Zobrazeno 1 - 10
of 5 117
pro vyhledávání: '"A. Lindauer"'
Autor:
Becktepe, Jannis, Dierkes, Julian, Benjamins, Carolin, Mohan, Aditya, Salinas, David, Rajan, Raghu, Hutter, Frank, Hoos, Holger, Lindauer, Marius, Eimer, Theresa
Publikováno v:
17th European Workshop on Reinforcement Learning 2024
Hyperparameters are a critical factor in reliably training well-performing reinforcement learning (RL) agents. Unfortunately, developing and evaluating automated approaches for tuning such hyperparameters is both costly and time-consuming. As a resul
Externí odkaz:
http://arxiv.org/abs/2409.18827
Autor:
Benjamins, Carolin, Cenikj, Gjorgjina, Nikolikj, Ana, Mohan, Aditya, Eftimov, Tome, Lindauer, Marius
Publikováno v:
GECCO 2024
Dynamic Algorithm Configuration (DAC) addresses the challenge of dynamically setting hyperparameters of an algorithm for a diverse set of instances rather than focusing solely on individual tasks. Agents trained with Deep Reinforcement Learning (RL)
Externí odkaz:
http://arxiv.org/abs/2407.13513
Optimizing Time Series Forecasting Architectures: A Hierarchical Neural Architecture Search Approach
Autor:
Deng, Difan, Lindauer, Marius
The rapid development of time series forecasting research has brought many deep learning-based modules in this field. However, despite the increasing amount of new forecasting architectures, it is still unclear if we have leveraged the full potential
Externí odkaz:
http://arxiv.org/abs/2406.05088
Autor:
Lindauer, Marius, Karl, Florian, Klier, Anne, Moosbauer, Julia, Tornede, Alexander, Mueller, Andreas, Hutter, Frank, Feurer, Matthias, Bischl, Bernd
Automated machine learning (AutoML) was formed around the fundamental objectives of automatically and efficiently configuring machine learning (ML) workflows, aiding the research of new ML algorithms, and contributing to the democratization of ML by
Externí odkaz:
http://arxiv.org/abs/2406.03348
Hyperparameter optimization plays a pivotal role in enhancing the predictive performance and generalization capabilities of ML models. However, in many applications, we do not only care about predictive performance but also about objectives such as i
Externí odkaz:
http://arxiv.org/abs/2405.07640
Deep Learning (DL) has advanced various fields by extracting complex patterns from large datasets. However, the computational demands of DL models pose environmental and resource challenges. Deep shift neural networks (DSNNs) offer a solution by leve
Externí odkaz:
http://arxiv.org/abs/2404.01965
In today's data-driven landscape, time series forecasting is pivotal in decision-making across various sectors. Yet, the proliferation of more diverse time series data, coupled with the expanding landscape of available forecasting methods, poses sign
Externí odkaz:
http://arxiv.org/abs/2312.08528
Hyperparameter optimization (HPO) is important to leverage the full potential of machine learning (ML). In practice, users are often interested in multi-objective (MO) problems, i.e., optimizing potentially conflicting objectives, like accuracy and e
Externí odkaz:
http://arxiv.org/abs/2309.03581
Autor:
Elisa Pfeiffer, Johanna Unterhitzenberger, Pia Enderby, Aino Juusola, Zlatina Kostova, Ramon J. L. Lindauer, Sanna-Kaija Nuotio, Poa Samuelberg, Tine K. Jensen
Publikováno v:
BMC Health Services Research, Vol 24, Iss 1, Pp 1-12 (2024)
Abstract Background There is broad scientific evidence for the effectiveness of individual trauma-focused evidence-based treatments (EBTs) such as “trauma-focused cognitive behavioural therapy” (TF-CBT) for children and adolescents with posttraum
Externí odkaz:
https://doaj.org/article/1ec54cfa423e4969879d155979a30813
Optimizing a machine learning pipeline for a task at hand requires careful configuration of various hyperparameters, typically supported by an AutoML system that optimizes the hyperparameters for the given training dataset. Yet, depending on the Auto
Externí odkaz:
http://arxiv.org/abs/2306.16913