← Search

Aitian Ma

2 accepted papers

2026

MixLinear: Extreme Low Resource Multivariate Time Series Forecasting with $0.1K$ Parameters

ICLR 2026poster

Recently, there has been a growing interest in Long-term Time Series Forecasting (LTSF), which involves predicting long-term future values by analyzing a large amount of historical time-series data to identify patterns and trends. Significant challenges exist in LTSF due to its complex temporal depe…

Cited by 0SourcecodeScholar
2024

Parametric Augmentation for Time Series Contrastive Learning

ICLR 2024poster

Modern techniques like contrastive learning have been effectively used in many areas, including computer vision, natural language processing, and graph-structured data. Creating positive examples that assist the model in learning robust and discriminative representations is a crucial stage in contra…