paper-with-me

홈 › Papers

HiGrad: Uncertainty Quantification for Online Learning and Stochastic Approximation

2018-02-13 · Weijie J. Su, Yuancheng Zhu

Stochastic gradient descent (SGD) is an immensely popular approach for online learning in settings where data arrives in a stream or data sizes are very large. However, despite an ever-increasing volume of work on SGD, much less is known about the statistical inferential properties of SGD-based predictions. Taking a fully inferential viewpoint, this paper introduces a novel procedure termed HiGrad to conduct statistical inference for online learning, without incurring additional computational cost compared with SGD. The HiGrad procedure begins by performing SGD updates for a while and then splits the single thread into several threads, and this procedure hierarchically operates in this fashion along each thread. With predictions provided by multiple threads in place, a $t$-based confidence interval is constructed by decorrelating predictions using covariance structures given by a Donsker-style extension of the Ruppert--Polyak averaging scheme, which is a technical contribution of independent interest. Under certain regularity conditions, the HiGrad confidence interval is shown to attain asymptotically exact coverage probability. Finally, the performance of HiGrad is evaluated through extensive simulation studies and a real data example. An R package \texttt{higrad} has been developed to implement the method.

📄 PDF Abstract BibTeX arXiv:1802.04876

Code (0)

등록된 구현이 없습니다.

Tasks

Uncertainty Quantification

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

Resampling Stochastic Gradient Descent Cheaply for Efficient Uncertainty Quantification

2023-10-17 · Henry Lam, Zitong Wang

Stochastic gradient descent (SGD) or stochastic approximation has been widely used in model training and stochastic optimization. While there is a huge literature on analyzing its convergence, inference on the obtained s…

Stochastic OptimizationUncertainty Quantification

Neuronal Stochastic Attention Circuit (NSAC) for Probabilistic Representation Learning

2026-05-25 · Waleed Razzaq, Yun-Bo Zhao arxiv

Reliable uncertainty quantification in continuous-time (CT) representation learning remains nascent, particularly within CT attention literature. We introduce the Neuronal Stochastic Attention Circuit (NSAC), a novel bio…

Representation LearningAutonomous Vehicles

Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problems

2018-09-21 · Dongkun Zhang, Lu Lu, Ling Guo, George Em. Karniadakis

Physics-informed neural networks (PINNs) have recently emerged as an alternative way of solving partial differential equations (PDEs) without the need of building elaborate grids, instead, using a straightforward impleme…

Active LearningUncertainty Quantification

Assessment of DeepONet for reliability analysis of stochastic nonlinear dynamical systems

2022-01-31 · Shailesh Garg, Harshit Gupta, Souvik Chakraborty

Time dependent reliability analysis and uncertainty quantification of structural system subjected to stochastic forcing function is a challenging endeavour as it necessitates considerable computational time. We investiga…

Uncertainty QuantificationZero-Shot Learning

Surrogate modeling for uncertainty quantification in nonlinear dynamics

2025-07-16 · S. Marelli, S. Schär, B. Sudret arxiv

Predicting the behavior of complex systems in engineering often involves significant uncertainty about operating conditions, such as external loads, environmental effects, and manufacturing variability. As a result, unce…