Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series
- Vijay E
- Arindam Jati
- et al.
- 2024
- NeurIPS 2024
Bio
Hi! I am currently working at IBM Research, Bangalore, India as a Research Scientist. My current research interests include foundational modeling, deep learning, explainable AI, and timeseries forecasting.
I did my PhD in Electrical Engineering from University of Southern California (USC) under the supervision of Prof. Shrikanth Narayanan (have a look at Signal Analysis and Interpretation Laboratory (SAIL)). I completed my undergraduate degree in Electronics and Telecommunication Engineering in Jadavpur University, Kolkata, India.
Publications
Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series
- Vijay E
- Arindam Jati
- et al.
- 2024
- arXiv
AutoMixer for Improved Multivariate Time-Series Forecasting on Business and IT Observability Data
- Santosh Palaskar
- Vijay E
- et al.
- 2024
- IAAI 2024
Physics-based multiple time-series univariate forecasting
- Sumanta Mukherjee
- Arindam Jati
- et al.
- 2022
- Big Data 2022
Automating Complex and Distributed Forecasting Tasks for Faster Supply Chain Decisions
- Vijay E
- Arindam Jati
- et al.
- 2022
- INFORMS 2022
Hyperparameter Optimization over Data Hierarchy for Model Selection in Time Series Forecasting
- Arindam Jati
- Vijay E
- et al.
- 2022
- INFORMS 2022
Top collaborators
VE
Vijay E
Granite TSFM Research Lead, Master Inventor
PD
Pankaj Dayama
Senior Technical Staff Member & Manager, AI for Industry 4.0, Master Inventor
CN
Chandra Narayanaswami
Distinguished Research Scientist, Manager - Observability, Insights, & Actions for ITOps
AS
Avirup Saha
Research Scientist