2.5k citations
- IBM Research - Thomas J. Watson Research CenterUS84 papers
- Massachusetts Institute of TechnologyUS48 papers
- IBM Research - AlmadenUS32 papers
- IBM Research - ZurichCH30 papers
- California Institute of TechnologyUS24 papers
- University of Illinois Urbana-ChampaignUS19 papers
- Rensselaer Polytechnic InstituteUS17 papers
- University of Maryland, College ParkUS17 papers
- Vassar CollegeUS17 papers
- Columbia UniversityUS16 papers
- Stanford UniversityUS16 papers
- Centre National de la Recherche ScientifiqueFR14 papers
4 papers · 2 filters
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…
One Arrow, Two Kills: An Unified Framework for Achieving Optimal Regret Guarantees in Sleeping Bandits
Pierre Gaillard, Aadirupa Saha, Soham Dan
We address the problem of \emph{`Internal Regret'} in \emph{Sleeping Bandits} in the fully adversarial setup, as well as draw connections between different existing notions of slee…
Saliency Cards: A Framework to Characterize and Compare Saliency Methods
Angie Boggust, Harini Suresh, Hendrik Strobelt +2
Saliency methods are a common class of machine learning interpretability techniques that calculate how important each input feature is to a model's output. We find that, with the r…
Nonlocal Kernel Network (NKN): a Stable and Resolution-Independent Deep Neural Network
Huaiqian You, Yue Yu, Marta D'Elia +2
Neural operators have recently become popular tools for designing solution maps between function spaces in the form of neural networks. Differently from classical scientific machin…