783 citations
- EdgeWave (Germany)DE23 papers
- Freie Universität BerlinDE16 papers
- Technische Universität BerlinDE14 papers
- Deutsches Elektronen-Synchrotron DESYDE11 papers
- University of EdinburghGB11 papers
- University of LiverpoolGB11 papers
- University of RegensburgDE11 papers
- Centre National de la Recherche ScientifiqueFR8 papers
- John von Neumann Institute for ComputingDE8 papers
- Helmholtz-Zentrum Berlin für Materialien und EnergieDE6 papers
- Technical University of MunichDE6 papers
- Physikalisch-Technische BundesanstaltDE5 papers
5 papers · 1 filter
Don't Be Greedy, Just Relax! Pruning LLMs via Frank-Wolfe
Christophe Roux, Max Zimmer, Alexandre d'Aspremont +1
Pruning is a common technique to reduce the compute and storage requirements of Neural Networks. While conventional approaches typically retrain the model to recover pruning-induce…
Learning to Schedule Heuristics in Branch-and-Bound
Antonia Chmiela, Elias B. Khalil, Ambros Gleixner +2
Primal heuristics play a crucial role in exact solvers for Mixed Integer Programming (MIP). While solvers are guaranteed to find optimal solutions given sufficient time, real-world…
Linear Bandits on Uniformly Convex Sets
Thomas Kerdreux, Christophe Roux, Alexandre d'Aspremont +1
Linear bandit algorithms yield pseudo-regret bounds on compact convex action sets and two types of structural assu…
Adversaries in Online Learning Revisited: with applications in Robust Optimization and Adversarial training
Sebastian Pokutta, Huan Xu
We revisit the concept of "adversary" in online learning, motivated by solving robust optimization and adversarial training using online learning methods. While one of the classica…
IPBoost -- Non-Convex Boosting via Integer Programming
Marc E. Pfetsch, Sebastian Pokutta
Recently non-convex optimization approaches for solving machine learning problems have gained significant attention. In this paper we explore non-convex boosting in classification…