4 citations · 8 across the 26 of their papers we have counts for
26 papers
Off-Policy Evaluation with Strategic Agents via Local Disclosure
Kiet Q. H. Vo, Abbavaram Gowtham Reddy, Julian Rodemann +2
We study off-policy evaluation (OPE) under strategic behavior where decision subjects (or agents) respond to a decision maker's policy by strategically modifying their covariates.…
Self-Supervised Laplace Approximation for Bayesian Uncertainty Quantification
Julian Rodemann, Alexander Marquard, Thomas Augustin +1
Approximate Bayesian inference typically revolves around computing the posterior parameter distribution. In practice, however, the main object of interest is often a model's predic…
Self-Reinforcing Controllable Synthesis of Rare Relational Data via Bayesian Calibration
Chongsheng Zhang, Hao Wang, Zelong Yu +7
Imbalanced data are commonly present in real-world applications. While data synthesis can effectively mitigate data scarcity for rare classes, and LLMs have revolutionized text gen…
Quantification of Credal Uncertainty: A Distance-Based Approach
Xabier Gonzalez-Garcia, Siu Lun Chau, Julian Rodemann +6
Credal sets, i.e., closed convex sets of probability measures, provide a natural framework to represent aleatoric and epistemic uncertainty in machine learning. Yet how to quantify…
Incentive Aware AI Regulations: A Credal Characterisation
Anurag Singh, Julian Rodemann, Rajeev Verma +2
The rapid proliferation of AI applications has intensified debate on effective regulation of these black-box services. Effective regulation must balance two competing goals: (1) de…
Beyond Arrow: From Impossibility to Possibilities in Multi-Criteria Benchmarking
Polina Gordienko, Christoph Jansen, Julian Rodemann +1
Modern benchmarks such as HELM MMLU account for multiple metrics like accuracy, robustness and efficiency. When trying to turn these metrics into a single ranking, natural aggregat…
Performative Learning Theory
Julian Rodemann, Unai Fischer-Abaigar, James Bailie +1
Performative predictions influence the very outcomes they aim to forecast. We study performative predictions that affect a sample (e.g., only existing users of an app) and/or the w…
The Geometry of Creative Variability: How Credal Sets Expose Calibration Gaps in Language Models
Esteban Garces Arias, Julian Rodemann, Christian Heumann
Understanding uncertainty in large language models remains a fundamental challenge, particularly in creative tasks where multiple valid outputs exist. We present a geometric framew…
GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generation
Yuanhao Ding, Esteban Garces Arias, Meimingwei Li +6
Open-ended text generation faces a critical challenge: balancing coherence with diversity in LLM outputs. While contrastive search-based decoding strategies have emerged to address…
Statistical Multicriteria Evaluation of LLM-Generated Text
Esteban Garces Arias, Hannah Blocher, Julian Rodemann +2
Assessing the quality of LLM-generated text remains a fundamental challenge in natural language processing. Current evaluation approaches often rely on isolated metrics or simplist…
Generalization Bounds and Stopping Rules for Learning with Self-Selected Data
Julian Rodemann, James Bailie
Many learning paradigms self-select training data in light of previously learned parameters. Examples include active learning, semi-supervised learning, bandits, or boosting. Rodem…
A Statistical Case Against Empirical Human-AI Alignment
Julian Rodemann, Esteban Garces Arias, Christoph Luther +2
Empirical human-AI alignment aims to make AI systems act in line with observed human behavior. While noble in its goals, we argue that empirical alignment can inadvertently introdu…
Towards Better Open-Ended Text Generation: A Multicriteria Evaluation Framework
Esteban Garces Arias, Hannah Blocher, Julian Rodemann +3
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…
Reciprocal Learning
Julian Rodemann, Christoph Jansen, Georg Schollmeyer
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…
How to Choose a Reinforcement-Learning Algorithm
Fabian Bongratz, Vladimir Golkov, Lukas Mautner +5
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…
Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Generation
Esteban Garces Arias, Julian Rodemann, Meimingwei Li +2
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, s…
Towards Bayesian Data Selection
Julian Rodemann
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 Bayesi…
Statistical Multicriteria Benchmarking via the GSD-Front
Christoph Jansen, Georg Schollmeyer, Julian Rodemann +2
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 reliabili…
Semi-Supervised Learning guided by the Generalized Bayes Rule under Soft Revision
Stefan Dietrich, Julian Rodemann, Christoph Jansen
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 selectio…
Explaining Bayesian Optimization by Shapley Values Facilitates Human-AI Collaboration
Julian Rodemann, Federico Croppi, Philipp Arens +7
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 consider…
Partial Rankings of Optimizers
Julian Rodemann, Hannah Blocher
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 fo…
Pseudo Label Selection is a Decision Problem
Julian Rodemann
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…
Robust Statistical Comparison of Random Variables with Locally Varying Scale of Measurement
Christoph Jansen, Georg Schollmeyer, Hannah Blocher +2
Spaces with locally varying scale of measurement, like multidimensional structures with differently scaled dimensions, are pretty common in statistics and machine learning. Neverth…
In all LikelihoodS: How to Reliably Select Pseudo-Labeled Data for Self-Training in Semi-Supervised Learning
Julian Rodemann, Christoph Jansen, Georg Schollmeyer +1
Self-training is a simple yet effective method within semi-supervised learning. The idea is to iteratively enhance training data by adding pseudo-labeled data. Its generalization p…