HomeGroupsTalkZeitgeist
Hide this

Results from Google Books

Click on a thumbnail to go to Google Books.

Prediction, Learning, and Games by Nicolo…
Loading...

Prediction, Learning, and Games (2006)

by Nicolo Cesa-Bianchi, Gabor Lugosi

MembersReviewsPopularityAverage ratingConversations
171587,099 (4.75)None
None

None.

Loading...

Sign up for LibraryThing to find out whether you'll like this book.

No current Talk conversations about this book.

A wonderful synthesis of the literature on competitive, individual-sequence forecasting with expert advice. That is, the problems considered are all variants on a situation where you need to make a prediction about the future (or more generally take an action whose consequences will only be revealed in the future), have access to a range of "experts" or forecasting algorithms, and want to ensure that, no matter what actually happens, your performance will be close to that of the best expert. This is thus a study of sequential decision-making under uncertainty without probability. Often, but not always, the solution lies in taking weighted averages of the experts, giving more weight to those which have done well in the past. This works not because past performance provides any kind of inductive evidence of future success, but merely because it keeps your predictions from drifting too far from what is, in fact, working. (Perversely, many of the proofs rely on probabilistic arguments, but they don't make probabilistic assumptions.) Of course, it may be that even the best expert is very bad, but the possibility of improving on the experts is not really considered, though it's certainly possible (at least with convex loss functions).

Anyone at all interested in machine learning, forecasting, information, game theory, or decision-making under uncertainty needs to read this. It may also be useful to epistemologists. ( )
  cshalizi | Aug 8, 2008 |
no reviews | add a review

» Add other authors

Author nameRoleType of authorWork?Status
Nicolo Cesa-Bianchiprimary authorall editionsconfirmed
Lugosi, Gabormain authorall editionsconfirmed
You must log in to edit Common Knowledge data.
For more help see the Common Knowledge help page.
Series (with order)
Canonical title
Original title
Alternative titles
Original publication date
People/Characters
Important places
Important events
Related movies
Awards and honors
Epigraph
Dedication
First words
Quotations
Last words
Disambiguation notice
Publisher's editors
Blurbers
Publisher series
Original language

References to this work on external resources.

Wikipedia in English (1)

Book description
Haiku summary

Amazon.com Product Description (ISBN 0521841089, Hardcover)

This important new text and reference for researchers and students in machine learning, game theory, statistics and information theory offers the first comprehensive treatment of the problem of predicting individual sequences. Unlike standard statistical approaches to forecasting, prediction of individual sequences does not impose any probabilistic assumption on the data-generating mechanism. Yet, prediction algorithms can be constructed that work well for all possible sequences, in the sense that their performance is always nearly as good as the best forecasting strategy in a given reference class. The central theme is the model of prediction using expert advice, a general framework within which many related problems can be cast and discussed. Repeated game playing, adaptive data compression, sequential investment in the stock market, sequential pattern analysis, and several other problems are viewed as instances of the experts' framework and analyzed from a common nonstochastic standpoint that often reveals new and intriguing connections. Old and new forecasting methods are described in a mathematically precise way in order to characterize their theoretical limitations and possibilities.

(retrieved from Amazon Mon, 30 Sep 2013 14:19:06 -0400)

"This important new text and reference for researchers and students in machine learning, game theory, statistics, and information theory offers the first comprehensive treatment of the problem of predicting individual sequences. Unlike standard statistical approaches to forecasting, prediction of individual sequences does not impose any probabilistic assumption on the data-generating mechanism. Yet, prediction algorithms can be constructed that work well for all possible sequences, in the sense that their performance is always nearly as good as the best forecasting strategy in a given reference class."--BOOK JACKET.… (more)

Quick Links

Swap Ebooks Audio
2 wanted1 pay

Popular covers

Rating

Average: (4.75)
0.5
1
1.5
2
2.5
3
3.5
4 1
4.5
5 3

Is this you?

Become a LibraryThing Author.

 

Help/FAQs | About | Privacy/Terms | Blog | Contact | LibraryThing.com | APIs | WikiThing | Common Knowledge | Legacy Libraries | Early Reviewers | 94,039,077 books! | Top bar: Always visible