The paper introduces a GPU‑accelerated regularized estimation framework for the logarithmic vector multiplicative error model (log‑vMEM) with multivariate Gamma errors, designed to handle high‑dimensional positive‑valued financial time series. It proposes three hierarchical lag structures—componentwise, own‑other, and elementwise—combined with group lasso, group MCP, group SCAD, and adaptive group lasso penalties to induce sparsity and capture heterogeneous lag dynamics. Parameter estimation uses an alternating block‑coordinate algorithm with sequential Gauss‑Seidel updates, while GPU‑accelerated numerical quadrature mitigates the computational load of evaluating the multivariate Gamma likelihood; simulation studies assess parameter recovery and lag selection, and a real‑data application on Microsoft’s realized volatility demonstrates the approach in practice.
By Rohan Hemant Chhatre, Chiranjit Dutta, Nalini Ravishanker, Sumanta Basu
arXiv:2411. 17136v2 Announce Type: replace-cross Abstract: Realised volatility has become increasingly prominent in volatility forecasting due to its ability to capture intraday price fluctuations.
By Qianli Zhao, Chao Wang, Richard Gerlach, Giuseppe Storti, Lingxiang Zhang
arXiv:2606. 03184v1 Announce Type: cross Abstract: Financial forecasting is difficult due to low signal-to-noise ratios, latent factors, heavy tails, regime shifts, and jumps.
By Jiaze Sun, Kelvin J. L. Koa, Ruiyang Ni, Yize Liu, Haonan Chen, Ke-Wei Huang
The paper introduces μs’ autotune, an automatic tuning strategy for the Lasso that optimizes a penalized Gaussian log‑likelihood over regression coefficients and noise standard deviation. Extensive simulations on regression and VAR models show that autotune is faster and yields better generalization and model selection, especially in low signal‑to‑noise regimes. The method also delivers a new noise‑standard‑deviation estimator, a visual diagnostic for sparsity, and is demonstrated on a real‑world financial dataset, with an accompanying R package available on GitHub.
By Tathagata Sadhukhan, Ines Wilms, Stephan Smeekes, Sumanta Basu
arXiv:2608. 06340v1 Announce Type: cross Abstract: Vector autoregressive moving-average (VARMA) models have long been considered impractical beyond moderate dimensions: the likelihood is non-convex, the parametrization is identified only up to equivalence, and every evaluation costs a pass over the entire series.
By Daniel Paulin, Victor Elvira
arXiv:2502. 18834v3 Announce Type: replace-cross Abstract: Financial time series (FinTS) record the behavior of human-brain-augmented decision-making, capturing valuable historical information that can be leveraged for profitable investment strategies.
By Yifan Hu, Yuante Li, Peiyuan Liu, Yuxia Zhu, Naiqi Li, Tao Dai, Shu-tao Xia, Dawei Cheng, Changjun Jiang