Pinned Loading

1. supermario-optimizer supermario-optimizer Public

   SMO (Super Mario Optimizer) is an ultra-memory-efficient PyTorch optimizer designed to solve the "Memory Wall" problem in Deep Learning. It reduces the optimizer state memory by 60-93% while retain…

   Python

2. dge-optimizer dge-optimizer Public

   A memory-efficient, gradient-free zeroth-order (derivative-free) optimizer designed to solve the "Curse of Dimensionality" in Black-Box optimization and memory-constrained Machine Learning. It prov…

   Python

3. seismic-descent seismic-descent Public

   A paradigm-shifting stochastic optimization algorithm that mimics physical earthquakes. Instead of bouncing particles randomly, Seismic Descent cyclically disrupts the geometry of the target landsc…

   Python

4. k-alternatives-meta-algorithm k-alternatives-meta-algorithm Public

   k-Alternatives is a stochastic search algorithm designed to optimize combinatorial problems by exploring controlled deviations from a heuristic baseline. Originally designed for the Traveling Sales…

   JavaScript 1

5. neural-tablebases neural-tablebases Public

   Deep learning approach to chess tablebase compression using geometric position encoding. Achieves 99.93% accuracy on 3-piece endgames with 79.7x compression ratio vs Syzygy format.

   Rust 1

6. ripple-insertion ripple-insertion Public

   Ripple Insertion (Recursive Cheapest Insertion) is an experimental algorithm designed for Dynamic Traveling Salesperson Problem (TSP) scenarios. Unlike traditional solvers that calculate a route fr…

   JavaScript 1