activity
20132023
most citedA Time Series is Worth 64 Words: Long-term Forecasting with Transformers

559 citations · 859 across the 8 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2023★ 274 cited

TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting

Vijay Ekambaram, Arindam Jati, Nam Nguyen +2

Transformers have gained popularity in time series forecasting for their ability to capture long-sequence interactions. However, their high memory and computing requirements pose a…

cs.LG2023

An End-to-End Time Series Model for Simultaneous Imputation and Forecast

Trang H. Tran, Lam M. Nguyen, Kyongmin Yeo +4

Time series forecasting using historical data has been an interesting and challenging topic, especially when the data is corrupted by missing values. In many industrial problem, it…

cs.LG2022★ 559 cited

A Time Series is Worth 64 Words: Long-term Forecasting with Transformers

Yuqi Nie, Nam H. Nguyen, Phanwadee Sinthong +1

We propose an efficient design of Transformer-based models for multivariate time series forecasting and self-supervised representation learning. It is based on two key components:…

cs.LG2021

Interpretable Clustering via Multi-Polytope Machines

Connor Lawless, Jayant Kalagnanam, Lam M. Nguyen +2

Clustering is a popular unsupervised learning tool often used to discover groups within a larger population such as customer segments, or patient subtypes. However, despite its use…

cs.LG2021

Deep Policy Iteration with Integer Programming for Inventory Management

Pavithra Harsha, Ashish Jagmohan, Jayant Kalagnanam +2

We present a Reinforcement Learning (RL) based framework for optimizing long-term discounted reward problems with large combinatorial action space and state dependent constraints.…

cs.LG2020★ 17 cited

A Scalable MIP-based Method for Learning Optimal Multivariate Decision Trees

Haoran Zhu, Pavankumar Murali, Dzung T. Phan +2

Several recent publications report advances in training optimal decision trees (ODT) using mixed-integer programs (MIP), due to algorithmic advances in integer programming and a gr…