machine-learning-algorithms

What problem does it solve?

Helps users craft CLRS-style machine-learning algorithm prompts by separating textbook models, invariants, and proofs from production ML practice, reducing hallucinations and misapplied heuristics.

Core Features & Use Cases

• Enforces CLRS conventions for mathematical formatting, theorem hooks, and display-block organization.
• Supports prompts for k-means, Lloyd's procedure, multiplicative weights, weighted majority, online experts, gradient descent, projected gradient descent, convex optimization, linear regression, and regularization with explicit model assumptions.
• Provides structured prompts and guardrails to keep theoretical reasoning aligned with CLRS while allowing optional production guidance upon request.

Quick Start

Pose a CLRS-style ML prompt and request a rigorous, theorem-based solution with explicit model assumptions.