paper-with-me

Papers

Validation, Robustness, and Accuracy of Perturbation-Based Sensitivity Analysis Methods for Time-Series Deep Learning Models

2024-01-29 · Zhengguang Wang

This work undertakes studies to evaluate Interpretability Methods for Time-Series Deep Learning. Sensitivity analysis assesses how input changes affect the output, constituting a key component of interpretation. Among the post-hoc interpretation methods such as back-propagation, perturbation, and approximation, my work will investigate perturbation-based sensitivity Analysis methods on modern Transformer models to benchmark their performances. Specifically, my work answers three research questions: 1) Do different sensitivity analysis (SA) methods yield comparable outputs and attribute importance rankings? 2) Using the same sensitivity analysis method, do different Deep Learning (DL) models impact the output of the sensitivity analysis? 3) How well do the results from sensitivity analysis methods align with the ground truth?

📄 PDF Abstract BibTeX arXiv:2401.16521

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeDeep LearningSensitivityTime Series

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Residual Connection 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Multi-Head Attention 설명 없음
Adam 설명 없음

Similar Papers 제목 키워드 기반

Adversarial Vulnerabilities in Neural Operator Digital Twins: Gradient-Free Attacks on Nuclear Thermal-Hydraulic Surrogates

2026-03-23 · Samrendra Roy, Kazuma Kobayashi, Souvik Chakraborty, Rizwan-uddin 외 arxiv

Operator learning models are rapidly emerging as the predictive core of digital twins for nuclear and energy systems, promising real-time field reconstruction from sparse sensor measurements. Yet their robustness to adve…

Anomaly Detection

Global Sensitivity Analysis for MAP Inference in Graphical Models

2014-12-01 · NeurIPS 2014 12 · Jasper De Bock, Cassio P. de Campos, Alessandro Antonucci

We study the sensitivity of a MAP configuration of a discrete probabilistic graphical model with respect to perturbations of its parameters. These perturbations are global, in the sense that simultaneous perturbations of…

Sensitivity

Non-Singular Adversarial Robustness of Neural Networks

2021-02-23 · Yu-Lin Tsai, Chia-Yi Hsu, Chia-Mu Yu, Pin-Yu Chen

Adversarial robustness has become an emerging challenge for neural network owing to its over-sensitivity to small input perturbations. While being critical, we argue that solving this singular issue alone fails to provid…

Adversarial RobustnessSensitivity

Sharpness-Aware Minimization and Muon: Robustness under the Spectral Norm

2026-07-28 · Wenzhi Zhong, Edward Milsom, Michael Murray arxiv

Sharpness-Aware Minimization (SAM) aims to improve generalization by encouraging insensitivity to small, worst-case parameter perturbations. However, the notion of a "small" perturbation is inherently geometry-dependent:…

Formalizing Generalization and Adversarial Robustness of Neural Networks to Weight Perturbations

2021-12-01 · NeurIPS 2021 12 · Yu-Lin Tsai, Chia-Yi Hsu, Chia-Mu Yu, Pin-Yu Chen

Studying the sensitivity of weight perturbation in neural networks and its impacts on model performance, including generalization and robustness, is an active research topic due to its implications on a wide range of mac…

Adversarial RobustnessModel Compression