Researcher profile

Sebastian Pokutta

2 papers in the PaperMetrix corpus

Publications

Papers by this author

  1. 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 …

  2. 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 …