Please Note: This seminar will be given in-person.
|
Distinguished Lecture Series
Vladimir
Vovk Room: DC 1302 |
Nonparametric prediction and testing
The assumption of randomness (the data are generated in the IID fashion) is the key assumption used in machine learning and much of nonparametric statistics. My main topics will be prediction under this assumption and testing the assumption. The treatment of both topics will be based on the relatively recent technique of conformal prediction, but I will try to connect it with David A. Sprott's ideas and areas of research pointing out some paradoxical features of prediction and testing in the framework of unrestricted randomness. On one hand, they are barely possible, in the sense that the existence of non-trivial prediction and testing procedures is fragile: they cease to exist when the problem settings are modified in natural ways. On the other, such procedures can be highly efficient in realistic situations; I will give both theoretical and experimental results demonstrating this.
Vladimir Vovk
Vladimir
Vovk
is
Professor
of
Computer
Science
at
Royal
Holloway,
University
of
London.
His
research
interests
include
machine
learning
and
the
foundations
of
probability
and
statistics.
He
was
one
of
the
founders
of
prediction
with
expert
advice,
an
area
of
machine
learning
avoiding
making
any
statistical
assumptions
about
the
data.
In
2001
he
and
Glenn
Shafer
published
a
book
("Probability
and
Finance:
It's
Only
a
Game")
on
new
game-theoretic
foundations
of
probability;
the
sequel
("Game-theoretic
Foundations
for
Probability
and
Finance")
appeared
in
2019.
His
second
book
("Algorithmic
Learning
in
a
Random
World",
2005),
co-authored
with
Alex
Gammerman
and
Glenn
Shafer,
is
the
first
monograph
on
conformal
prediction,
method
of
machine
learning
that
provides
provably
valid
measures
of
confidence
for
their
predictions;
an
expanded
and
updated
second
edition
has
just
been
published
(December
2022).
His
current
research
centres
on
applications
of
game-theoretic
probability
to
statistics
and
machine
learning.
David A. Sprott (1930-2013)
Professor David Sprott was the first Chair (1967-1975) of the Department of Statistics and Actuarial Science at the University of Waterloo and first Dean of the Faculty of Mathematics (1967-1972). The David Sprott Distinguished Lecture Series was created in recognition of his tremendous leadership at a formative time of our department, as well as his highly influential research in statistical science.