paper-with-me

홈 › Papers

Single Model Uncertainty Estimation via Stochastic Data Centering

2022-07-14 · Jayaraman J. Thiagarajan, Rushil Anirudh, Vivek Narayanaswamy, Peer-Timo Bremer

We are interested in estimating the uncertainties of deep neural networks, which play an important role in many scientific and engineering problems. In this paper, we present a striking new finding that an ensemble of neural networks with the same weight initialization, trained on datasets that are shifted by a constant bias gives rise to slightly inconsistent trained models, where the differences in predictions are a strong indicator of epistemic uncertainties. Using the neural tangent kernel (NTK), we demonstrate that this phenomena occurs in part because the NTK is not shift-invariant. Since this is achieved via a trivial input transformation, we show that this behavior can therefore be approximated by training a single neural network -- using a technique that we call $\Delta-$UQ -- that estimates uncertainty around prediction by marginalizing out the effect of the biases during inference. We show that $\Delta-$UQ's uncertainty estimates are superior to many of the current methods on a variety of benchmarks -- outlier rejection, calibration under distribution shift, and sequential design optimization of black box functions. Code for $\Delta-$UQ can be accessed at https://github.com/LLNL/DeltaUQ

📄 PDF Abstract BibTeX arXiv:2207.07235

Code (1)

llnl/deltauq 공식 구현 pytorch

Tasks

model

Methods 이 논문이 사용한 방법론

NTK 설명 없음

Similar Papers 제목 키워드 기반

Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks

2023-09-20 · Puja Trivedi, Mark Heimann, Rushil Anirudh, Danai Koutra 외

Safe deployment of graph neural networks (GNNs) under distribution shift requires models to provide accurate confidence indicators (CI). However, while it is well-known in computer vision that CI quality diminishes under…

Uncertainty Quantification

Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks

2024-01-07 · Puja Trivedi, Mark Heimann, Rushil Anirudh, Danai Koutra 외

While graph neural networks (GNNs) are widely used for node and graph representation learning tasks, the reliability of GNN uncertainty estimates under distribution shifts remains relatively under-explored. Indeed, while…

Graph ClassificationGraph Representation LearningOut-of-Distribution DetectionRepresentation Learning

Stochastic Actor-Critic: Mitigating Overestimation via Temporal Aleatoric Uncertainty

2026-01-02 · Uğurcan Özalp arxiv

Off-policy actor-critic methods in reinforcement learning train a critic with temporal-difference updates and use it as a learning signal for the policy (actor). This design typically achieves higher sample efficiency th…

Computational EfficiencyReinforcement Learning

Stochastic Order Learning: An Approach to Rank Estimation Using Noisy Data

2026-07-09 · Chaewon Lee, Seon-Ho Lee, Chang-Su Kim arxiv

Rank estimation under label noise poses a fundamental challenge, as ordinal annotations often exhibit structured uncertainty rather than simple label corruption. In this paper, we reformulate rank estimation with noisy o…

Interacting Contour Stochastic Gradient Langevin Dynamics

2022-02-20 · ICLR 2022 4 · Wei Deng, Siqi Liang, Botao Hao, Guang Lin 외

We propose an interacting contour stochastic gradient Langevin dynamics (ICSGLD) sampler, an embarrassingly parallel multiple-chain contour stochastic gradient Langevin dynamics (CSGLD) sampler with efficient interaction…