Researcher profile
Sebastian Pokutta
2 papers in the PaperMetrix corpus
Publications
Papers by this author
-
Acceleration of Frank-Wolfe Algorithms with Open-Loop Step-Sizes
2022 · arXiv (Cornell University)
Frank-Wolfe algorithms (FW) are popular first-order methods for solving constrained convex optimization problems that rely on a linear minimization oracle instead of potentially expensive projection-like oracles. Many works have identified accelerated convergence rates under various …
-
Training on Plausible Counterfactuals Removes Spurious Correlations
2025 · arXiv (Cornell University)
Plausible counterfactual explanations (p-CFEs) are perturbations that minimally modify inputs to change classifier decisions while remaining plausible under the data distribution. In this study, we demonstrate that classifiers can be trained on p-CFEs labeled with …