Self Fitting Method

Self-fitting methods encompass techniques where a model automatically adjusts its parameters to optimize performance on a given dataset, often without explicit human intervention. Current research focuses on understanding and mitigating issues like catastrophic overfitting in adversarial training, improving the robustness and generalizability of these methods across diverse data distributions (including those with heavy tails), and developing effective evaluation metrics, particularly for multi-class problems and applications like hearing aid personalization. These advancements are crucial for enhancing the reliability and efficiency of machine learning models in various domains, ranging from robust computer vision to personalized healthcare technologies.

Papers

April 6, 2023

Classification of Heavy-tailed Features in High Dimensions: a Superstatistical Approach
Urte Adomaityte, Gabriele Sicuro, Pierpaolo Vivo
Classification Code Regularization Model High Dimension Heavy Tailed Gaussian Distribution Convex Regularization General Convex Loss Gaussian Universality Self Fitting Method

February 23, 2023

Investigating Catastrophic Overfitting in Fast Adversarial Training: A Self-fitting Perspective
Zhengbao He, Tao Li, Sizhe Chen, Xiaolin Huang
Adversarial Example Adversarial Training Fast Adversarial Training Catastrophic Overfitting Self Fitting Method

October 25, 2022

August 11, 2022

Goodness of Fit Metrics for Multi-class Predictor
Uri Itai, Natan Katz
Multi Class Confusion Matrix Various Metric Class Prediction Self Fitting Method

May 4, 2022

CE-based white-box adversarial attacks will not work using super-fitting
Youhuan Yang, Lei Sun, Leyu Dai, Song Guo, Xiuqing Mao, Xiaoqin Wang, Bayi Xu
Adversarial Attack Adversarial Robustness White Box Adversarial Attack Self Fitting Method

February 10, 2022

Hardness of Noise-Free Learning for Two-Hidden-Layer Neural Networks
Sitan Chen, Aravind Gollakota, Adam R. Klivans, Raghu Meka
ReLU Network Two Layer Neural Network Hardness Result Agnostic Learning Noise Robust Learning Layer ReLU Network Self Fitting Method