Hiroto Yamamoto | Searcharxiv

arXiv2026

DAD4TS: Data-Augmentation-Oriented Diffusion Model for Time-Series Forecasting with Small-Scale Data

Small-scale data is a critical problem in time-series forecasting tasks. Data augmentation is an effective strategy for this task, but it has a limitation in generating meaningful data. To address this limitation, we propose DAD4TS, a diffusion-model-based data augmentation method with reinforcement learning, designed for time-series forecasting with small-scale data. In DAD4TS, a data generator is simultaneously trained with a time-series model and controlled by a reinforcement learning model to efficiently generate samples that improve the forecast accuracy of the time-series model. To support small-scale data, we use mathematical methods instead of conventional VAE methods to train the diffusion model by projecting the time-series data into the geometric space. We validated the effectiveness of DAD4TS with seven comparative methods through qualitative and quantitative experiments on six real-world datasets and eight time-series models. As a result, DAD4TS was validated on five datasets.

cs.LG↗

arXiv2026

Finite-temperature quantum Krylov method from real-time overlaps

Accurately evaluating finite-temperature properties of quantum many-body systems remains a central challenge. Many existing quantum approaches typically require thermal-state preparation at each target temperature, making low-temperature calculations especially demanding in terms of circuit depth and accuracy. Here we introduce a distinct framework based only on the real-time overlap sequence $g_n=\langle ϕ|e^{-inτH}|ϕ\rangle$, which enables thermodynamic quantities to be obtained over a broad temperature range, without specifying a target temperature on the quantum device. For the one-dimensional spin-$\frac{1}{2}$ Heisenberg model with periodic boundary conditions, we obtain accurate specific heat, magnetic susceptibility, and entropy in the noiseless case. Magnetic susceptibility is also evaluated accurately without explicit symmetry-sector decomposition by employing pseudorandom vectors compatible with $S_{\mathrm{tot}}^{z}$ conservation. With suitable stabilization, the method further retains the main thermodynamic features under finite-shot statistical errors up to $σ\sim10^{-3}$. Our results establish real-time-overlap-based finite-temperature evaluation as a promising framework for finite-temperature computation on near-future quantum hardware.

quant-ph↗