Tina Kapur — accepted AI-conference papers

2025

Calibrating Expressions of Certainty

Peiqi Wang, Barbara D. Lam, Yingcheng Liu, Ameneh Asgari-Targhi, Rameswar Panda, William M Wells +2

ICLR 2025poster

We present a novel approach to calibrating linguistic expressions of certainty, e.g., "Maybe" and "Likely". Unlike prior work that assigns a single score to each certainty phrase, we model uncertainty as distributions over the simplex to capture their semantics more accurately. To accommodate this n…

Cited by 1 Source ↗PDF ↗Scholar ↗

2020

PEP: Parameter Ensembling by Perturbation

Alireza Mehrtash, Purang Abolmaesumi, Polina Golland, Tina Kapur, Demian Wassermann, William Wells

NeurIPS 2020poster

Ensembling is now recognized as an effective approach for increasing the predictive performance and calibration of deep networks. We introduce a new approach, Parameter Ensembling by Perturbation (PEP), that constructs an ensemble of parameter values as random perturbations of the optimal parameter…

Cited by 10 Source ↗PDF ↗Scholar ↗