Chapter 10 · Part 4
Transformers for Time Series
A clear-eyed survey of transformers for forecasting — what works, what doesn't, and how to read the literature critically. Informer, Autoformer, FEDformer, PatchTST, iTransformer, Crossformer, TimeXer, and others, plus the Bergmeir critique and the cherry-picking problem in published benchmarks.
Learning objectives
By the end of this chapter you will be able to:
- ▸Place each transformer variant on the Informer → Autoformer → FEDformer → PatchTST → iTransformer → Crossformer → TimeXer map
- ▸Read transformer-forecasting papers critically
- ▸Recognise why simpler baselines often outperform transformers on standard benchmarks
- 1.1Introduction
- 2.1Background and Related Work
- 3.1Critical Analysis of Reported Results
- 4.1Discussion
- 5.1State-of-the-Art Transformer Architectures for Time Series Forecasting
- 6.1Top-Ranked Transformers from Benchmark Leaderboards
Get the full chapter
All eleven chapters · 478 references · private Discord community.
← Previous · Chapter 9
Deep Learning for Time Series
Next · Chapter 11 →
Foundation Models and LLMs for Forecasting