Error Minimizing Noise

Minimizing error in various contexts, from machine learning models to physical simulations, is a central theme in current research. Efforts focus on developing robust aggregation techniques that combine predictions from diverse models, improving the reliability of deep reinforcement learning in adversarial environments, and creating more stable methods for generating "unlearnable examples" to protect data privacy. These advancements aim to enhance the accuracy, robustness, and security of machine learning and data analysis across diverse applications, impacting fields ranging from autonomous systems to data security.

Papers

November 10, 2024

A Variance Minimization Approach to Temporal-Difference Learning
Xingguo Chen, Yu Gong, Shangdong Yang, Wenhao Wang
LeArning Abstract Value Based Reinforcement Learning Error Minimizing Noise

September 25, 2024

Model aggregation: minimizing empirical variance outperforms minimizing empirical error
Théo Bourdais, Houman Owhadi
Empirical Risk Minimization Model Aggregation Empirical Risk Systematic Error Optimal Aggregation Error Minimizing Noise

June 7, 2024

Probabilistic Perspectives on Error Minimization in Adversarial Reinforcement Learning
Roman Belaire, Arunesh Sinha, Pradeep Varakantham
Adversarial Attack Deep Reinforcement Learning Adversarial Perturbation Bayesian Perspective Adversarial Noise Adversarial Reinforcement Learning Error Minimizing Noise

February 15, 2024

Criterion Collapse and Loss Distribution Control
Matthew J. Holland
Optimization Purpose Partial Monotonicity Gradient Descent Ascent Front Door Criterion Error Minimizing Noise Line Loss

November 22, 2023

Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noise
Yixin Liu, Kaidi Xu, Xun Chen, Lichao Sun
Native Robustness Adversarial Perturbation Adversarial Noise Unlearnable Example Error Minimizing Noise

May 18, 2023

Re-thinking Data Availablity Attacks Against Deep Neural Networks
Bin Fang, Bo Li, Shuang Wu, Ran Yi, Shouhong Ding, Lizhuang Ma
Deep Neural Network Adversarial Training Unlearnable Example Availability Attack Error Minimizing Noise

July 14, 2022

Deep Point-to-Plane Registration by Efficient Backpropagation for Error Minimizing Function
Tatsuya Yatagawa, Yutaka Ohtake, Hiromasa Suzuki
Efficient Deep Input Point Cloud Point to Plane Distance Map Registration Registration Model Optimization Based Registration Error Minimizing Noise Ground Truth Normal

March 28, 2022

Robust Unlearnable Examples: Protecting Data Against Adversarial Learning
Shaopeng Fu, Fengxiang He, Yang Liu, Li Shen, Dacheng Tao
Adversarial Training Raw Data Adversarial Learning Adversarial Loss Unlearnable Example Error Minimizing Noise

March 8, 2022

Informative Planning for Worst-Case Error Minimisation in Sparse Gaussian Process Regression
Jennifer Wakulicz, Ki Myung Brian Lee, Chanyeol Yoo, Teresa Vidal-Calleja, Robert Fitch
Task Planning Sparse Gaussian Process Error Minimizing Noise Sparse Gaussian Process Regression

December 22, 2021

Robust learning of data anomalies with analytically-solvable entropic outlier sparsification
Illia Horenko
Robust Learning Non Gaussian Anomalous Event Unsupervised Anomaly Error Minimizing Noise

Error Minimizing Noise

Papers

A Variance Minimization Approach to Temporal-Difference Learning

Model aggregation: minimizing empirical variance outperforms minimizing empirical error

Probabilistic Perspectives on Error Minimization in Adversarial Reinforcement Learning

Criterion Collapse and Loss Distribution Control

Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noise

Re-thinking Data Availablity Attacks Against Deep Neural Networks

Deep Point-to-Plane Registration by Efficient Backpropagation for Error Minimizing Function

Robust Unlearnable Examples: Protecting Data Against Adversarial Learning

Informative Planning for Worst-Case Error Minimisation in Sparse Gaussian Process Regression

Robust learning of data anomalies with analytically-solvable entropic outlier sparsification