Distance-Aware Error for Spline Networks: A Bottom-Up Approach to Uncertainty
Not on the map. Why?
Abstract (arXiv)
We develop a new class of distance-aware error bounds that tightly characterize the approximation error of spline neural networks. Our bottom-up approach analyzes the error bound of each neuron (a spline) and then extends it to the full network. We begin with error bounds for Newton's polynomial, generalize them to arbitrary splines under higher-order Lipschitz continuity, and extend the result to function compositions, the core of deep networks such as Kolmogorov-Arnold networks. By analyzing error propagation through composed spline layers, we obtain error bounds for the entire network. These bounds are deterministic, do not rely on sampling or probabilistic assumptions, and hold under mild regularity conditions. We evaluate our method on object shape estimation from sparse laser scans and safe navigation in unstructured environments. Our method is faster than the Gaussian process and Monte Carlo approaches, and our bounds reliably enclose the true error. We also develop a metric for the distance-awareness of an uncertainty estimator and show that distance-aware uncertainty for Kolmogorov networks (DAREK) is distance-aware in more regions than the baselines.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 48 of its 92 references that are in the map. First posted on arXiv 8 Jan 2025.
Builds on
48 of 92 references.
References · 48
- 2017On Calibration of Modern Neural Networkscited by 4,860
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
- 2014Deep Learning Face Attributes in the Wildcited by 3,679
- 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
- 2021Convex optimizationcited by 2,479
- 2023Progress measures for grokking via mechanistic interpretabilitycited by 822
- 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
- 2024KAN: Kolmogorov-Arnold Networkscited by 634
- 2017Deep Neural Networks as Gaussian Processescited by 617
- 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 555
- 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
36 more
- 2017Safe Model-based Reinforcement Learning with Stability Guaranteescited by 347
- 2015Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networkscited by 295
- 2014Scalable Variational Gaussian Process Classificationcited by 226
- 2018When Gaussian Process Meets Big Data: A Review of Scalable GPscited by 205
- 2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200
- 2017SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernelscited by 160
- 2024Wav-KAN: Wavelet Kolmogorov-Arnold Networkscited by 118
- 2020Neuron Shapley: Discovering the Responsible Neuronscited by 98
- 2024Kolmogorov-Arnold Networks (KANs) for Time Series Analysiscited by 97
- 2020The Kolmogorov-Arnold representation theorem revisitedcited by 89
- 2021On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertaintycited by 87
- 2024DeepOKAN: Deep Operator Network Based on Kolmogorov Arnold Networks for Mechanics Problemscited by 82
- 2024TKAN: Temporal Kolmogorov-Arnold Networkscited by 70
- 2019Uniform Error Bounds for Gaussian Process Regression with Application to Safe Controlcited by 64
- 2017Ensemble Samplingcited by 62
- 2024KAN-ODEs: Kolmogorov-Arnold Network Ordinary Differential Equations for Learning Dynamical Systems and Hidden Physicscited by 58
- 2019No-Regret Bayesian Optimization with Unknown Hyperparameterscited by 50
- 2019Error bounds for deep ReLU networks using the Kolmogorov--Arnold superposition theoremcited by 49
- 2024KAGNNs: Kolmogorov-Arnold Networks meet Graph Learningcited by 48
- 2022Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagationcited by 45
- 2022ExSpliNet: An interpretable and expressive spline-based neural networkcited by 33
- 2020Deep Neural Networks with Trainable Activations and Controlled Lipschitz Constantcited by 25
- 2019Robust Regression for Safe Exploration in Controlcited by 24
- 2021The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspectivecited by 21
- 2020Safe Multi-Agent Interaction through Robust Control Barrier Functions with Learned Uncertaintiescited by 20
- 2020Control Barriers in Bayesian Learning of System Dynamicscited by 17
- 2020A three layer neural network can represent any multivariate functioncited by 10
- 2023Learning Active Subspaces for Effective and Scalable Uncertainty Quantification in Deep Neural Networkscited by 9
- 2023Conformalized Deep Splines for Optimal and Efficient Prediction Setscited by 5
- 2018SplineNets: Continuous Neural Decision Graphscited by 4
- 2021Limits of Probabilistic Safety Guarantees when Considering Human Uncertaintycited by 4
- 2021Spline parameterization of neural network controls for deep learningcited by 3
- 2024DADEE: Well-calibrated uncertainty quantification in neural networks for barriers-based robot safetycited by 3
- 2024ISR: Invertible Symbolic Regressioncited by 2
- 2023Scalable Model-Based Gaussian Process Clusteringcited by 1
- 2024Investigating KAN-Based Physics-Informed Neural Networks for EMI/EMC Simulationscited by 1
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.