Reposted by Bálint Mucsányi
Excited to present our work Rethinking Approximate Gaussian Inference (AGI 🤯) in Classification at NeurIPS 2025 in San Diego! Find out why you shouldn’t use Softmax in uncertainty quantification. 😳
Exhibit Hall C,D,E, Poster #601
Thu 4 Dec 11 am - 2 pm
📖 arxiv.org/abs/2502.03366
arxiv.org
Rethinking Approximate Gaussian Inference in Classification
In classification tasks, softmax functions are ubiquitously used as output activations to produce predictive probabilities. Such outputs only capture aleatoric uncertainty. To capture epistemic uncert...
