Error Aware Distribution Prediction for Lightweight Implicit Neural Representations

• URL: http://arxiv.org/abs/2607.10068v1
• Date: Sat, 11 Jul 2026 01:45:01 GMT
• Title: Error Aware Distribution Prediction for Lightweight Implicit Neural Representations
• Abstract summary: Implicit neural representations (INRs) offer compact encoding of volumes, but as lossy approximators, inevitably have prediction errors.<n>We consider INRs that can simultaneously encode relative error scales by predicting distributions using tools from uncertainty estimation.
• Score: 7.945055464912347
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Implicit neural representations (INRs) offer compact encoding of volumes, but as lossy approximators, inevitably have prediction errors. We consider INRs that can simultaneously encode relative error scales by predicting distributions using tools from uncertainty estimation. Typically, uncertainty estimation relies on computationally expensive approaches or on predefined parametric assumptions about the predictive distribution (e.g., Gaussian). In this study, we propose a lightweight method that reformulates regression-based INR training as a classification task by discretizing continuous targets into bins, enabling flexible distribution modeling to capture complex multimodal behaviors. We analyze the trade-off between regression and classification for INR training and demonstrate that the classification setting tends to achieve high reconstruction quality and competitive error awareness through uncertainty estimation, compared to regression-based approaches.

Related papers

• Conformal risk control for model-form uncertainty in parametric non-intrusive reduced-order models [1.5749416770494706]
  Non-intrusive reduced-order models (NIROMs) have become a standard tool for approximating parametric partial differential equations from computer design of experiments.<n>However, assessing the reliability of their predictions remains a major challenge, particularly in extrapolation regimes or under limited training data.<n>We introduce a framework for quantifying model-form uncertainty in NIROMs by combining a perturbative representation of reduced bases with distribution-free conformal-type methods.
  arXiv  Detail & Related papers  (2026-08-04T09:08:16Z)
• Practical Deep Heteroskedastic Regression [15.023152666894049]
  In heteroskedastic regression, where the uncertainty of the target depends on the input, a common approach is to train a neural network that parameterizes the mean and the variance of the predictive distribution.<n>We propose a simple and efficient procedure that addresses these challenges jointly by post-hoc fitting a variance model across the intermediate layers of a pretrained network on a hold-out dataset.<n>We demonstrate that our method on-par or state-of-the-art uncertainty quantification on several molecular graph datasets, without compromising mean prediction accuracy and remaining cheap to use at prediction time.
  arXiv  Detail & Related papers  (2026-03-02T11:19:32Z)
• Nonparametric Distribution Regression Re-calibration [3.0204520109309847]
  Minimizing overall prediction error encourages models to prioritize informativeness over calibration.<n>In safety-critical settings, trustworthy uncertainty estimates are often more valuable than narrow intervals.<n>We propose a novel non-parametric re-calibration algorithm based on conditional kernel mean embeddings.
  arXiv  Detail & Related papers  (2026-02-13T11:48:43Z)
• Uncertainty Quantification for Deep Regression using Contextualised Normalizing Flows [1.8899300124593648]
  We introduce MCNF, a novel uncertainty quantification method that produces both prediction intervals and the full conditioned predictive distribution.<n>MCNF operates on top of the underlying trained predictive model; thus, no predictive model retraining is needed.<n>We provide experimental evidence that the MCNF-based uncertainty estimate is well calibrated, is competitive with state-of-the-art uncertainty quantification methods, and provides richer information for downstream decision-making tasks.
  arXiv  Detail & Related papers  (2025-11-30T11:08:40Z)
• Active operator learning with predictive uncertainty quantification for partial differential equations [6.519088943440059]
  We develop a method for uncertainty quantification in deep operator networks (DeepONets) using predictive uncertainty estimates calibrated to model errors observed during training.<n>The uncertainty framework operates using a single network, in contrast to existing ensemble approaches, and introduces minimal overhead during training and inference.<n>We evaluate the uncertainty-equipped models on a series of partial differential equation (PDE) problems, and show that the model predictions are unbiased, non-skewed, and accurately reproduce solutions to the PDEs.
  arXiv  Detail & Related papers  (2025-03-05T04:48:14Z)
• Quantification of Predictive Uncertainty via Inference-Time Sampling [57.749601811982096]
  We propose a post-hoc sampling strategy for estimating predictive uncertainty accounting for data ambiguity. The method can generate different plausible outputs for a given input and does not assume parametric forms of predictive distributions.
  arXiv  Detail & Related papers  (2023-08-03T12:43:21Z)
• Dense Uncertainty Estimation [62.23555922631451]
  In this paper, we investigate neural networks and uncertainty estimation techniques to achieve both accurate deterministic prediction and reliable uncertainty estimation. We work on two types of uncertainty estimations solutions, namely ensemble based methods and generative model based methods, and explain their pros and cons while using them in fully/semi/weakly-supervised framework.
  arXiv  Detail & Related papers  (2021-10-13T01:23:48Z)
• Evaluating probabilistic classifiers: Reliability diagrams and score decompositions revisited [68.8204255655161]
  We introduce the CORP approach, which generates provably statistically Consistent, Optimally binned, and Reproducible reliability diagrams in an automated way. Corpor is based on non-parametric isotonic regression and implemented via the Pool-adjacent-violators (PAV) algorithm.
  arXiv  Detail & Related papers  (2020-08-07T08:22:26Z)
• Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift [100.52588638477862]
  We develop an approximate Bayesian inference scheme based on posterior regularisation. We demonstrate the utility of our method in the context of transferring prognostic models of prostate cancer across globally diverse populations.
  arXiv  Detail & Related papers  (2020-06-26T13:50:19Z)
• Frequentist Uncertainty in Recurrent Neural Networks via Blockwise Influence Functions [121.10450359856242]
  Recurrent neural networks (RNNs) are instrumental in modelling sequential and time-series data. Existing approaches for uncertainty quantification in RNNs are based predominantly on Bayesian methods. We develop a frequentist alternative that: (a) does not interfere with model training or compromise its accuracy, (b) applies to any RNN architecture, and (c) provides theoretical coverage guarantees on the estimated uncertainty intervals.
  arXiv  Detail & Related papers  (2020-06-20T22:45:32Z)
• Learning to Predict Error for MRI Reconstruction [67.76632988696943]
  We demonstrate that predictive uncertainty estimated by the current methods does not highly correlate with prediction error. We propose a novel method that estimates the target labels and magnitude of the prediction error in two steps.
  arXiv  Detail & Related papers  (2020-02-13T15:55:32Z)

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.