Not Just How Much, But Where: Decomposing Epistemic Uncertainty into Per-Class Contributions

• URL: http://arxiv.org/abs/2602.21160v2
• Date: Thu, 26 Feb 2026 02:51:33 GMT
• Title: Not Just How Much, But Where: Decomposing Epistemic Uncertainty into Per-Class Contributions
• Authors: Mame Diarra Toure, David A. Stephens,
• Abstract summary: In safety-critical classification, the cost of failure is often asymmetric.<n>We decompose MI into a per-class vector $C_k(x)=_k2/ (2_k)$, with $_k=mathbbE[p_k]$ and $_k2=mathrmVar[p_k]$ across posterior samples.
• Score: 1.2891210250935148
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In safety-critical classification, the cost of failure is often asymmetric, yet Bayesian deep learning summarises epistemic uncertainty with a single scalar, mutual information (MI), that cannot distinguish whether a model's ignorance involves a benign or safety-critical class. We decompose MI into a per-class vector $C_k(x)=σ_k^{2}/(2μ_k)$, with $μ_k{=}\mathbb{E}[p_k]$ and $σ_k^2{=}\mathrm{Var}[p_k]$ across posterior samples. The decomposition follows from a second-order Taylor expansion of the entropy; the $1/μ_k$ weighting corrects boundary suppression and makes $C_k$ comparable across rare and common classes. By construction $\sum_k C_k \approx \mathrm{MI}$, and a companion skewness diagnostic flags inputs where the approximation degrades. After characterising the axiomatic properties of $C_k$, we validate it on three tasks: (i) selective prediction for diabetic retinopathy, where critical-class $C_k$ reduces selective risk by 34.7\% over MI and 56.2\% over variance baselines; (ii) out-of-distribution detection on clinical and image benchmarks, where $\sum_k C_k$ achieves the highest AUROC and the per-class view exposes asymmetric shifts invisible to MI; and (iii) a controlled label-noise study in which $\sum_k C_k$ shows less sensitivity to injected aleatoric noise than MI under end-to-end Bayesian training, while both metrics degrade under transfer learning. Across all tasks, the quality of the posterior approximation shapes uncertainty at least as strongly as the choice of metric, suggesting that how uncertainty is propagated through the network matters as much as how it is measured.

Related papers

• Optimal Unconstrained Self-Distillation in Ridge Regression: Strict Improvements, Precise Asymptotics, and One-Shot Tuning [61.07540493350384]
  Self-distillation (SD) is the process of retraining a student on a mixture of ground-truth and the teacher's own predictions.<n>We show that for any prediction risk, the optimally mixed student improves upon the ridge teacher for every regularization level.<n>We propose a consistent one-shot tuning method to estimate $star$ without grid search, sample splitting, or refitting.
  arXiv  Detail & Related papers  (2026-02-19T17:21:15Z)
• On the Sparsifiability of Correlation Clustering: Approximation Guarantees under Edge Sampling [6.908972852063454]
  Correlation Clustering (CC) is a fundamental unsupervised learning primitive.<n>We study how much edge information is needed to retain LP-based guarantees.<n>We show via Yao's minimax principle that without pseudometric structure, any algorithm observing $o(n)$ uniformly random edges incurs an approximation ratio.
  arXiv  Detail & Related papers  (2026-02-14T09:12:15Z)
• Phase-space entropy at acquisition reflects downstream learnability [54.4100065023873]
  We propose an acquisition-level scalar $S_mathcal B$ based on instrument-resolved phase space.<n>We show theoretically that (S_mathcal B) correctly identifies the phase-space coherence of periodic sampling.<n>$|S_mathcal B|$ consistently ranks sampling geometries and predicts downstream reconstruction/recognition difficulty emphwithout training.
  arXiv  Detail & Related papers  (2025-12-22T10:03:51Z)
• Spectral Sentinel: Scalable Byzantine-Robust Decentralized Federated Learning via Sketched Random Matrix Theory on Blockchain [0.0]
  Byzantine clients poison gradients under heterogeneous (Non-IID) data.<n>We propose Spectral Sentinel, a Byzantine detection and aggregation framework.<n>We implement the full system with blockchain integration on Polygon networks.
  arXiv  Detail & Related papers  (2025-12-14T09:43:03Z)
• The Structure of Cross-Validation Error: Stability, Covariance, and Minimax Limits [3.3008315224941978]
  We show how properties of algorithm-distribution pairs can affect the choice for the number of folds in $k$-fold cross-validation.<n>We also prove that CV cannot attain the optimum of order $1/n$ achievable by a validation set of size $n$.
  arXiv  Detail & Related papers  (2025-11-05T15:35:46Z)
• Emergence and scaling laws in SGD learning of shallow neural networks [64.48316762675141]
  We study the complexity of online gradient descent (SGD) for learning a two-layer neural network with $P$ neurons on isotropic Gaussian data.<n>We provide a precise analysis of SGD dynamics for the training of a student two-layer network to minimize the mean squared error (MSE) objective.
  arXiv  Detail & Related papers  (2025-04-28T16:58:55Z)
• Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis [55.561961365113554]
  3D Gaussian Splatting (3DGS) has demonstrated remarkable effectiveness in novel view synthesis (NVS)<n>In this paper, we introduce Self-Ensembling Gaussian Splatting (SE-GS)<n>We achieve self-ensembling by incorporating an uncertainty-aware perturbation strategy during training.<n> Experimental results on the LLFF, Mip-NeRF360, DTU, and MVImgNet datasets demonstrate that our approach enhances NVS quality under few-shot training conditions.
  arXiv  Detail & Related papers  (2024-10-31T18:43:48Z)
• Agnostic Smoothed Online Learning without Knowledge of the Base Measure [5.167069404528051]
  We propose an algorithm to guarantee sublinear regret for smoothed online learning without prior knowledge of $mu$.<n>R-Cover has adaptive regret $tilde O(sqrtdT/sigma)$ for function classes with dimension $d$, which is optimal up to logarithmic factors.
  arXiv  Detail & Related papers  (2024-10-07T15:25:21Z)
• On Characterizing and Mitigating Imbalances in Multi-Instance Partial Label Learning [57.18649648182171]
  We make contributions towards addressing a problem that hasn't been studied so far in the context of MI-PLL.<n>We derive class-specific risk bounds for MI-PLL, while making minimal assumptions.<n>Our theory reveals a unique phenomenon: that $sigma$ can greatly impact learning imbalances.
  arXiv  Detail & Related papers  (2024-07-13T20:56:34Z)
• TIC-TAC: A Framework for Improved Covariance Estimation in Deep Heteroscedastic Regression [109.69084997173196]
  Deepscedastic regression involves jointly optimizing the mean and covariance of the predicted distribution using the negative log-likelihood. Recent works show that this may result in sub-optimal convergence due to the challenges associated with covariance estimation. We study two questions: (1) Does the predicted covariance truly capture the randomness of the predicted mean? Our results show that not only does TIC accurately learn the covariance, it additionally facilitates an improved convergence of the negative log-likelihood.
  arXiv  Detail & Related papers  (2023-10-29T09:54:03Z)
• Kernel-Based Tests for Likelihood-Free Hypothesis Testing [21.143798051525646]
  Given $n$ observations from two balanced classes, consider the task of labeling an additional $m$ inputs that are known to all belong to emphone of the two classes. Special cases of this problem are well-known; when $m=1$ it corresponds to binary classification; and when $mapprox n$ it is equivalent to two-sample testing. In recent work it was discovered that there is a fundamental trade-off between $m$ and $n$: increasing the data sample $m$ reduces the amount $n$ of training/simulation data needed.
  arXiv  Detail & Related papers  (2023-08-17T15:24:03Z)
• The Sample Complexity of Robust Covariance Testing [56.98280399449707]
  We are given i.i.d. samples from a distribution of the form $Z = (1-epsilon) X + epsilon B$, where $X$ is a zero-mean and unknown covariance Gaussian $mathcalN(0, Sigma)$. In the absence of contamination, prior work gave a simple tester for this hypothesis testing task that uses $O(d)$ samples. We prove a sample complexity lower bound of $Omega(d2)$ for $epsilon$ an arbitrarily small constant and $gamma
  arXiv  Detail & Related papers  (2020-12-31T18:24:41Z)
• Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction [63.41789556777387]
  Asynchronous Q-learning aims to learn the optimal action-value function (or Q-function) of a Markov decision process (MDP) We show that the number of samples needed to yield an entrywise $varepsilon$-accurate estimate of the Q-function is at most on the order of $frac1mu_min (1-gamma)5varepsilon2+ fract_mixmu_min (1-gamma)$ up to some logarithmic factor.
  arXiv  Detail & Related papers  (2020-06-04T17:51:00Z)
• Agnostic Learning of a Single Neuron with Gradient Descent [92.7662890047311]
  We consider the problem of learning the best-fitting single neuron as measured by the expected square loss. For the ReLU activation, our population risk guarantee is $O(mathsfOPT1/2)+epsilon$. For the ReLU activation, our population risk guarantee is $O(mathsfOPT1/2)+epsilon$.
  arXiv  Detail & Related papers  (2020-05-29T07:20:35Z)

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.