3 papers
cs.LG2025
Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning
Wu Fei, Shuxian Liang, Yibo Yang +5
Process Reinforcement Learning~(PRL) has demonstrated considerable potential in enhancing the reasoning capabilities of Large Language Models~(LLMs). However, introducing additiona…
cs.LG2023
AMLNet: Adversarial Mutual Learning Neural Network for Non-AutoRegressive Multi-Horizon Time Series Forecasting
Yang Lin
Multi-horizon time series forecasting, crucial across diverse domains, demands high accuracy and speed. While AutoRegressive (AR) models excel in short-term predictions, they suffe…
cs.LG2023
Progressive Neural Network for Multi-Horizon Time Series Forecasting
Yang Lin
In this paper, we introduce ProNet, an novel deep learning approach designed for multi-horizon time series forecasting, adaptively blending autoregressive (AR) and non-autoregressi…