Introduces recency-biased causal attention via heavy-tailed decay reweighting to improve Transformer performance on time-series forecasting benchmarks.
Is mamba effective for time series forecasting? ArXiv, abs/2403.11144
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
A Mamba-plus-attention hybrid with FFT-Laplace and TCN encoding claims state-of-the-art accuracy and efficiency on eight multivariate time-series forecasting benchmarks.
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.
-
UniMamba: A Unified Spatial-Temporal Modeling Framework with State-Space and Attention Integration
A Mamba-plus-attention hybrid with FFT-Laplace and TCN encoding claims state-of-the-art accuracy and efficiency on eight multivariate time-series forecasting benchmarks.