Critique

Just saw that the page got an update, will try to reply with an update critique by the end of Thursday.

Comments

This page is apparently unfinished, so it seems there is a lot of work left to do. Here are my current suggestions:

• Abstract is good but should cover what is being done in the page. Right now it seems very general, and the single sentence description of the title section may also serve as abstract.
• Builds on / Related Pages are unfinished, I think there is a lot of related topics to cover. Annealing, gradient descent, optimization in general, all kinds of machine learning stuff I assume.
• I guess SGD is a good start, but the page ends here. I think code examples work great in this page, and I would cover several other optimization techniques next to SGD.
• The wiki page for optimization has a wealth of suggestions, how about picking good representative examples of the topics listed here: https://en.wikipedia.org/wiki/Stochastic_optimization?
• Also using Wikipedia as bibliography is probably not a good idea, since it is very volatile. Maybe a textbook on SGD?

Marking Scheme

I a scale of 1 to 5, where 1 means "strongly disagree" and 5 means "strongly agree" please rate and comment on the following:

   The topic is relevant for the course. 5
   The writing is clear and the English is good. 4 
   The page is written at an appropriate level for CPSC 522 students (where the students have diverse backgrounds). 3
   The formalism (definitions, mathematics) was well chosen to make the page easier to understand. 4
   The abstract is a concise and clear summary. 3 (The abstract is a bit general and refers to Stochastic Optimization instead of the wiki page.)
   There were appropriate (original) examples that helped make the topic clear. 5 
   There was appropriate use of (pseudo-) code. 1 (There is none.)
   It had a good coverage of representations, semantics, inference and learning (as appropriate for the topic). 2 ()
   It was neither too short nor too long for the topic. 3 ( For Markov Logic this is correct, on the other hand there seems to be a lot of content on Markov Logic Networks.) 
   It was an appropriate unit for a page (it shouldn't be split into different topics or merged with another page). 4 (Technically, it is)
   It links to appropriate other pages in the wiki. 2
   The references and links to external pages are well chosen. 2
   I would recommend this page to someone who wanted to find out about the topic. 1
   This page should be highlighted as an exemplary page for others to emulate. 1

If I was grading it out of 20, I would give it: 5

CRITIQUE UPDATE:

The page improved but still seems quite unfinished. Anyway, here is my updated review.

Comments

• Abstract is good but should cover what is being done in the page. Right now it seems very general, and the single sentence description of the title section may also serve as abstract.
• Builds on / Related Pages are unfinished, I think there is a lot of related topics to cover. Annealing, gradient descent, optimization in general, all kinds of machine learning stuff I assume.
• I guess SGD is a good start. I think code works great in this page, for example some short python implementation or more elaborate pseudo code example.
• It is good that AdaGrad and Adam got add, but I there is little explanation of the pseudocode. It makes things a bit confusing.
• Also using Wikipedia as bibliography is probably not a good idea, since it is very volatile. Maybe a textbook on SGD?
• Citations have brackets around them, this seems like a formatting mistake.
• The page might benefit from a somewhat more precise introduction and more context about Optimization. Why do we need it and what are we solving with it?
• There are only few references to other pages.

Marking Scheme

I a scale of 1 to 5, where 1 means "strongly disagree" and 5 means "strongly agree" please rate and comment on the following:

   The topic is relevant for the course. 5
   The writing is clear and the English is good. 4 
   The page is written at an appropriate level for CPSC 522 students (where the students have diverse backgrounds). 5
   The formalism (definitions, mathematics) was well chosen to make the page easier to understand. 4
   The abstract is a concise and clear summary. 3 (The abstract is a bit general and refers to Stochastic Optimization instead of the wiki page.)
   There were appropriate (original) examples that helped make the topic clear. 3 ( The examples for ADAM and AdaGrad are not explained and a bit confusing.)
   There was appropriate use of (pseudo-) code. 1 (There is none.)
   It had a good coverage of representations, semantics, inference and learning (as appropriate for the topic). 3 (Some learning is covered.)
   It was neither too short nor too long for the topic. 3 ( For Markov Logic this is correct, on the other hand there seems to be a lot of content on Markov Logic Networks.) 
   It was an appropriate unit for a page (it shouldn't be split into different topics or merged with another page). 4 (Technically, it is)
   It links to appropriate other pages in the wiki. 1 (There are no links.)
   The references and links to external pages are well chosen. 3 (Reference seem to make sense, no external links)
   I would recommend this page to someone who wanted to find out about the topic. 2
   This page should be highlighted as an exemplary page for others to emulate. 1

If I was grading it out of 20, I would give it: 10