11 citations · 16 across the 8 of their papers we have counts for
6 papers · 1 filter
TSPulse: Tiny Pre-Trained Models with Disentangled Representations for Rapid Time-Series Analysis
Vijay Ekambaram, Subodh Kumar, Arindam Jati +5
Time-series tasks often benefit from signals expressed across multiple representation spaces (e.g., time vs. frequency) and at varying abstraction levels (e.g., local patterns vs.…
Towards Unbiased Evaluation of Time-series Anomaly Detector
Debarpan Bhattacharya, Sumanta Mukherjee, Chandramouli Kamanchi +3
Time series anomaly detection (TSAD) is an evolving area of research motivated by its critical applications, such as detecting seismic activity, sensor failures in industrial plant…
Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series
Vijay Ekambaram, Arindam Jati, Pankaj Dayama +5
Large pre-trained models excel in zero/few-shot learning for language and vision tasks but face challenges in multivariate time series (TS) forecasting due to diverse data characte…
Semi-supervised counterfactual explanations
Shravan Kumar Sajja, Sumanta Mukherjee, Satyam Dwivedi
Counterfactual explanations for machine learning models are used to find minimal interventions to the feature values such that the model changes the prediction to a different outpu…
TsSHAP: Robust model agnostic feature-based explainability for time series forecasting
Vikas C. Raykar, Arindam Jati, Sumanta Mukherjee +4
A trustworthy machine learning model should be accurate as well as explainable. Understanding why a model makes a certain decision defines the notion of explainability. While vario…
Hierarchical Proxy Modeling for Improved HPO in Time Series Forecasting
Arindam Jati, Vijay Ekambaram, Shaonli Pal +6
Selecting the right set of hyperparameters is crucial in time series forecasting. The classical temporal cross-validation framework for hyperparameter optimization (HPO) often lead…