Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Rodemann, Julian"'
Autor:
Arias, Esteban Garces, Blocher, Hannah, Rodemann, Julian, Li, Meimingwei, Heumann, Christian, Aßenmacher, Matthias
Open-ended text generation has become a prominent task in natural language processing due to the rise of powerful (large) language models. However, evaluating the quality of these models and the employed decoding strategies remains challenging becaus
Externí odkaz:
http://arxiv.org/abs/2410.18653
We demonstrate that a wide array of machine learning algorithms are specific instances of one single paradigm: reciprocal learning. These instances range from active learning over multi-armed bandits to self-training. We show that all these algorithm
Externí odkaz:
http://arxiv.org/abs/2408.06257
Autor:
Bongratz, Fabian, Golkov, Vladimir, Mautner, Lukas, Della Libera, Luca, Heetmeyer, Frederik, Czaja, Felix, Rodemann, Julian, Cremers, Daniel
The field of reinforcement learning offers a large variety of concepts and methods to tackle sequential decision-making problems. This variety has become so large that choosing an algorithm for a task at hand can be challenging. In this work, we stre
Externí odkaz:
http://arxiv.org/abs/2407.20917
Autor:
Arias, Esteban Garces, Rodemann, Julian, Li, Meimingwei, Heumann, Christian, Aßenmacher, Matthias
Decoding from the output distributions of large language models to produce high-quality text is a complex challenge in language modeling. Various approaches, such as beam search, sampling with temperature, $k-$sampling, nucleus $p-$sampling, typical
Externí odkaz:
http://arxiv.org/abs/2407.18698
Autor:
Rodemann, Julian
A wide range of machine learning algorithms iteratively add data to the training sample. Examples include semi-supervised learning, active learning, multi-armed bandits, and Bayesian optimization. We embed this kind of data addition into decision the
Externí odkaz:
http://arxiv.org/abs/2406.12560
Given the vast number of classifiers that have been (and continue to be) proposed, reliable methods for comparing them are becoming increasingly important. The desire for reliability is broken down into three main aspects: (1) Comparisons should allo
Externí odkaz:
http://arxiv.org/abs/2406.03924
We provide a theoretical and computational investigation of the Gamma-Maximin method with soft revision, which was recently proposed as a robust criterion for pseudo-label selection (PLS) in semi-supervised learning. Opposed to traditional methods fo
Externí odkaz:
http://arxiv.org/abs/2405.15294
Autor:
Rodemann, Julian, Croppi, Federico, Arens, Philipp, Sale, Yusuf, Herbinger, Julia, Bischl, Bernd, Hüllermeier, Eyke, Augustin, Thomas, Walsh, Conor J., Casalicchio, Giuseppe
Bayesian optimization (BO) with Gaussian processes (GP) has become an indispensable algorithm for black box optimization problems. Not without a dash of irony, BO is often considered a black box itself, lacking ways to provide reasons as to why certa
Externí odkaz:
http://arxiv.org/abs/2403.04629
Autor:
Rodemann, Julian, Blocher, Hannah
We introduce a framework for benchmarking optimizers according to multiple criteria over various test functions. Based on a recently introduced union-free generic depth function for partial orders/rankings, it fully exploits the ordinal information a
Externí odkaz:
http://arxiv.org/abs/2402.16565
Autor:
Rodemann, Julian
Pseudo-Labeling is a simple and effective approach to semi-supervised learning. It requires criteria that guide the selection of pseudo-labeled data. The latter have been shown to crucially affect pseudo-labeling's generalization performance. Several
Externí odkaz:
http://arxiv.org/abs/2309.13926