25 March 2006

Yesterday was Structured Learning Day

I'm out in Chicago at the atomic learning workshop and yesterday was structured prediction day. There were a lot of cool talks on pretty much all the major SP techniques: Charles talked about efficient training of CRFs, Yasemin talked about semi-supervised learning in M3Ns and SVMISOs, Ben talked about efficient training of M3Ns for combinatorial-style problems (like word alignment), Drew talked about planning as a SP problem, Vasin talked about the tradeoffs of local vs. global inference in SP, and I of course talked about search.

I really enjoyed Drew's talk. He is considering the problem of robot navigation, which is typically handled using A* search and some very crafty hand-written heuristic rules for generating the cost map over which A* search runs. He wants to get rid of the crafty part and replace it with learning. The idea is simple and cute: use observed features the robot receives to learn to produce a cost map so that when A* runs it finds the right path. Here, he defines the right path by having a human remote control the robot and drive it to the correct place. He casts this as a max-margin problem and solves it using very fast subgradient methods. There's no paper on this yet, but if all goes well there will be soon. I think there's a lot of stuff here that could strongly influence how we think about SP.

There were many questions raised at the workshop that I deserve significant thought. These include:

  1. What is structured learning?
  2. How does structured learning related to multi-task learning (ala Rich Caruana and others)?
  3. What sort of techniques are there for dealing with un- or partially-labeled data for structured learning?
  4. What can be done about featuritis (i.e., throwing in all possible features)? Also: Is this a legitimate concern?
  5. How important is it what loss function we optimize?
  6. When is local learning enough (ala Dan Roth) and when must you do "global learning?"
  7. What training techniques scale sufficiently?
Almost all of these questions deserve separate posts, and of course they are non-independent. Modulo feedback, I'll probably start at the top and work my way down. (Of course, if John beats me to it, I'll just post on his blog and cross-link here.)

7 comments:

Deepak said...

Structured Learning techniques:

More and more I am getting the feeling that this should exactly be the opposite direction we should be taking.

I like to work on what I call the Wal-mart effect problems: "Almost as good -- but for cheap".
Hal likes the so called Saks Fifth Avenue approach: "Just slightly better but a lot more expensive."

I have a strong feeling that working on such (SP) problems means getting married more to principles of Machine Learning than trying to make any progress towards real world problems. I initially started off working on a more principled theoritic way of attacking problems couple of years ago but now very strongly believe this is simply useless.

Hal is one of his post says:
"Fortunately, I think there are many interesting real-world problems for which simple memorization techniques will not work, and deeper "analysis" or "understanding" is required."

Unfortunately, this is what a lot of lot of smart (young?) people in the NLP/ML community think. They simply cannot admit the fact that simple techniques go a long way and cannot understand the fact that
a more complicated model gives very little improvements and generally never scales easily. Why cannot people simply use heuristicy and hackery approaches that have been proven over years to work well?

Walmart (and not Saks Fifth Avenue) is the biggest retail corportaion for perhaps this reason. I know I am taking a jab at the entire community here but I would encourage healthy discussions on this topic.

hal said...

I started a separate post on heuristics to discuss this. Please reply there.

Kevin said...

I don't think that structured learning is such a complicated approach--people have worked on prediction problems with structured outputs for years. For example, speech recognition (predicting a sequence of words), communication theory (decoding streams of bits), etc. are all so-called "structured learning" problems. It's just that recently the term has been coined and people looked at things in a more general light.

Hal, regarding your post on the TTI atomic learning workshop--I'd appreciate if you could comment on each of the issues mentioned when you have time. :)

. said...

酒店經紀PRETTY GIRL 台北酒店經紀人 ,禮服店 酒店兼差PRETTY GIRL酒店公關 酒店小姐 彩色爆米花酒店兼職,酒店工作 彩色爆米花酒店經紀, 酒店上班,酒店工作 PRETTY GIRL酒店喝酒酒店上班 彩色爆米花台北酒店酒店小姐 PRETTY GIRL酒店上班酒店打工PRETTY GIRL酒店打工酒店經紀 彩色爆米花

seldamuratim said...

Really trustworthy blog. Please keep updating with great posts like this one. I have booked marked your site and am about to email it to a few friends of mine that I know would enjoy reading..
sesli sohbetsesli chatkamerali sohbetseslisohbetsesli sohbet sitelerisesli chat siteleriseslichatsesli sohpetseslisohbet.comsesli chatsesli sohbetkamerali sohbetsesli chatsesli sohbetkamerali sohbet
seslisohbetsesli sohbetkamerali sohbetsesli chatsesli sohbetkamerali sohbet

DiSCo said...

Really trustworthy blog. Please keep updating with great posts like this one. I have booked marked your site and am about to email it

to a few friends of mine that I know would enjoy reading..
seslisohbet
seslichat
sesli sohbet
sesli chat
sesli
sesli site
görünlütü sohbet
görüntülü chat
kameralı sohbet
kameralı chat
sesli sohbet siteleri
sesli chat siteleri
görüntülü sohbet siteleri
görüntülü chat siteleri
kameralı sohbet siteleri
canlı sohbet
sesli muhabbet
görüntülü muhabbet
kameralı muhabbet
seslidunya
seslisehir
sesli sex

Sesli Chat said...

Really trustworthy blog. Please keep updating with great posts like this one. I have booked marked your site and am about to email it

to a few friends of mine that I know would enjoy reading..
seslisohbet
seslichat
sesli sohbet
sesli chat
sesli
sesli site
görünlütü sohbet
görüntülü chat
kameralı sohbet
kameralı chat
sesli sohbet siteleri
sesli chat siteleri
sesli muhabbet siteleri
görüntülü sohbet siteleri
görüntülü chat siteleri
görüntülü muhabbet siteleri
kameralı sohbet siteleri
kameralı chat siteleri
kameralı muhabbet siteleri
canlı sohbet
sesli muhabbet
görüntülü muhabbet
kameralı muhabbet
birsesver
birses
seslidunya
seslisehir
sesli sex