Liam Paninski

Think long and hard before taking this class. Not because it's bad, but because it requires a serious commitment of your time and effort. This class is really two classes in one -- it covers two semesters of material (all of 3105/4105 and all of 3107/4107) plus the classes are 2hr 45min twice a week. Also, it's impossible to get ahead of your work, because there's always another problem set due in just a few days (see the workload below). Of course, it's also worth six credits, so you'll be rewarded for your efforts, especially if you can pull off a good grade. But just appreciate how long you'll be spending in each class and doing problem sets and just generally doing probability/statistics. In addition, IMO, the fact that this class goes at double-speed makes it more than twice as difficult. For example, if you were to ever miss a class or ever be unfocused during class, you're suddenly way behind. Furthermore, there's less time to let the often difficult concepts sink in before you've moved onto concepts which build on top of those concepts. If you're confused about anything, going to office hours is very important, otherwise you may stuck behind for a while. Two other important details to realize about the class: (1) It's almost entirely master's students, many of them getting master's in statistics. So the people in this class are bound to be pretty smart and you can't re…

Nice guy but boring class. Basically he spends the whole class doing proofs and working out calculations. He give good examples, where everyone figures out in the first 5 min how to set up and solve it, but then he goes on for 15 min solving tedious calculations. He should just skip to the answer. I took as an undergrad a probability course which I think helped me alot, thus this class was fairly easy for me. I think those who took this class as an intro to probability theory had a very difficult time. I hate the Ross book we used. It uses examples to teach, not proofs, which is something I don't like (others might like it though). Also, I feel that the book got pretty useless by the later chapters (almost as if Ross was tired of writing it)

Prof. Paninski is friendly and laid back. However, I spent the whole time lost in the class because I don't feel like there was enough explanation of the theories, examples were just done, and in all fairness, he did try to see if everyone was clear, but his problem is that instead of explaining the method and how to think about a certain problem, he just does it in class. So I ended up understanding what he was doing and not understanding why he was doing it. The material was really hard, the homework was hard, everything about the class was hard, and if you couldn't make it to the recitations or the office hours (as was my situation) you ended up lost the whole semester. Piece of advice: Don't take the class unless you absolutely need it! I need it for my major (I'm a stat major), and it was ridiculous...

Flippin hard material! Before you read this, be aware that I am an undergrad who was forced to take this class because i couldnt fit anything else in my schedule. Most people in this class were bschool and stats masters, so I am speaking from an undergrad perspective (therefore others may have found the course easier than I did). Professor Paninski is a cool guy, very laid back and friendly. I think this was his first time teaching as well. The course material was quite difficult and I had a hard time following him. The theme of the class was "oh, well if you see my mistake, let me know" or "ya, well it looks something like that." Anyone who takes math classes knows these statements tend to pop up. I felt they popped up a little to often in this class, usually to the point that it was hard for me to grasp what was right and what was wrong. The real problem with his teaching style is something alot of teachers have, he sets the bar way too high. He doesn't do any examples of the theories taught in class, leaving students to fend for themselves. The homework problems were explained by teh TA, and if you miss recitation you will be clueless (as i was) on all of them.

NA 1 Columbia University: Arts & Sciences Fall 2024 Course: STATGR5293_001_2024_3-TOPICSINMODERNSTATISTICS : STATGR5293_001_2024_3 - TOPICS IN MODERN STATISTICS Instructor: Xiaofu He

Problem sets due EVERY SINGLE CLASS. That's right, every Monday and every Wednesday. They're usually around ten questions from the textbook, some of which are pretty straightforward, some of which can be pretty challenging. The problem sets won't play such a big role in your final grade though. It's really about the midterm which covers all of probability and the final which covers all of statistics (it's not cumulative). They were both eight questions and were tough but not impossible.

The materials are quite different from other DS electives. 1 Columbia University: Arts & Sciences Fall 2022 Course: STATGR5293_002_2022_3-TOPICSINMODERNSTATISTICS : Applied Machine Learning for Image Analysis- STATGR5293_002_2022_3 - TOPICS IN MODERN STATISTICS Instructor: Xiaofu He

I will recommend to my friends and new graduate student to pursue this course due to its practical orientation and applied machine learning. Professor Xiaofu He is great professor and his knowledge is beyond comparision. 1 Columbia University: Arts & Sciences Fall 2021 Course: STATGR5293_001_2021_3-TOPICSINMODERNSTATISTICS : STATGR5293_001_2021_3 - TOPICS IN MODERN STATISTICS Instructor: Xiaofu He