paper-with-me

Papers

Generalization Error Bounds on Deep Learning with Markov Datasets

2021-12-23 · Lan V. Truong

In this paper, we derive upper bounds on generalization errors for deep neural networks with Markov datasets. These bounds are developed based on Koltchinskii and Panchenko's approach for bounding the generalization error of combined classifiers with i.i.d. datasets. The development of new symmetrization inequalities in high-dimensional probability for Markov chains is a key element in our extension, where the spectral gap of the infinitesimal generator of the Markov chain plays a key parameter in these inequalities. We also propose a simple method to convert these bounds and other similar ones in traditional deep learning and machine learning to Bayesian counterparts for both i.i.d. and Markov datasets. Extensions to $m$-order homogeneous Markov chains such as AR and ARMA models and mixtures of several Markov data services are given.

📄 PDF Abstract BibTeX arXiv:2201.11059

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Learning

Methods 이 논문이 사용한 방법론

ARMA The ARMA GNN layer implements a rational graph filter with a recursive approximation.

Similar Papers 제목 키워드 기반

Generalization Error Bounds for Noisy, Iterative Algorithms

2018-01-12 · Ankit Pensia, Varun Jog, Po-Ling Loh

In statistical learning theory, generalization error is used to quantify the degree to which a supervised machine learning algorithm may overfit to training data. Recent work [Xu and Raginsky (2017)] has established a bo…

Learning Theory

Generalization Bounds for Equivariant Networks on Markov Data

2025-03-01 · Hui Li, Zhiguo Wang, Bohui Chen, Li Sheng

Equivariant neural networks play a pivotal role in analyzing datasets with symmetry properties, particularly in complex data structures. However, integrating equivariance with Markov properties presents notable challenge…

Generalization Bounds

Generalization Bounds on Multi-Kernel Learning with Mixed Datasets

2022-05-15 · Lan V. Truong

This paper presents novel generalization bounds for the multi-kernel learning problem. Motivated by applications in sensor networks and spatial-temporal models, we assume that the dataset is mixed where each sample is ta…

Generalization Bounds

Understanding the Generalization Error of Markov algorithms through Poissonization

2025-02-11 · Benjamin Dupuis, Maxime Haddouche, George Deligiannidis, Umut Simsekli

Using continuous-time stochastic differential equation (SDE) proxies to stochastic optimization algorithms has proven fruitful for understanding their generalization abilities. A significant part of these approaches are …

Generalization BoundsStochastic Optimization

Stability and Generalization for Markov Chain Stochastic Gradient Methods

2022-09-16 · Puyu Wang, Yunwen Lei, Yiming Ying, Ding-Xuan Zhou

Recently there is a large amount of work devoted to the study of Markov chain stochastic gradient methods (MC-SGMs) which mainly focus on their convergence analysis for solving minimization problems. In this paper, we pr…

Generalization BoundsLearning Theory