24 papers · ranked by Valyu relevance
Moisés Silva-Muñoz, Alberto Franzin, Hugues Bersini, Muhammad Aleem
Database systems play a central role in modern data-centered applications. Their performance is thus a key factor in the efficiency of data processing pipelines. Modern database systems expose several parameters that users and database administrators can configure to tailor the database settings to the specific…
Geethu Joy, Christian Huyck, Xin‐She Yang
Almost all optimization algorithms have algorithm-dependent parameters, and the setting of such parameter values can largely influence the behaviour of the algorithm under consideration. Thus, proper parameter tuning should be carried out to ensure the algorithm used for optimization may perform well and can be…
Xin‐She Yang, Suash Deb, Martin Loomes, Mehmet Karamanoglu
The performance of any algorithm will largely depend on the setting of its algorithmdependent parameters. The optimal setting should allow the algorithm to achieve the best performance for solving a range of optimization problems. However, such parameter-tuning itself is a tough optimization problem. In this paper, we…
Qiwen Hu, Casey S. Greene
Single-cell RNA sequencing (scRNA-seq) is a powerful tool to simultaneously sequencing the transcriptomes of a large number of individual cells at a high resolution. These data usually contain measurements of gene expression for many genes in thousands or tens of thousands of cells, though some datasets now reach the…
Geethu Joy, Christian Huyck, Xin‐She Yang
Almost all optimization algorithms have algorithm-dependent parameters, and the setting of such parameter values can significantly influence the behavior of the algorithm under consideration. Thus, proper parameter tuning should be carried out to ensure that the algorithm used for optimization performs well and is…
Kristofor D. Carlson, Jayram Moorkanikara Nageswaran, Nikil Dutt, Jeffrey L. Krichmar
'Jeffrey L. Krichmar'] As the desire for biologically realistic spiking neural networks (SNNs) increases, tuning the enormous number of open parameters in these models becomes a difficult challenge. SNNs have been used to successfully model complex neural circuits that explore various neural phenomena such as neural…
Katerina Tashkova, Peter Korošec, Jurij Šilc, Ljupčo Todorovski + 1 more
'Sašo Džeroski'] Background We address the task of parameter estimation in models of the dynamics of biological systems based on ordinary differential equations (ODEs) from measured data, where the models are typically non-linear and have many parameters, the measurements are imperfect due to noise, and the studied…
Felix Raimundo, Celine Vallot, Jean Philippe Vert
Many computational methods have been developed recently to analyze single-cell RNA-seq (scRNA-seq) data. Several benchmark studies have compared these methods on their ability for dimensionality reduction, clustering or differential analysis, often relying on default parameters. Yet given the biological diversity of…
George Teodoro, Tahsin M Kurç, Luís F R Taveira, Alba C M A Melo + 4 more
Our parameter study framework is illustrated in [btw749-F1]. An investigator specifies a set of input images, an image analysis workflow, the value ranges of input parameters for the image analysis workflow, and the metric of interest (e.g. Dice) for comparison of analysis results. The image analysis workflow is…
Áthila Rocha Trindade, Felipe Campelo
Tuning parameters is an important step for the application of metaheuristics to problem classes of interest. In this work we present a tuning framework based on the sequential optimization of perturbed regression models. Besides providing algorithm configurations with good expected performance, the proposed methodology…
Effat Jalaeian Zaferani, Mohammad Teshnehlab, Amirreza Khodadadian, Clemens Heitzinger + 4 more
'Clemens Heitzinger' 'Mansour Vali' 'Nima Noii' 'Thomas Wick' 'Jing Tian'] In this work, a method for automatic hyper-parameter tuning of the stacked asymmetric auto-encoder is proposed. In previous work, the deep learning ability to extract personality perception from speech was shown, but hyper-parameter tuning was…
Jie Feng, Mingdong He, Lei Jin, Hui Dou + 1 more
Software systems often expose a large number of configurable parameters to satisfy diverse application requirements and deployment scenarios. Given the intricate dependencies between parameters, manually finding a well-performing configuration is a daunting task even for experienced operators. Most existing automatic…
Peter Domanski, Dirk Pflüger, Jochen Rivoir, Raphaël Latty
—Increasing complexity of modern integrated circuits makes design validation more difficult. Existing approaches are not able anymore to cope with the complexity of tasks such as robust performance tuning in post-silicon validation. Therefore, we propose a novel learn-to-optimize approach based on reinforcement…
Máté Mohácsi, Márk Patrik Török, Sára Sáray, Luca Tar + 1 more
Finding optimal parameters for detailed neuronal models is a ubiquitous challenge in neuroscientific research. Recently, manual model tuning has been replaced by automated parameter search using a variety of different tools and methods. However, using most of these software tools and choosing the most appropriate…
Samuel Sledzieski, Meghana Kshirsagar, Minkyung Baek, Bonnie Berger + 2 more
Proteomics has been revolutionized by large pre-trained protein language models, which learn unsupervised representations from large corpora of sequences. The parameters of these models are then fine-tuned in a supervised setting to tailor the model to a specific downstream task. However, as model size increases, the…
Ian Knight, Khanh Tang, John Irwin
Molecular docking is a widely used technique for leveraging protein structure in ligand discovery, but as a method, it remains difficult to utilize due to limitations that have not been adequately addressed. Despite some progress towards automation, docking still requires expert guidance, hindering its adoption by a…
Owen Madin, Michael Shirts
Dispersion-repulsion interactions, commonly represented in atomistic force fields by the Lennard-Jones (LJ) potential, play an important role in the accuracy of molecular simulations. Training the force field parameters used in the LJ potential is challenging, generally requiring adjustment based on simulations of…
Paul Stapor, Leonard Schmiester, Christoph Wierling, Bodo M.H. Lange + 2 more
Quantitative dynamical models are widely used to study cellular signal processing. A critical step in modeling is the estimation of unknown model parameters from experimental data. As model sizes and datasets are steadily growing, established parameter optimization approaches for mechanistic models become…
Mehmet Cagri Kaymak, Ali Rahnamoun, Kurt A. O'Hearn, Adri C. T. van Duin + 2 more
Molecular dynamics (MD) simulations ease the study of the chemistry of interest. While classical models that governs the interaction of the atoms lack reactivity, the quantum mechanics based methods increase the computational cost drastically. ReaxFF fills the gap between these two ends of the spectrum by allowing bond…
Lucian Chan, Geoffrey Hutchison, Garrett Morris
Generating low-energy molecular conformers is a key task for many areas of computational chemistry, molecular modeling and cheminformatics. Most current conformer generation methods primarily focus on generating geometrically diverse conformers rather than finding the most probable or energetically lowest minima. Here…
Lucian Chan, Geoffrey Hutchison, Garrett Morris
Generating low-energy molecular conformers is a key task for many areas of computational chemistry, molecular modeling and cheminformatics. Most current conformer generation methods primarily focus on generating geometrically diverse conformers rather than finding the most probable or energetically lowest minima. Here…
Olga Bokareva, Patrick Zobel, Ayla Kruse, Omar Baig + 4 more
Density functional theory is an efficient computational tool to investigate photophysical and photochemical processes in transition metal complexes, giving invaluable assistance in the interpretation of spectroscopic and catalytic experiments. Optimally-tuned range-separated functionals are particularly promising, as…
Authors not listed
This paper formally defines an operational isomorphism between spectral damping in molecular vibronic systems and neuromodulatory control in biological sensory systems. Without asserting causal continuity or physical identity across scales, we show that both domains instantiate the same class of output-selective…
Authors not listed
Inverse molecular design aims to generate novel chemical structures that satisfy multiple property constraints, yet reinforcement-learning (RL) fine-tuning can be sensitive to how objectives are converted into a scalar reward. Here, we systematically analyze how scalarization choices and stabilization mechanisms shape…