|国家预印本平台
首页|Alternators With Noise Models

Alternators With Noise Models

Alternators With Noise Models

来源:Arxiv_logoArxiv
英文摘要

Alternators have recently been introduced as a framework for modeling time-dependent data. They often outperform other popular frameworks, such as state-space models and diffusion models, on challenging time-series tasks. This paper introduces a new Alternator model, called Alternator++, which enhances the flexibility of traditional Alternators by explicitly modeling the noise terms used to sample the latent and observed trajectories, drawing on the idea of noise models from the diffusion modeling literature. Alternator++ optimizes the sum of the Alternator loss and a noise-matching loss. The latter forces the noise trajectories generated by the two noise models to approximate the noise trajectories that produce the observed and latent trajectories. We demonstrate the effectiveness of Alternator++ in tasks such as density estimation, time series imputation, and forecasting, showing that it outperforms several strong baselines, including Mambas, ScoreGrad, and Dyffusion.

Mohammad R. Rezaei、Adji Bousso Dieng

自动化基础理论计算技术、计算机技术

Mohammad R. Rezaei,Adji Bousso Dieng.Alternators With Noise Models[EB/OL].(2025-05-18)[2025-06-22].https://arxiv.org/abs/2505.12544.点此复制

评论