Moritz Venzin — accepted AI-conference papers

2026

Learning-Augmented Online Covering Problems

Afrouz Ameli, Laura Sanità, Moritz Venzin

ICML 2026poster

We give a very general and simple framework to incorporate predictions on requests for online covering problems in a rigorous and black-box manner. Our framework turns any online algorithm with competitive ratio $\rho(k, \cdot)$ depending on $k$, the number of arriving requests, into an algorithm wi…

Cited by 0 Source ↗Scholar ↗

2025

Approximation algorithms for combinatorial optimization with predictions

Antonios Antoniadis, Marek Elias, Adam Polak, Moritz Venzin

ICLR 2025spotlight

We initiate a systematic study of utilizing predictions to improve over approximation guarantees of classic algorithms, without increasing the running time. We propose a generic method for a wide class of optimization problems that ask to select a feasible subset of input items of minimal (or maxima…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗