BEGIN:VCALENDAR
PRODID:-//Columba Systems Ltd//NONSGML CPNG/SpringViewer/ICal Output/3.3-
M3//EN
VERSION:2.0
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTAMP:20231123T094643Z
DTSTART:20231129T143000Z
DTEND:20231129T160000Z
SUMMARY:SQUIDS Seminar - A State-Space Perspective on Modelling and Infer
ence for Online Skill Rating
UID:{http://www.columbasystems.com/customers/uom/gpp/eventid/}w2ce-lpb0ed
xy-o5vye6
DESCRIPTION:Schedule:\n- 2:30pm: pretalk\n- 3:05pm: research talk 'How ma
thematics can inspire novel deep learning architectures: two case studie
s'\n \nAbstract: In the quantitative analysis of competitive sports\, a
fundamental task is to estimate the skills of the different agents (‘pla
yers’) involved in a given competition based on the outcome of pairwise
comparisons (‘matches’) between said players\, often in an online settin
g. In this talk\, I will discuss recent work in which we advocate for ad
option of the state-space modelling paradigm in solving this problem. Th
is perspective facilitates the decoupling of modelling from inference\,
enabling a more focused approach to development and critique of model as
sumptions\, while also fostering the development of general-purpose infe
rence tools. \n\nI will first describe some illustrative model classes w
hich arise in this framework\, before turning to a careful discussion of
inference and computation strategies for these models. A key challenge
throughout is to develop methodology which scales gracefully to problems
with a large number of players and a high frequency of matches. I then
conclude by describing some real-data applications of our approach\, dem
onstrating how this framework facilitates a practical workflow across di
fferent sports.\n\nThis is joint work with Samuel Duffield (Normal Compu
ting) and Lorenzo Rimella (Lancaster University).
STATUS:TENTATIVE
TRANSP:TRANSPARENT
CLASS:PUBLIC
LOCATION:G.114\, Alan Turing Building\, Manchester
END:VEVENT
END:VCALENDAR