Hopformer (Homogeneity-Pursuit Transformer), a two-stage framework that addresses multiple time-series with high-dimensional covariates, and proves that SPA achieves a near-optimal bias-variance trade-off via an oracle inequality.
Abstract
Forecasting multiple time-series with high-dimensional covariates presents a core challenge: unifying common temporal patterns while retaining meaningful series-specific information. We introduce Hopformer (Homogeneity-Pursuit Transformer), a two-stage framework that addresses this challenge. In the first stage, we perform a Sparsity Pattern Aggregation (SPA) scheme extracting a common low-variance trend that incorporates the covariates. This acts as a homogenization layer. In the second stage, a LoRA-fine-tuned Transformer models the remaining complex dependencies in the residual. Our method is theoretically grounded. We prove that SPA achieves a near-optimal bias-variance trade-off via an oracle inequality. We also provide generalization bounds for the second stage under dependent time series data. Hopformer sets a new state of the art, improving MASE by an average of 6.56% across synthetic and real-world forecasting benchmarks.
A forecasting framework that explicitly models the coupling between trend and seasonality, and a heteroscedastic Laplace loss function that combines uncertainty weighting with heteroscedastic modeling, reducing the impact of error accumulation over long prediction horizons and enhancing robustness to outliers and heavy...
Zi-Qiong Li, He-Yu Chai, Xinru Liu et al.· IEEE Transactions on Neural...· 0 citations
SETTer is introduced, a transformer-based model that addresses challenges of long-term multivariate time series forecasting by incorporating novel techniques for decoupled self-attention and hybrid masking and outperforms state-of-the-art models in 88% of the scenarios.
Abraham Ezema, C. Eze, F. Ponci et al.· 0 citations
Time-series foundation models are increasingly adapted to new domains through fine-tuning on target data, under the implicit assumption that more target data yields better forecasts. We show that this assumption can fail in financial forecasting, where individual price changes are difficult to predict, but large moves...
Manh Nguyen, M. Nguyen, H. Nguyen et al.· 0 citations
TS-MTM is proposed, a Temporal-Spectral Masked Time-series Modeling framework that formalizes pretraining within a joint representation space and introduces two synergistic mechanisms: Axial-Period Cross Masking to capture temporal dependencies across phases, and Structure-aware Spectral Magnitude Masking to reconstruc...
Pengcheng Zhang, Xiao-Cao Ouyang, Xin Li et al.· Proceedings of the 32nd ACM...· 0 citations
This work proposes FTSformer, a novel financial-initiated multi-scale exogenous-fusion framework for time series forecasting that substantially outperforms existing baselines in terms of forecasting accuracy, training stability, and robustness to exogenous perturbations.
Zong-Xin Dong, Shuang-Shuang Li, Guang-Yuan Pan et al.· International Journal of Mac...· 0 citations
This work proposes AsyTO, an Asymmetric Temporal Operator, an Asymmetric Temporal Operator that factorizes the tensor of per-variable operators into shared but distinct history-reading and future-writing temporal modes with per-variable mode-wise gains, complemented by a low-rank periodic prototype and a cycle-separabl...
Xiachong Lin, Du Yin, Hao Xue et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
