IEEE

Latent Cluster Discovery in a Collection of Low Count Non-Gaussian Time Series in Economics Domain

Abstract: The main focus of this work is to discover naturally occurring clusters in behavioral time series, and then associate a numerical representation with every cluster, which could be used to ...
IEEE

Dynamic Clustering for Federated Learning: A Reinforcement Learning Approach to Minimize Time Divergence

Abstract: Federated learning (FL) offers a decentralized approach to training machine learning models, allowing data to remain on local devices and preserving privacy. However, the decentralized ...
GitHub

Is Mamba Effective for Time Series Forecasting?

We propose S-Mamba, a Mamba-based model for time series forecasting, which delegates the extraction of inter-variate correlations and temporal dependencies to a bidirectional Mamba block and a ...
GitHub

Time Series Foundation Model - TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting

The official code for ["TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting (ICLR 2024)"]. TEMPO is one of the very first open source Time Series Foundation Models for ...