Smoothing Factor

Smoothing techniques aim to reduce noise and improve the robustness and efficiency of various models and algorithms across diverse fields. Current research focuses on applying smoothing within machine learning, particularly to enhance the robustness of deep learning models against adversarial attacks and improve the accuracy of predictions, often employing randomized smoothing, denoising diffusion models, and graph convolutional networks. These advancements have significant implications for improving the reliability and trustworthiness of machine learning systems in critical applications like medical image analysis and autonomous driving, as well as accelerating optimization in probabilistic programming.

Papers

November 7, 2024

Sampling-guided Heterogeneous Graph Neural Network with Temporal Smoothing for Scalable Longitudinal Data Imputation
Zhaoyang Zhang, Ziqi Chen, Qiao Liu, Jinhan Xie, Hongtu Zhu
Temporal Information Heterogeneous Graph Neural Network Imputation Method Data Imputation Smoothing Factor Signal Imputation

November 1, 2024

Certified Robustness for Deep Equilibrium Models via Serialized Random Smoothing
Weizhi Gao, Zhichao Hou, Han Xu, Xiaorui Liu
Native Robustness Randomized Smoothing Implicit Model Deep Equilibrium Model Certified Robustness Smoothing Factor Lipschitz Bound

October 27, 2024

Integrating uncertainty quantification into randomized smoothing based robustness guarantees
Sina Däubener, Kira Maag, David Krueger, Asja Fischer
Adversarial Attack Native Robustness Uncertainty Quantification Robustness Evaluation Robustness Guarantee Smoothing Factor

October 19, 2024

GNNRL-Smoothing: A Prior-Free Reinforcement Learning Model for Mesh Smoothing
Zhichao Wang, Xinhai Chen, Chunye Gong, Bo Yang, Liang Deng, Yufei Sun, Yufei Pang, Jie Liu
Smoothing Factor Mesh Ratio Mesh Network Smoothing Algorithm Mesh Smoothing

July 8, 2024

Smoothing of Headland Path Edges and Headland-to-Mainfield Lane Transitions Based on a Spatial Domain Transformation and Linear Programming
Mogens Plessen
Linear Programming Lane Change Vehicle Dynamic Smoothing Factor Planning Pipeline Nonholonomic Robot Spatial Transformation Edge Map

June 4, 2024

Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized Smoothing
Youwei Shu, Xi Xiao, Derui Wang, Yuxin Cao, Siji Chen, Jason Xue, Linyi Li, Bo Li
Mixed Effect Randomized Smoothing Gaussian Distribution Robustness Certification Smoothing Factor Norm Attack

May 14, 2024

Computation-Aware Kalman Filtering and Smoothing
Marvin Pförtner, Jonathan Wenger, Jon Cockayne, Philipp Hennig
Kalman Filter Predictive Uncertainty Efficient Inference Smoothing Factor Gauss Markov

May 1, 2024

Certified Adversarial Robustness of Machine Learning-based Malware Detectors via (De)Randomized Smoothing
Daniel Gibert, Luca Demetrio, Giulio Zizzo, Quan Le, Jordi Planes, Battista Biggio
Malware Detection Adversarial Patch Adversarial Text Smoothing Factor Patch Attack Insertion Based

April 18, 2024

Advancing the Robustness of Large Language Models through Self-Denoised Smoothing
Jiabao Ji, Bairu Hou, Zhen Zhang, Guanhua Zhang, Wenqi Fan, Qing Li, Yang Zhang, Gaowen Liu, Sijia Liu, Shiyu Chang
Large Language Model Adversarial Attack Native Robustness Adversarial Training Adversarial Perturbation Self Supervised Denoising Smoothing Factor

February 23, 2024

A Robust Defense against Adversarial Attacks on Deep Learning-based Malware Detectors via (De)Randomized Smoothing
Daniel Gibert, Giulio Zizzo, Quan Le, Jordi Planes
Adversarial Attack Adversarial Text Robust Defense Smoothing Factor Smoothed Classifier Adversarial Malware Based Malware

February 19, 2024

Diagonalisation SGD: Fast & Convergent SGD for Non-Differentiable Models via Reparameterisation and Smoothing
Dominik Wagner, Basim Khajwal, C. -H. Luke Ong
Gradient Descent Stochastic Gradient Descent Reparameterization Method Smoothing Factor Gradient Based Optimisation Non Differentiable

January 17, 2024

Functional Autoencoder for Smoothing and Representation Learning
Sidi Wu, Cédric Beaulac, Jiguo Cao
Representation Learning Neural Network Autoencoder Functional Data Analysis Smoothing Factor Functional Principal Component Nonlinear Representation Functional Learning

December 22, 2023

Transformer-Based Multi-Object Smoothing with Decoupled Data Association and Smoothing
Juliano Pinto, Georg Hess, Yuxuan Xia, Henk Wymeersch, Lennart Svensson
Multi Object Tracking Smoothing Factor Object Coordinate Space Bayesian Tracking

November 1, 2023

SmoothHess: ReLU Network Feature Interactions via Stein's Lemma
Max Torop, Aria Masoomi, Davin Hill, Kivanc Kose, Stratis Ioannidis, Jennifer Dy
Second Order ReLU Network Feature Interaction Smoothing Factor Fundamental Lemma

October 5, 2023

Certification of Deep Learning Models for Medical Image Segmentation
Othmane Laousy, Alexandre Araujo, Guillaume Chassagnon, Nikos Paragios, Marie-Pierre Revel, Maria Vakalopoulou
Deep Learning Model Medical Image Segmentation Segmentation Model Randomized Smoothing Smoothing Factor Segmentation Baseline

August 8, 2023

Class-level Structural Relation Modelling and Smoothing for Visual Representation Learning
Zitan Chen, Zhuang Qi, Xiao Cao, Xiangxian Li, Xiangxu Meng, Lei Meng
Representation Learning Visual Representation Learning Smoothing Factor Relation Modeling

June 24, 2023

Machine Learning needs Better Randomness Standards: Randomised Smoothing and PRNG-based attacks
Pranav Dahiya, Ilia Shumailov, Ross Anderson
Machine Learning Inherent Randomness Smoothing Factor Random Number Generator Randomness Factor

May 15, 2023

Label Smoothing is Robustification against Model Misspecification
Ryoya Yamasaki, Toshiyuki Tanaka
Logistic Regression Label Smoothing Model Misspecification Smoothing Factor Robustification Aware Manner

May 11, 2023

Randomized Smoothing with Masked Inference for Adversarially Robust Text Classifications
Han Cheol Moon, Shafiq Joty, Ruochen Zhao, Megh Thakkar, Xu Chi
Adversarial Example Adversarial Robustness NLP Model Scale Pre Trained Language Model Masked Modeling Smoothing Factor Robust Text Classification

April 5, 2023

On the universal approximation property of radial basis function neural networks
Aysu Ismayilova, Muhammad Ismayilov
Neural Network Universal Approximation Radial Basis Function Smoothing Factor Multivariate Function

Smoothing Factor

Papers

Sampling-guided Heterogeneous Graph Neural Network with Temporal Smoothing for Scalable Longitudinal Data Imputation

Certified Robustness for Deep Equilibrium Models via Serialized Random Smoothing

Integrating uncertainty quantification into randomized smoothing based robustness guarantees

GNNRL-Smoothing: A Prior-Free Reinforcement Learning Model for Mesh Smoothing

Smoothing of Headland Path Edges and Headland-to-Mainfield Lane Transitions Based on a Spatial Domain Transformation and Linear Programming

Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized Smoothing

Computation-Aware Kalman Filtering and Smoothing

Certified Adversarial Robustness of Machine Learning-based Malware Detectors via (De)Randomized Smoothing

Advancing the Robustness of Large Language Models through Self-Denoised Smoothing

A Robust Defense against Adversarial Attacks on Deep Learning-based Malware Detectors via (De)Randomized Smoothing

Diagonalisation SGD: Fast & Convergent SGD for Non-Differentiable Models via Reparameterisation and Smoothing

Functional Autoencoder for Smoothing and Representation Learning

Transformer-Based Multi-Object Smoothing with Decoupled Data Association and Smoothing

SmoothHess: ReLU Network Feature Interactions via Stein's Lemma

Certification of Deep Learning Models for Medical Image Segmentation

Class-level Structural Relation Modelling and Smoothing for Visual Representation Learning

Machine Learning needs Better Randomness Standards: Randomised Smoothing and PRNG-based attacks

Label Smoothing is Robustification against Model Misspecification

Randomized Smoothing with Masked Inference for Adversarially Robust Text Classifications

On the universal approximation property of radial basis function neural networks