paper-with-me

Papers

A Granger-Causal Perspective on Gradient Descent with Application to Pruning

2024-12-04 · Aditya Shah, Aditya Challa, Sravan Danda, Archana Mathur, Snehanshu Saha

Stochastic Gradient Descent (SGD) is the main approach to optimizing neural networks. Several generalization properties of deep networks, such as convergence to a flatter minima, are believed to arise from SGD. This article explores the causality aspect of gradient descent. Specifically, we show that the gradient descent procedure has an implicit granger-causal relationship between the reduction in loss and a change in parameters. By suitable modifications, we make this causal relationship explicit. A causal approach to gradient descent has many significant applications which allow greater control. In this article, we illustrate the significance of the causal approach using the application of Pruning. The causal approach to pruning has several interesting properties - (i) We observe a phase shift as the percentage of pruned parameters increase. Such phase shift is indicative of an optimal pruning strategy. (ii) After pruning, we see that minima becomes "flatter", explaining the increase in accuracy after pruning weights.

📄 PDF Abstract BibTeX arXiv:2412.03035

Code (0)

등록된 구현이 없습니다.

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…
Pruning 설명 없음

Similar Papers 제목 키워드 기반

GCAD: Anomaly Detection in Multivariate Time Series from the Perspective of Granger Causality

2025-01-23 · Zehao Liu, Mengzhou Gao, Pengfei Jiao

Multivariate time series anomaly detection has numerous real-world applications and is being extensively studied. Modeling pairwise correlations between variables is crucial. Existing methods employ learnable graph struc…

Anomaly DetectionTime SeriesTime Series Anomaly Detection

Graphs in State-Space Models for Granger Causality in Climate Science

2023-07-20 · Víctor Elvira, Émilie Chouzenoux, Jordi Cerdà, Gustau Camps-Valls

Granger causality (GC) is often considered not an actual form of causality. Still, it is arguably the most widely used method to assess the predictability of a time series from another one. Granger causality has been wid…

EconometricsState Space ModelsTime Series

A Gradient-based Causal Discovery Framework with Applications to Complex Industrial Processes

2025-07-15 · Meiliang Liu, Huiwen Dong, Xiaoxiao Yang, Yunfang Xu 외 arxiv

With the advancement of deep learning technologies, various neural network-based Granger causality models have been proposed. Although these models have demonstrated notable improvements, several limitations remain. Most…

Time Series ForecastingTime Series Prediction

Granger Causality Detection with Kolmogorov-Arnold Networks

2024-12-19 · Hongyu Lin, Mohan Ren, Paolo Barucca, Tomaso Aste

Discovering causal relationships in time series data is central in many scientific areas, ranging from economics to climate science. Granger causality is a powerful tool for causality detection. However, its original for…

Kolmogorov-Arnold Networks

Variable-lag Granger Causality for Time Series Analysis

2019-12-18 · Chainarong Amornbunchornvej, Elena Zheleva, Tanya Y. Berger-Wolf

Granger causality is a fundamental technique for causal inference in time series data, commonly used in the social and biological sciences. Typical operationalizations of Granger causality make a strong assumption that e…

Causal InferenceLeadership InferenceTime SeriesTime Series Analysis