Machine-Learning-Regression

Code and results accompanying our paper titled RATT: Leveraging Unlabeled Data to guarantee generalization at ICML 2021 (Long Talk)

This is the official repository for the ICLR 2024 paper Out-Of-Domain Unlabeled Data Improves Generalization.

Stagewise training accelerates convergence of testing error over sgd

Official implementation for "A Statistical Model for Predicting Generalization in Few-Shot Classification" accepted at EUSIPCO 2023

Meta Ensemble Self-Learning Model with Optimization

A small C library for computation of U-statistics

Single Layer Perceptrons (SLPs) and Multi-Layer Perceptrons (MLPs) from scratch, only with numpy, for classification and regression. MLPs with Keras for time-series prediction.

Assessing Impact of Vicinal Risk Minimization on Teacher-Student Learning

Intuitive Package for Heterogeneous Ensemble Meta-Learning (Classification, Regression) that is fully-automated

On the onset of memorization to generalization transition in diffusion models

All codes of my master thesis conducted under computational learning theory