Adding three learnable 'complementor' sequences to each input channel of a PatchTST-style transformer lowers forecasting error by 1-5 percent on standard benchmarks, though the stated information-theoretic guarantee does not actually apply to the trained model.
R.; Chen, M.; Rodrigues, M
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Sequence Complementor: Complementing Transformers For Time Series Forecasting with Learnable Sequences
Adding three learnable 'complementor' sequences to each input channel of a PatchTST-style transformer lowers forecasting error by 1-5 percent on standard benchmarks, though the stated information-theoretic guarantee does not actually apply to the trained model.