Is the Last Layer Sufficient for Uncertainty Quantification?

• URL: http://arxiv.org/abs/2605.30741v1
• Date: Fri, 29 May 2026 02:09:27 GMT
• Title: Is the Last Layer Sufficient for Uncertainty Quantification?
• Abstract summary: Epistemic uncertainty quantification (UQ) for deep neural networks (DNNs) is a requirement for safe adoption of AI in mission-critical settings.<n>We compare GLMs arising from full-network and last-layer linearization using both theoretical and empirical approaches.<n>A last-layer approximation yields comparable UQ performance while offering substantially improved computational efficiency.
• Score: 13.132499571608868
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Epistemic uncertainty quantification (UQ) for deep neural networks (DNNs) is a requirement for safe adoption of AI in mission-critical settings. Several leading methods for UQ linearize DNNs to form Bayesian Generalized Linear Models (GLMs), where epistemic uncertainty is modeled via the predictive posterior distribution. Linearizing around the parameters of the final connected layer of a DNN is a commonly used approximation for reducing the computational burden of such GLMs, though it is often believed to come at the cost of degraded performance. In this work, we compare GLMs arising from full-network and last-layer linearization using both theoretical and empirical approaches. We first employ tools from random matrix theory to conduct a theoretical comparison; this analysis reveals no meaningful improvement in the UQ capabilities of full linearization. Coupled with a large-scale empirical evaluation across a range of modern machine learning tasks, we arrive at the following conclusion: a last-layer approximation yields comparable UQ performance while offering substantially improved computational efficiency.

Related papers

• Optimal Condition for Initialization Variance in Deep Neural Networks: An SGD Dynamics Perspective [0.0]
  gradient descent (SGD) is one of the most fundamental optimization algorithms in machine learning (ML)<n>We study the relationship between the quasi-stationary distribution derived from this equation and the initial distribution through the Kullback-Leibler (KL) divergence.<n>We experimentally confirm our theoretical results by using the classical SGD to train fully connected neural networks on the MNIST and Fashion-MNIST datasets.
  arXiv  Detail & Related papers  (2025-08-18T11:18:12Z)
• MesaNet: Sequence Modeling by Locally Optimal Test-Time Training [67.45211108321203]
  We introduce a numerically stable, chunkwise parallelizable version of the recently proposed Mesa layer.<n>We show that optimal test-time training enables reaching lower language modeling perplexity and higher downstream benchmark performance than previous RNNs.
  arXiv  Detail & Related papers  (2025-06-05T16:50:23Z)
• Evidential Uncertainty Probes for Graph Neural Networks [3.5169632430086315]
  We propose a plug-and-play framework for uncertainty quantification in Graph Neural Networks (GNNs)<n>Our Evidential Probing Network (EPN) uses a lightweight Multi-Layer-Perceptron (MLP) head to extract evidence from learned representations.<n>EPN-reg achieves state-of-the-art performance in accurate and efficient uncertainty quantification, making it suitable for real-world deployment.
  arXiv  Detail & Related papers  (2025-03-11T07:00:54Z)
• Matrix Completion via Nonsmooth Regularization of Fully Connected Neural Networks [7.349727826230864]
  It has been shown that enhanced performance could be attained by using nonlinear estimators such as deep neural networks. In this paper, we control over-fitting by regularizing FCNN model in terms of norm intermediate representations. Our simulations indicate the superiority of the proposed algorithm in comparison with existing linear and nonlinear algorithms.
  arXiv  Detail & Related papers  (2024-03-15T12:00:37Z)
• Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL [86.0987896274354]
  We first identify a fundamental pattern, self-excitation, as the primary cause of Q-value estimation divergence in offline RL. We then propose a novel Self-Excite Eigenvalue Measure (SEEM) metric to measure the evolving property of Q-network at training. For the first time, our theory can reliably decide whether the training will diverge at an early stage.
  arXiv  Detail & Related papers  (2023-10-06T17:57:44Z)
• Improved uncertainty quantification for neural networks with Bayesian last layer [0.0]
  Uncertainty quantification is an important task in machine learning. We present a reformulation of the log-marginal likelihood of a NN with BLL which allows for efficient training using backpropagation.
  arXiv  Detail & Related papers  (2023-02-21T20:23:56Z)
• A Meta-Learning Approach to the Optimal Power Flow Problem Under Topology Reconfigurations [69.73803123972297]
  We propose a DNN-based OPF predictor that is trained using a meta-learning (MTL) approach. The developed OPF-predictor is validated through simulations using benchmark IEEE bus systems.
  arXiv  Detail & Related papers  (2020-12-21T17:39:51Z)
• LQF: Linear Quadratic Fine-Tuning [114.3840147070712]
  We present the first method for linearizing a pre-trained model that achieves comparable performance to non-linear fine-tuning. LQF consists of simple modifications to the architecture, loss function and optimization typically used for classification.
  arXiv  Detail & Related papers  (2020-12-21T06:40:20Z)
• Exploring the Uncertainty Properties of Neural Networks' Implicit Priors in the Infinite-Width Limit [47.324627920761685]
  We use recent theoretical advances that characterize the function-space prior to an ensemble of infinitely-wide NNs as a Gaussian process. This gives us a better understanding of the implicit prior NNs place on function space. We also examine the calibration of previous approaches to classification with the NNGP.
  arXiv  Detail & Related papers  (2020-10-14T18:41:54Z)
• Improving predictions of Bayesian neural nets via local linearization [79.21517734364093]
  We argue that the Gauss-Newton approximation should be understood as a local linearization of the underlying Bayesian neural network (BNN) Because we use this linearized model for posterior inference, we should also predict using this modified model instead of the original one. We refer to this modified predictive as "GLM predictive" and show that it effectively resolves common underfitting problems of the Laplace approximation.
  arXiv  Detail & Related papers  (2020-08-19T12:35:55Z)
• Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networks [50.42141893913188]
  We study a distributed variable for large-scale AUC for a neural network as with a deep neural network. Our model requires a much less number of communication rounds and still a number of communication rounds in theory. Our experiments on several datasets show the effectiveness of our theory and also confirm our theory.
  arXiv  Detail & Related papers  (2020-05-05T18:08:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.