Arshia Abolghasemi, Seyed Reza Tavakoli, Parsa Naderi, Nazanin Mirzaei, Behrad Jahani, Saba Yousefzadeh, Tahereh Javaheri, Mohammad Hosein Rohban · 2026 · arXiv
DOI: 10.48550/arXiv.2610.21081 · open-access PDF
Metode difusi berbasis skor biasanya mengganggu data dengan kebisingan Brownian Gaussian, yang sesuai dengan persamaan diferensial stochastic forward-tailed (SDE). Untuk seri waktu pasar, SDE ini bisa menjadi abstraksi yang buruk: buku perintah batas (LOB) aliran pesanan berat, meledak, dan kadang-kadang melompat-like. Kami mempelajari STOCHLOB, kerangka kerja yang cocok dengan skor hanya pelatihan yang mengubah hukum korupsi difusi forward sementara meninggalkan determinist prediktor yang didistribusikan. Alih-alih korupsi Brownian-only Gaussian, tidak ada pemrosesan menggunakan dua alternatif non-Gaussian SDE-inspirasi: kebisingan jump-Lévy
Machine translation (Meta M2M100); the English original follows.
Score-based diffusion methods usually perturb data with Brownian Gaussian noise, corresponding to a light-tailed forward stochastic differential equation (SDE). For market time series this SDE can be a poor abstraction: limit order book (LOB) order flow is heavy-tailed, bursty, and occasionally jump-like. We study STOCHLOB, a training-only score-matching framework that changes the forward diffusion corruption law while leaving the deployed predictor deterministic. Instead of Brownian-only Gaussian corruption, the noising process uses two non-Gaussian SDE-inspired alternatives: jump-Lévy noise
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.21081, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange