rademacher-complexity

[CEC 2019] Genetic Programming with Rademacher Complexity. Paper Link: https://ieeexplore.ieee.org/document/8790341

An implementation of Giuseppe Paleologo's Rademacher Antiserum, designed to assess strategy performance consistency through Rademacher complexity and RAS-adjusted Sharpe Ratios. This code evaluates strategy robustness by applying Rademacher random vectors for anti-overfitting analysis.

Lecture notes taken in the Quantitative Foundations of Artificial Intelligence class in Fall 2023, taught by Prof. Dr. Ludger Overbeck at Justus Liebig University Giessen.

Testing VC dimension & Rademacher complexity generalization error bounds for a simple perceptron and a rectangular classifier.

Codes and experiments for the paper "Learning Vector-valued Functions with Local Rademacher Complexity". Preprint.

Research code for On the Generalization of Adversarially Trained Quantum Classifiers

Codes and experiments for "Multi-Class Learning using Unlabeled Samples: Theory and Algorithm", published in IJCAI 2019

Rigorous solutions + verified experiments for Stanford STATS214/CS229M Machine Learning Theory (concentration, Rademacher complexity, margins, kernels, NTK, implicit regularization, online learning)

Generalization bounds for two-layer ReLU neural networks via scale-invariant complexity measures

Codes and experiments for "Multi-Class Learning: From Theory to Algorithm", published in NeurIPS 2018

Repository dealing with key concepts in Machine Learning

Investigating the effects of an innovative L2 regularization approach in a neural network model, replacing the traditional summation of squared weights with a multiplicative interaction of weights, to assess its influence on model behavior and performance.

Code for the paper "Bavarian: Betweenness Centrality Approximation with Variance-Aware Rademacher Averages", by Chloe Wohlgemuth, Cyrus Cousins, and Matteo Riondato, appearing in ACM KDD'21 and ACM TKDD'23