svrg

MATLAB/Octave library for stochastic optimization algorithms: Version 1.0.20

The code in order to implement FedProx (ICPP 2020)

Code the ICML 2024 paper: "Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models"

A clean, theoretical implementation of Stochastic Variance Reduced Gradient (SVRG) demonstrating linear convergence rates on convex objectives. Includes comparative analysis against vanilla SGD with empirical validation on synthetic and real-world datasets.

Project definition and implementations for Convex Optimization Course

NYCU Optimization Algorithms coursework: convex analysis proofs, first-order methods, variance-reduced SGD/SVRG, and QP/conic programming with Gurobi.

Query unified single-cell gene expression metadata across 12 databases with AI-driven retrieval and cross-database links