Ioannis Mavrothalassitis

collaborators

2 papers

cs.LG2025

Ascent Fails to Forget

Ioannis Mavrothalassitis, Pol Puigdemont, Noam Itzhak Levi +1

Contrary to common belief, we show that gradient ascent-based unconstrained optimization methods frequently fail to perform machine unlearning, a phenomenon we attribute to the inh…

math.OC2024

Efficient Continual Finite-Sum Minimization

Ioannis Mavrothalassitis, Stratis Skoulakis, Leello Tadesse Dadi +1

Given a sequence of functions $f_{1}, \dots, f_{n}$ with $f_{i} : D \mapsto R$ , finite-sum minimization seeks a point $x^{⋆} \in D$ minimizing $\sum_{j=1}^n…