Search Results for author:
Found 8 papers, 4 papers with code
A Generative Model of Symmetry Transformations
Correctly capturing the symmetry transformations of data can lead to efficient models with strong generalization capabilities, though methods incorporating symmetries often require prior knowledge.
A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image Models
In particular, we ask "Given a large pool of prompts, can we automatically score the prompts and ensemble those that are most suitable for a particular downstream dataset, without needing access to labeled validation data?".
Adapting the Linearised Laplace Model Evidence for Modern Deep Learning
The linearised Laplace method for estimating model uncertainty has received renewed attention in the Bayesian deep learning community.
Linearised Laplace Inference in Networks with Normalisation Layers and the Neural g-Prior
We show that for neural networks (NN) with normalisation layers, i. e. batch norm, layer norm, or group norm, the Laplace model evidence does not approximate the volume of a posterior mode and is thus unsuitable for model selection.
Sparse MoEs meet Efficient Ensembles
Machine learning models based on the aggregated outputs of submodels, either at the activation or prediction levels, often exhibit strong performance compared to individual models.
Bayesian Deep Learning via Subnetwork Inference
In particular, we implement subnetwork linearized Laplace as a simple, scalable Bayesian deep learning method: We first obtain a MAP estimate of all weights and then infer a full-covariance Gaussian posterior over a subnetwork using the linearized Laplace approximation.
Depth Uncertainty in Neural Networks
Existing methods for estimating uncertainty in deep learning tend to require multiple forward passes, making them unsuitable for applications where computational resources are limited.
Variational Depth Search in ResNets
One-shot neural architecture search allows joint learning of weights and network architecture, reducing computational cost.
