A Julia package for solving multi-objective optimization problems with composite structure (F = f + h). Implements Conditional Gradient, Proximal Gradient, and Partially Derivative-Free algorithms that operate directly on the vector-valued objective, without scalarization or heuristics (direct / vector-optimization methods).

Advanced Mathematical Optimization & Deep Learning Optimizers from scratch. Covers KKT duality, L-BFGS, proximal methods (ADMM, FISTA), stochastic algorithms (SVRG, Lion), and cutting-edge deep learning optimizers like K-FAC, Shampoo, Sophia, SAM, and Muon. Bridging strict convex calculus with large-scale Transformer training.