Kyle Roth

This post was created as an assignment in Irina Rish’s neural scaling laws course (IFT6167) in winter 2022. The post contains no summarization, only questions and thoughts. In this paper they mention that the mask vector is learned, and it sounds like the positional embeddings are also learned. I remember in Attention is all you need they found that cosine positional embeddings worked better than learned ones, especially for sequences of longer length. But now it seems like most papers are doing learned embeddings. If anyone knows why, send me an email.

This paper is all about trying a bunch of different changes to the training setup to see what affects the power law exponent over dataset size. Here are some of the answers: encoder-decoder size asymmetry: exponent not affected, but effective model capacity affected architecture (LSTM vs. Transformer): exponent not affected, but effective model capacity affected dataset quality (filtered vs. not): exponent and effective model capacity not effected, losses on smaller datasets affected dataset source (ParaCrawl vs. in-house dataset): exponent not affected adding independent noise: exponent not affected, but effective model capacity affected Here are some other things to test that I thought of while I read this:

This post was created as an assignment in Irina Rish’s neural scaling laws course (IFT6167) in winter 2022. The post contains no summarization, only questions and thoughts. Once I learned how the loss functions worked for each chunk, my first question was whether the earlier chunks were going to be able to learn the low-level features that later chunks would need. Figure 7 seems to show that they do, although their quality apparently decreases with increasingly local updates.

This post was created as an assignment in Bang Liu’s IFT6289 course in winter 2022. The structure of the post follows the structure of the assignment: summarization followed by my own comments. paper summarization permalink Word embeddings have gotten so good that state-of-the-art sentence classification can often be achieved with just a one-layer convolutional network on top of those embeddings. This paper dials in on the specifics of training that convolutional layer for this downstream sentence classification task.

This post was created as an assignment in Irina Rish’s neural scaling laws course (IFT6167) in winter 2022. The post contains no summarization, only questions and thoughts. This concept of wide vs. narrow supervision (rather than binary “supervised” and “unsupervised”) is an interesting and flexible way to think about the way these training schemes leverage data. The zero-shot CLIP matches the performance of 4-shot CLIP, which is a surprising result. What do the authors mean when they make this guess about zero-shot’s advantage: