Customer Reviews

Monte Carlo Strategies in Scientific Computing

5 star:		(2)
4 star:		(2)
3 star:		(0)
2 star:		(1)
1 star:		(1)

 

 

Jun Liu has been a prominent researcher in MCMC since the mid 90's. His research has contributed a great deal to the development of Gibbs sampler, sequential Monte Carlo, weighting/importance sampling, missing data, and MCMC related applications in Bioinformatics. Not surprisingly, this book has them all, plus many other interesting topics. The final two chapters review some of the theories. This book has a strong flavor in statistical physics, which I like very much. It also contains some applications in, for examples, engineering (e.g. nonlinear filter, sequential Monte Carlo), biology (DNA sequencing), image analysis (clustering) and stochastic optimization.
Jun Liu presents things very clearly and concisely, and hopefully you can benefit from his book.

The author is a top young gun from Harvard's Statistics Dept., and is an expert in many applied areas that utilize Monte Carlo, like the red hot bioinformatics. This book covers MC techniques developed in many different fields e.g., physics,structural biology, statistics. It has a wide range of examples, some of which are very new (e.g., bioinformatics) and non-standard. It contains many interesting ideas, and is concise mathematically and easy to read. Highly recommended.

I purchased this book because it had a section on Hybrid Monte Carlo and I was looking for something longer and more recent than Radford Neal's well-known paper on the subject.

The HMC portion of the book was pretty thorough but riddled with spelling and grammatical errors in the text, enough that I became suspicious that this was a draft that had seen only one or two casual QA/editing passes. That led me to suspect there might be errors in the math, which drive me crazy -- nothing frustrates me more than spending a lot of time trying to understand a set of equations before realizing there's a typo in them.

If you're looking for a book that covers a topic that others don't, it's probably worth getting, especially if you're really comfortable with the math, but I wouldn't recommend as a general introduction to Monte Carlo methods.

This review is about the material quality of the printing in the copy I received. This is not about the content.

I have access to a real copy of this edition in the local library. It is the usual quality book: beautifully bound; the paper inside is high-quality, very soft and slightly off-white; and the printing of the text is very sharp. The version I received from Amazon claimed to be exactly the same, but was very different:
- The paper inside is whiter, horribly white, like standard printing A4 paper;
- The text printing looks like a cheap photocopy of the original. It don't even match a home laser printer. Some formulas are difficult to read. Moreover, some pages are not even centered.

It looks and feels like a cheap knock-off photocopy done in a garage. Authors should avoid their work being degraded with this cheap printing.

Solid theory in Monte Carlo, but less application examples

Now, I am reading this book. I would like to mark it 4.5 stars if possible.

[1] The author is an expert of computational statistics and Bayesian analysis, an active mathematician at Harvard.
[2] The background of this book is related to bioinformatics, physics, etc, which puzzles me a lot while reading.
[3] You can find the author's deep understanding of MC methods throughout the book.
[3] It is suitable for the graduate students of statistics.
[4] It's a little bit pity that this book is not purely written for mathematicians. Anyway, it is a witness of MC methods in development.