Generating Long Sequences with Sparse Transformers — HN submission

Tue, 16 Jan 2024 17:15:58 GMT

Generating Long Sequences with Sparse Transformers

3 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Generating Long Sequences with Sparse Transformers — mentioned by p1esk

Sat, 28 Mar 2020 05:13:54 GMT

Interesting you mentioned Makridakis competitions. There's one going on right now on Kaggle, and the current leader believes a NN will be the winning model: https://www.kaggle.com/c/m5-forecasting-accuracy/discussion/... More generally, it seems that time series forecasting so far has mostly attracted statisticians with little DL experience [1]. Now that there is $50k prize, this will be a good test of whether statistical methods are "still king". If I were to enter this field, I'd probably look into latest transformer based models, especially the ones used to model raw audio data, e.g. [2].…

Paper and discussion history. A mention is not an endorsement.

Generating Long Sequences with Sparse Transformers · HackerPapers discussions

Generating Long Sequences with Sparse Transformers — HN submission

Generating Long Sequences with Sparse Transformers — mentioned by p1esk