18-at-2.55.25 PM.png
END:VEVENT
END:VCALENDAR