Introduces recency-biased causal attention via heavy-tailed decay reweighting to improve Transformer performance on time-series forecasting benchmarks.
TSMixer: An all-MLP architecture for time series forecast-ing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Recency Biased Causal Attention for Time-series Forecasting
Introduces recency-biased causal attention via heavy-tailed decay reweighting to improve Transformer performance on time-series forecasting benchmarks.