The article emphasizes the wrong thing, in my view. The interesting part is that compression -- without learning a model -- can be used for classification. This raises the question of what other information-theoretic measures can be used; cheaper, lossy ones.
I remember seeing an example of using zip to classify languages. You take a set of documents of equal size where you know the languages, then individually concatenate and zip them with the unknown text. The smallest compressed output is likely to be the target language.
Ideally, you'd take all the documents in each language, and compress them in turn with the unclassified text, to see which compresses it better. But this won't work very well with gzip, since it compresses based on a 32KB sliding window. You might as well truncate the training data for each class to the last 32KB (more or less). So to get any performance at all out of a gzip-based classifier, you need to combine a ton of individually quite bad predictors with some sort of ensemble method. (The linked code demonstrates a way of aggregating them which does not work at all).
How much better would that get if you append all but one of the equal size documents? (or other combinations like 2 of the top results after using a single one)
Better, if the compressor can use all that extra context. Gzip, and most traditional general purpose compressors, can't.
It's hard to use distant context effectively. Even general purpose compression methods which theoretically can, often deliberately reset part of their context, since assuming a big file follows the same distribution throughout as in its beginning often hurts compression more than just starting over periodically.
An increasingly common refrain in machine learning is “intelligence is compression.” Folks who believe that might bristle at the distinction between learning and compression.
I doubt it because learned features already constitute lossy compression. The question is what kind of compression; lossy vs. lossless, learned vs. unlearned.
The point is not to have "elegant and compact" code, this is meant to be a fun curiosity, and doing it in 10 lines is just an additional layer of challenge for the heck of it.
The interesting thing is not in whether GZip can achieve SOTA, it's that it can do a decent job at all. (The interesting thing is not in whether the bear can recreate Mozart exactly, it's that it can play the piano at all.)
Yeah, it does demonstrate that you can use compression to measure similarity of two images.
But it also demonstrates that it's a pretty poor similarity measure. Something as simple as counting % of matches between the black and white pixels performs much better.
It's not trying to break records, it just shows a neat aspect of compression. It's still 8 times better than baseline, which showcases that compression can learn representation.
To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Review https://arxiv.org/abs/2304.09355\*