Search Results for author: Florian Buettner

Found 14 papers, 12 papers with code

Uncertainty Estimates of Predictions via a General Bias-Variance Decomposition

1 code implementation21 Oct 2022 Sebastian G. Gruber, Florian Buettner

In this work we introduce a general bias-variance decomposition for proper scores, giving rise to the Bregman Information as the variance term.

Out-of-Distribution Detection

Encoding Domain Knowledge in Multi-view Latent Variable Models: A Bayesian Approach with Structured Sparsity

1 code implementation13 Apr 2022 Arber Qoku, Florian Buettner

Many real-world systems are described not only by data from a single source but via multiple data views.

Better Uncertainty Calibration via Proper Scores for Classification and Beyond

2 code implementations15 Mar 2022 Sebastian G. Gruber, Florian Buettner

With model trustworthiness being crucial for sensitive real-world applications, practitioners are putting more and more focus on improving the uncertainty calibration of deep neural networks.

Encoding Domain Information with Sparse Priors for Inferring Explainable Latent Variables

1 code implementation8 Jul 2021 Arber Qoku, Florian Buettner

Additionally, in settings where partial knowledge on the latent structure of the data is readily available, a statistically sound integration of prior information into current methods is challenging.

Multi-output Gaussian Processes for Uncertainty-aware Recommender Systems

1 code implementation8 Jun 2021 Yinchong Yang, Florian Buettner

Many common approaches to solve the collaborative filtering task are based on learning representations of users and items, including simple matrix factorization, Gaussian process latent variable models, and neural-network based embeddings.

Collaborative Filtering Gaussian Processes +2

Parameterized Temperature Scaling for Boosting the Expressive Power in Post-Hoc Uncertainty Calibration

1 code implementation24 Feb 2021 Christian Tomani, Daniel Cremers, Florian Buettner

We address the problem of uncertainty calibration and introduce a novel calibration method, Parametrized Temperature Scaling (PTS).

Hierarchical Variational Auto-Encoding for Unsupervised Domain Generalization

no code implementations23 Jan 2021 Xudong Sun, Florian Buettner

We address the task of domain generalization, where the goal is to train a predictive model such that it is able to generalize to a new, previously unseen domain.

Domain Generalization Model Selection

Towards Trustworthy Predictions from Deep Neural Networks with Fast Adversarial Calibration

1 code implementation20 Dec 2020 Christian Tomani, Florian Buettner

That is, it is crucial for predictive models to be uncertainty-aware and yield well-calibrated (and thus trustworthy) predictions for both in-domain samples as well as under domain shift.

Decision Making

Post-hoc Uncertainty Calibration for Domain Drift Scenarios

1 code implementation CVPR 2021 Christian Tomani, Sebastian Gruber, Muhammed Ebrar Erdem, Daniel Cremers, Florian Buettner

First, we show that existing post-hoc calibration methods yield highly over-confident predictions under domain shift.

AAAI FSS-19: Human-Centered AI: Trustworthiness of AI Models and Data Proceedings

no code implementations15 Jan 2020 Florian Buettner, John Piorkowski, Ian McCulloh, Ulli Waltinger

To facilitate the widespread acceptance of AI systems guiding decision-making in real-world applications, it is key that solutions comprise trustworthy, integrated human-AI systems.

Autonomous Driving Decision Making +1

textTOvec: Deep Contextualized Neural Autoregressive Topic Models of Language with Distributed Compositional Prior

1 code implementation ICLR 2019 Pankaj Gupta, Yatin Chaudhary, Florian Buettner, Hinrich Schütze

We address two challenges of probabilistic topic modelling in order to better estimate the probability of a word in a given context, i. e., P(word|context): (1) No Language Structure in Context: Probabilistic topic models ignore word order by summarizing a given context as a "bag-of-word" and consequently the semantics of words in the context is lost.

Information Extraction Information Retrieval +4

Document Informed Neural Autoregressive Topic Models with Distributional Prior

1 code implementation15 Sep 2018 Pankaj Gupta, Yatin Chaudhary, Florian Buettner, Hinrich Schütze

Here, we extend a neural autoregressive topic model to exploit the full context information around words in a document in a language modeling fashion.

Language Modelling Retrieval +1

Document Informed Neural Autoregressive Topic Models

1 code implementation11 Aug 2018 Pankaj Gupta, Florian Buettner, Hinrich Schütze

Context information around words helps in determining their actual meaning, for example "networks" used in contexts of artificial neural networks or biological neuron networks.

Language Modelling Retrieval +2

Cannot find the paper you are looking for? You can Submit a new open access paper.