Maximilian Zorn

Maximilian Zorn

Auto-generated profile, based on publicly available information

Maximilian Zorn

Mobile and Distributed Systems Group LMU Munich Germany

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 July 2023
Verified
Conference Paper
Open access
JSJonas Korbinian Stein
Jonas Korbinian Stein
FCFarbod Chamanian
Farbod Chamanian
MZMaximilian Zorn
Maximilian Zorn
JNJonas Nüßlein
Jonas Nüßlein
SZSebastian Zielinski
Sebastian Zielinski
CLClaudia Linnhoff-Popien
Claudia Linnhoff-Popien
Quantum computing provides powerful algorithmic tools that have been shown to outperform established classical solvers in specific optimization tasks. A core step in solving optimization problems with known quantum algorithms such as the Quantum Approximate Optimization Algorithm (QAOA) is the problem formulation. While quantum optimization has historically centered around Quadratic Unconstrained Optimization (QUBO) problems, recent studies show, that many combinatorial problems such as the TSP can be solved more efficiently in their native Polynomial Unconstrained Optimization (PUBO) forms. As many optimization problems in practice also contain continuous variables, our contribution investigates the performance of the QAOA in solving continuous optimization problems when using PUBO and QUBO formulations. Our extensive evaluation on suitable benchmark functions, shows that PUBO formulations generally yield better results, while requiring less qubits. As the multi-qubit interactions needed for the PUBO variant have to be decomposed using the hardware gates available, i.e., currently single- and two-qubit gates, the circuit depth of the PUBO approach outscales its QUBO alternative roughly linearly in the order of the objective function. However, incorporating the planned addition of native multi-qubit gates such as the global Mølmer-Sørenson gate, our experiments indicate that PUBO outperforms QUBO for higher order continuous optimization problems in general.

13 July 2025
Verified
Conference Paper
Open access
MKMichael Kölle
Michael Kölle
TBTom Bintener
Tom Bintener
MZMaximilian Zorn
Maximilian Zorn
GSGerhard Stenzel
Gerhard Stenzel
LSLeo Sünkel
Leo Sünkel
CLClaudia Linnhoff-Popien
Claudia Linnhoff-Popien

16 September 2025 in Proceedings of the International Conference on Automated Planning and Scheduling
Verified
Journal Article
Open access
PDF file
MZMaximilian Zorn
Maximilian Zorn
JSJonas Korbinian Stein
Jonas Korbinian Stein
MMMaximilian Balthasar Mansky
Maximilian Balthasar Mansky
PAPhilipp Altmann
Philipp Altmann
MKMichael Kölle
Michael Kölle
CLClaudia Linnhoff-Popien
Claudia Linnhoff-Popien
Optimizing the architecture of variational quantum circuits (VQCs) is crucial for advancing quantum computing (QC) towards practical applications. Current methods range from static ansatz design and evolutionary methods to machine learned VQC optimization, but are either slow, sample inefficient or require infeasible circuit depth to realize advantages. Quality diversity (QD) search methods combine diversity-driven optimization with user-specified features that offer insight into the optimization quality of circuit solution candidates. However, the choice of quality measures and the representational modeling of the circuits to allow for optimization with the current state-of-the-art QD methods like covariance matrix adaptation (CMA), is currently still an open problem. In this work we introduce a directly matrix-based circuit engineering, that can be readily optimized with QD-CMA methods and evaluate heuristic circuit quality properties like expressivity and gate-diversity as quality measures. We empirically show superior circuit optimization of our QD optimization w.r.t. speed and solution score against a set of robust benchmark algorithms from the literature on a selection of NP-hard combinatorial optimization problems.

14 July 2025
Verified
Conference Paper
Open access
GSGerhard Stenzel
Gerhard Stenzel
SGSarah Gerner
Sarah Gerner
MKMichael Kölle
Michael Kölle
MZMaximilian Zorn
Maximilian Zorn
TGThomas Gabor
Thomas Gabor

11 December 2023 in Research Square
Verified
Preprint
Open access
PDF file
PAPhilipp Altmann
Philipp Altmann
FRFabian Ritz
Fabian Ritz
MZMaximilian Zorn
Maximilian Zorn
MKMichael Kölle
Michael Kölle
TPThomy Phan
Thomy Phan
CLClaudia Linnhoff-Popien
Claudia Linnhoff-Popien
We propose discriminative reward co-training (DIRECT) as an extension to deep reinforcement learning algorithms. Building upon the concept of self-imitation learning (SIL), we introduce an imitation buffer to store beneficial trajectories generated by the policy, determined by their return. A discriminator network is trained concurrently to the policy to distinguish between trajectories generated by the current policy and beneficial trajectories generated by previous policies. The discriminator’s verdict is used to construct a reward signal for optimizing the policy. By interpolating prior experience, DIRECT is able to act as a reward surrogate, steering policy optimization towards more valuable regions of the reward landscape, thus, towards learning an optimal policy. In this article we formally introduce the additional components, their intended purpose and parameterization, and define a unified training procedure. To reveal insights into the mechanics of the proposed architecture, we provide evaluations of the introduced hyperparameters. Further benchmark evaluations in various discrete and continuous control environments provide evidence that DIRECT is especially beneficial in environments possessing sparse rewards, hard exploration tasks, and shifting circumstances. Our results show that DIRECT outperforms state-of-the-art algorithms in those challenging scenarios by providing a surrogate reward to the policy and directing the optimization towards valuable areas.

14 July 2024
Verified
Conference Paper
Open access
MZMaximilian Zorn
Maximilian Zorn
SGSarah Gerner
Sarah Gerner
PAPhilipp Altmann
Philipp Altmann
TGThomas Gabor
Thomas Gabor
Final productive fitness is an a posteriori fitness estimate for evolutionary algorithms that takes into account the fitness of an individual's descendants. We use that metric in the context of surrogate-based evolutionary algorithms to show that computing a surrogate not for the original objective function but for the final productive fitness based on said objective function improves optimization properties of the surrogate function and might thus be a useful tool for certain dynamic optimization problems.