Emanuel Sommer

Handbook of Bayesian Deep Learning

Claudio Agostinelli, Laurence Aitchison, Emanuel Aldea, Richard Allmendinger et autres

International audience

it, gb, fr, us, hk, de, ch, sa, dk, no, cn, nl, ca, au (code pays fourni par la source)

Handbook of Bayesian Deep Learning

Claudio Agostinelli, Laurence Aitchison, Emanuel Aldea, Richard Allmendinger et autres

it, gb, fr, us, hk, de, ch, sa, dk, no, cn, nl, ca, au (code pays fourni par la source)

bde: A Python Package for Bayesian Deep Ensembles via MILE

Vyron Arvanitis, Angelos Aslanidis, Emanuel Sommer, David Rügamer

bde is a Python package designed to

de (code pays fourni par la source)

Guiding Posterior Exploration with Optimizer-Derived Geometry

Moritz Schlager, Emanuel Sommer, Thomas Möllenhoff, David Rügamer

Sampling-based methods offer a principled approach to uncertainty quantification in Bayesian neural networks. Their practical use, however, is often challenged by the computational cost of exploring high-dimensional and multimodal posterior distributions. To overcome these difficulties, Bayesian Deep Ensembles, i.e., warmstarting the sampling …

Guiding Posterior Exploration with Optimizer-Derived Geometry

Moritz Schlager, Emanuel Sommer, Thomas Möllenhoff, David Rügamer

Sampling-based methods offer a principled approach to uncertainty quantification in Bayesian neural networks. Their practical use, however, is often challenged by the computational cost of exploring high-dimensional and multimodal posterior distributions. To overcome these difficulties, Bayesian Deep Ensembles, i.e., warmstarting the sampling …

nl, de (code pays fourni par la source)

bde: A Python Package for Bayesian Deep Ensembles via MILE

Vyron Arvanitis, Angelos Aslanidis, Emanuel Sommer, David Rügamer

bde is a user-friendly Python package for Bayesian Deep Ensembles with a particular focus on tabular data. Built on an efficient JAX implementation of the sampling-based inference method Microcanonical Langevin Ensembles (MILE), it provides scikit-learn compatible estimators for fast training, efficient Markov …

de (code pays fourni par la source)

bde: A Python Package for Bayesian Deep Ensembles via MILE

Vyron Arvanitis, Angelos Aslanidis, Emanuel Sommer, David Rügamer

bde is a user-friendly Python package for Bayesian Deep Ensembles with a particular focus on tabular data. Built on an efficient JAX implementation of the sampling-based inference method Microcanonical Langevin Ensembles (MILE), it provides scikit-learn compatible estimators for fast training, efficient Markov …

de (code pays fourni par la source)

On the Construction and Implications of Low-Loss Valleys in LoRA-based Bayesian Inference

Daniel Dold, Emanuel Sommer, Julius Kobialka, Oliver Dürr et autres

While parameter-efficient fine-tuning methods like low-rank adaptation (LoRA) are standard for large language models, principled estimation of epistemic uncertainty remains challenging. Recent results in the LoRA regime suggest that discrete multi-mode approaches such as deep ensembles offer little benefit over single-mode methods. …

On the Construction and Implications of Low-Loss Valleys in LoRA-based Bayesian Inference

Daniel Dold, Emanuel Sommer, Julius Kobialka, Oliver Dürr et autres

While parameter-efficient fine-tuning methods like low-rank adaptation (LoRA) are standard for large language models, principled estimation of epistemic uncertainty remains challenging. Recent results in the LoRA regime suggest that discrete multi-mode approaches such as deep ensembles offer little benefit over single-mode methods. …

de (code pays fourni par la source)

Position: The Time for Sampling Is Now! Charting a New Course for Bayesian Deep Learning

Emanuel Sommer, David Rügamer

The practical adoption of sampling-based inference (SAI) in Bayesian neural networks (BNNs) remains limited, partly due to persistent misconceptions about the feasibility and efficiency of sampling. This position paper argues that SAI has achieved computational parity with optimization-based methods and is at …

Position: The Time for Sampling Is Now! Charting a New Course for Bayesian Deep Learning

Emanuel Sommer, David Rügamer

The practical adoption of sampling-based inference (SAI) in Bayesian neural networks (BNNs) remains limited, partly due to persistent misconceptions about the feasibility and efficiency of sampling. This position paper argues that SAI has achieved computational parity with optimization-based methods and is at …

bde: A Python Package for Bayesian Deep Ensembles via MILE

Vyron Arvanitis, Angelos Aslanidis, Emanuel Sommer, David Rügamer

bde is a user-friendly Python package for Bayesian Deep Ensembles with a particular focus on tabular data. Built on an efficient JAX implementation of the sampling-based inference method Microcanonical Langevin Ensembles (MILE), it provides scikit-learn compatible estimators for fast training, efficient Markov …