BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//ARNI - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:ARNI
X-ORIGINAL-URL:https://arni-institute.org
X-WR-CALDESC:Events for ARNI
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:20250225T150000
DTEND;TZID=America/New_York:20250225T170000
DTSTAMP:20260426T103129
CREATED:20250217T144605Z
LAST-MODIFIED:20250224T195355Z
UID:1490-1740495600-1740502800@arni-institute.org
SUMMARY:ARNI WG Multi-resource-cost optimization of neural network models: Paul Schrater
DESCRIPTION:Title: Control when confidence is costly \nAbstract:\nWe develop a version of stochastic control that accounts for computational costs of inference. Past studies identified efficient coding without control\, or efficient control that neglects the cost of synthesizing information. Here we combine these concepts into a framework where agents rationally approximate inference for efficient control. Specifically\, we study Linear Quadratic Gaussian (LQG) control with an added internal cost on the relative precision of the posterior probability over the world state. This creates a trade-off: an agent can obtain more utility overall by sacrificing some task performance\, if doing so saves enough bits during inference. We discover that the rational strategy that solves the joint inference and control problem goes through phase transitions depending on the task demands\, switching from a costly but optimal inference to a family of suboptimal inferences related by rotation transformations\, each misestimate the stability of the world. In all cases\, the agent moves more to think less. This work provides a foundation for a new type of rational computations that could be used by both brains and machines for efficient but computationally constrained control.\nWe develop a version of stochastic control that accounts for computational costs of inference. Past studies identified efficient coding without control\, or efficient control that neglects the cost of synthesizing information. Here we combine these concepts into a framework where agents rationally approximate inference for efficient control. Specifically\, we study Linear Quadratic Gaussian (LQG) control with an added internal cost on the relative precision of the posterior probability over the world state. This creates a trade-off: an agent can obtain more utility overall by sacrificing some task performance\, if doing so saves enough bits during inference. We discover that the rational strategy that solves the joint inference and control problem goes through phase transitions depending on the task demands\, switching from a costly but optimal inference to a family of suboptimal inferences related by rotation transformations\, each misestimate the stability of the world. In all cases\, the agent moves more to think less. This work provides a foundation for a new type of rational computations that could be used by both brains and machines for efficient but computationally constrained control. \nZoom Link: https://columbiauniversity.zoom.us/j/98244449046?pwd=ZagtGamVQgwy8XrPdXdlzJRbgrXtVj.1
URL:https://arni-institute.org/event/arni-wg-multi-resource-cost-optimization-of-neural-network-models-paul-schrater/
LOCATION:Zuckerman Institute – L3-079\, 3227 Broadway\, New York\, NY\, 10027\, United States
END:VEVENT
END:VCALENDAR