Fixing Overconfidence in Dynamic Neural Networks

Fixing Overconfidence in Dynamic Neural Networks

13 February 2023

Arno Solin

Papers citing "Fixing Overconfidence in Dynamic Neural Networks"

11 / 11 papers shown

Title
Improving Group Fairness in Knowledge Distillation via Laplace Approximation of Early Exits Edvin Fasth Sagar Singh 24 0 0 02 May 2025
A novel framework for MCDM based on Z numbers and soft likelihood function Yuanpeng He 43 0 0 26 Dec 2024
Streamlining Prediction in Bayesian Deep Learning Rui Li Marcus Klasson Arno Solin Martin Trapp UQCV BDL 91 2 0 27 Nov 2024
Dynamic Vocabulary Pruning in Early-Exit LLMs Jort Vincenti Karim Abdel Sadek Joan Velja Matteo Nulli Metod Jazbec 24 0 0 24 Oct 2024
Joint or Disjoint: Mixing Training Regimes for Early-Exit Models Bartłomiej Krzepkowski Monika Michaluk Franciszek Szarwacki Piotr Kubaty Jary Pomponi Tomasz Trzciñski Bartosz Wójcik Kamil Adamczewski 26 0 0 19 Jul 2024
Fast yet Safe: Early-Exiting with Risk Control Metod Jazbec Alexander Timans Tin Hadvzi Veljković K. Sakmann Dan Zhang C. A. Naesseth Eric T. Nalisnick 38 5 0 31 May 2024
Early-Exit Neural Networks with Nested Prediction Sets Metod Jazbec Patrick Forré Stephan Mandt Dan Zhang Eric T. Nalisnick UQCV 29 1 0 10 Nov 2023
Collapsed Inference for Bayesian Deep Learning Zhe Zeng Guy Van den Broeck FedML BDL UQCV 22 8 0 16 Jun 2023
Towards Anytime Classification in Early-Exit Architectures by Enforcing Conditional Monotonicity Metod Jazbec J. Allingham Dan Zhang Eric T. Nalisnick 16 11 0 05 Jun 2023
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles Balaji Lakshminarayanan Alexander Pritzel Charles Blundell UQCV BDL 270 5,660 0 05 Dec 2016
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning Y. Gal Zoubin Ghahramani UQCV BDL 285 9,136 0 06 Jun 2015