Mhc Algorithm

Implement mHC (Manifold-Constrained Hyper-Connections) for stabilizing deep network training. Use when implementing residual connection improvements with doubly stochastic matrices via Sinkhorn-Knopp algorithm. Based on DeepSeek's 2025 paper (arXiv:2512.24880).

49 stars 5 forksResearch & Science

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add UCSB-NLP-Chang/Skill-Usage --skill mhc-algorithm
Manual install
git clone --depth 1 https://github.com/UCSB-NLP-Chang/Skill-Usage.git /tmp/Skill-Usage
mkdir -p ~/.claude/skills
cp -r /tmp/Skill-Usage/tasks/mhc-layer-impl/environment/skills/mhc-algorithm ~/.claude/skills/mhc-algorithm

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# mHC: Manifold-Constrained Hyper-Connections

## Overview

mHC (Manifold-Constrained Hyper-Connections) stabilizes deep network training by constraining residual mixing matrices to be **doubly stochastic**. It provides:

- **Stable Training**: Lower gradient norm variance via doubly stochastic constraints
- **Multiple Streams**: Hyper-Connections with learnable mixing across residual streams
- **Sinkhorn Projection**: Log-space Sinkhorn-Knopp algorithm for doubly stochastic projection
- **GPT Integration**: Pattern for wrapping attention and MLP layers

Two components:
- **HyperConnections Module**: Core PyTorch module with H_res, H_pre, H_post matrices
- **Sinkhorn-Knopp**: Log-space projection to doubly stochastic manifold

## Quick Reference

| Topic | Reference |
|-------|-----------|
| Core Concepts & Math | [Core Concepts](references/core-concepts.md) |
| Sinkhorn Algorithm | [Sinkhorn-Knopp](references/sinkhorn-knopp.md) |
| HyperConnections Module | [Module Implementation](references/module-implementation.md) |
| GPT Integration | [GPT Integration](references/gpt-integration.md) |
| Common Pitfalls | [Pitfalls](references/pitfalls.md) |

## Installation

```python
# Required packages
pip install torch einops numpy
```

## Minimal Example
Read the full skill on GitHub

Details

Skill name
mhc-algorithm
Path
tasks/mhc-layer-impl/environment/skills/mhc-algorithm/SKILL.md
Repo updated
8 April 2026

FAQ

What does the Mhc Algorithm skill do?

Implement mHC (Manifold-Constrained Hyper-Connections) for stabilizing deep network training. Use when implementing residual connection improvements with doubly stochastic matrices via Sinkhorn-Knopp algorithm. Based on DeepSeek's 2025 paper (arXiv:2512.24880).

How do I install the Mhc Algorithm skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add UCSB-NLP-Chang/Skill-Usage --skill mhc-algorithm. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Mhc Algorithm popular?

It lives in UCSB-NLP-Chang/Skill-Usage, which has 49 GitHub stars and 5 forks.

Related skills

Pubchem Database

49

UCSB-NLP-Chang/Skill-Usage

Query PubChem via PUG-REST API/PubChemPy (110M+ compounds). Search by name/CID/SMILES, retrieve properties, similarity/substructure searches, bioactivity, for cheminformatics.

Databases

Pymatgen

49

UCSB-NLP-Chang/Skill-Usage

Materials science toolkit. Crystal structures (CIF, POSCAR), phase diagrams, band structure, DOS, Materials Project integration, format conversion, for computational materials science.

Research & Science

Rdkit

49

UCSB-NLP-Chang/Skill-Usage

Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom sanitization, specialized algorithms.

Frontend & Design

Nlp Research Repo Package Installment

49

UCSB-NLP-Chang/Skill-Usage

Align Python version and repo-declared dependencies (requirements.txt / environment.yml) before installing packages for NLP research code reproduction.

Research & Science

Lab Unit Harmonization

49

UCSB-NLP-Chang/Skill-Usage

Comprehensive clinical laboratory data harmonization for multi-source healthcare analytics. Convert between US conventional and SI units, standardize numeric formats, and clean data quality issues. This skill should be used when you need to harmonize lab values from different sources, convert units for clinical analysis, fix formatting inconsistencies (scientific notation, decimal separators, whitespace), or prepare lab panels for research.

Research & Science

Seismic Picker Selection

49

UCSB-NLP-Chang/Skill-Usage

This is a summary the advantages and disadvantages of earthquake event detection and phase picking methods, shared by leading seismology researchers at the 2025 Earthquake Catalog Workshop. Use it when you have a seismic phase picking task at hand.

Research & Science

Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.