Marco Eckhoff

Last Name

Eckhoff

First Name

Marco

ORCID

0000-0002-5581-789X

Show all metadata

Search Results

Publications 1 - 6 of 6

NEAR: A Training-Free Pre-Estimator of Machine Learning Model Performance
Husistein, Raphael T.; Reiher, Markus; Eckhoff, Marco (2025)
The Thirteenth International Conference on Learning Representations
Artificial neural networks have been shown to be state-of-the-art machine learning models in a wide variety of applications, including natural language processing and image recognition. However, building a performant neural network is a labo rious task and requires substantial computing power. Neural Architecture Search (NAS) addresses this issue by an automatic selection of the optimal network from a set of potential candidates. While many NAS methods still require training of (some) neural networks, zero-cost proxies promise to identify the optimal network without training. In this work, we propose the zero-cost proxy Network Expres sivity by Activation Rank (NEAR). It is based on the effective rank of the pre and post-activation matrix, i.e., the values of a neural network layer before and after applying its activation function. We demonstrate the cutting-edge correla tion between this network score and the model accuracy on NAS-Bench-101 and NATS-Bench-SSS/TSS. In addition, we present a simple approach to estimate the optimal layer sizes in multi-layer perceptrons. Furthermore, we show that this score can be utilized to select hyperparameters such as the activation function and the neural network weight initialization scheme.
SCINE-Software for chemical interaction networks
Weymuth, Thomas; Unsleber, Jan Patrick; Türtscher, Paul; et al. (2024)
The Journal of Chemical Physics
The software for chemical interaction networks (SCINE) project aims at pushing the frontier of quantum chemical calculations on molecular structures to a new level. While calculations on individual structures as well as on simple relations between them have become routine in chemistry, new developments have pushed the frontier in the field to high-throughput calculations. Chemical relations may be created by a search for specific molecular properties in a molecular design attempt, or they can be defined by a set of elementary reaction steps that form a chemical reaction network. The software modules of SCINE have been designed to facilitate such studies. The features of the modules are (i) general applicability of the applied methodologies ranging from electronic structure (no restriction to specific elements of the periodic table) to microkinetic modeling (with little restrictions on molecularity), full modularity so that SCINE modules can also be applied as stand-alone programs or be exchanged for external software packages that fulfill a similar purpose (to increase options for computational campaigns and to provide alternatives in case of tasks that are hard or impossible to accomplish with certain programs), (ii) high stability and autonomous operations so that control and steering by an operator are as easy as possible, and (iii) easy embedding into complex heterogeneous environments for molecular structures taken individually or in the context of a reaction network. A graphical user interface unites all modules and ensures interoperability. All components of the software have been made available as open source and free of charge.
Machine Learning-Enhanced Calculation of Quantum-Classical Binding Free Energies
Bensberg, Moritz; Eckhoff, Marco; Thomasen, F. Emil; et al. (2025)
Journal of Chemical Theory and Computation
Binding free energies are key elements in understanding and predicting the strength of protein–drug interactions. While classical free energy simulations yield good results for many purely organic ligands, drugs, including transition metal atoms, often require quantum chemical methods for an accurate description. We propose a general and automated workflow that samples the potential energy surface with hybrid quantum mechanics/molecular mechanics (QM/MM) calculations and trains a machine learning (ML) potential on the QM/MM energies and forces to enable efficient alchemical free energy simulations. To represent systems including many different chemical elements efficiently and to account for the different descriptions of QM and MM atoms, we propose an extension of element-embracing atom-centered symmetry functions for QM/MM data as an ML descriptor. The ML potential approach takes electrostatic embedding and long-range electrostatics into account. We demonstrate the applicability of the workflow on the well-studied protein–ligand complex of myeloid cell leukemia 1 and the inhibitor 19G and on the anticancer drug NKP1339 acting on the glucose-regulated protein 78.
Lifelong Machine Learning Potentials for Chemical Reaction Network Explorations
Eckhoff, Marco; Reiher, Markus (2025)
Journal of Chemical Theory and Computation
Recent developments in computational chemistry facilitate the automated quantum chemical exploration of chemical reaction networks for the in-silico prediction of synthesis pathways, yield, and selectivity. However, the underlying quantum chemical energy calculations require vast computational resources, limiting these explorations severely in practice. Machine learning potentials (MLPs) offer a solution to increase computational efficiency, while retaining the accuracy of reliable first-principles data used for their training. Unfortunately, MLPs will be limited in their generalization ability within chemical (reaction) space, if the underlying training data are not representative for a given application. Within the framework of automated reaction network exploration, where new reactants or reagents composed of any elements from the periodic table can be introduced, this lack of generalizability will be the rule rather than the exception. Here, we therefore evaluate the benefits of the lifelong MLP concept in this context. Lifelong MLPs push their adaptability by efficient continual learning of additional data. We propose an improved learning algorithm for lifelong adaptive data selection yielding efficient integration of new data while previous expertise is preserved. In this way, we can reach chemical accuracy in reaction search trials.
Hierarchical Quantum Embedding by Machine Learning for Large Molecular Assemblies
Bensberg, Moritz; Eckhoff, Marco; Husistein, Raphael T.; et al. (2025)
Journal of Chemical Theory and Computation
We present a quantum-in-quantum embedding strategy coupled to machine learning potentials to improve on the accuracy of quantum-classical hybrid models for the description of large molecules. In such hybrid models, relevant structural regions (such as those around reaction centers or pockets for binding of host molecules) can be described by a quantum model that is then embedded into a classical molecular-mechanics environment. However, this quantum region may become so large that only approximate electronic structure models are applicable. To then restore accuracy in the quantum description, we here introduce the concept of quantum cores within the quantum region that are amenable to accurate electronic structure models due to their limited size. Huzinaga-type projection-based embedding, for example, can deliver accurate electronic energies obtained with advanced electronic structure methods. The resulting total electronic energies are then fed into a transfer learning approach that efficiently exploits the higher-accuracy data to improve on a machine learning potential obtained for the original quantum-classical hybrid approach. We explore the potential of this approach in the context of a well-studied protein–ligand complex for which we calculate the free energy of binding using alchemical free energy and nonequilibrium switching simulations.
CoRe optimizer: an all-in-one solution for machine learning
Eckhoff, Marco; Reiher, Markus (2024)
Machine Learning: Science and Technology
The optimization algorithm and its hyperparameters can significantly affect the training speed and resulting model accuracy in machine learning (ML) applications. The wish list for an ideal optimizer includes fast and smooth convergence to low error, low computational demand, and general applicability. Our recently introduced continual resilient (CoRe) optimizer has shown superior performance compared to other state-of-the-art first-order gradient-based optimizers for training lifelong ML potentials. In this work we provide an extensive performance comparison of the CoRe optimizer and nine other optimization algorithms including the Adam optimizer and resilient backpropagation (RPROP) for diverse ML tasks. We analyze the influence of different hyperparameters and provide generally applicable values. The CoRe optimizer yields best or competitive performance in every investigated application, while only one hyperparameter needs to be changed depending on mini-batch or batch learning.

Publications 1 - 6 of 6

Marco Eckhoff

Last Name

First Name

ORCID

Organisational unit

Filters

Search Results