2 Repos
Strategies for balancing multiple competing performance metrics during model training.
Distinct from GraphQL Performance Optimizers: Distinct from GraphQL performance optimizers: focuses on multi-objective hyperparameter tuning.
Explore 2 awesome GitHub repositories matching software engineering & architecture · Optimization Objectives. Refine with filters or upvote what's useful.
Optuna is a Python-based hyperparameter optimization framework designed to automate the search for optimal machine learning model configurations. It functions as a Bayesian optimization library that systematically tests parameter combinations to maximize or minimize objective functions, streamlining the model development process through iterative evaluation. The project distinguishes itself through a define-by-run dynamic construction model, which allows users to build complex, conditional search spaces using standard programming logic. Its architecture is highly modular, featuring a pluggabl
Finds optimal parameter sets that balance multiple competing performance metrics simultaneously during model training.
Penrose is a compiler that transforms structured mathematical notation into optimized SVG diagrams. It uses a three-stage pipeline of separate domain, substance, and style files to define mathematical objects, relationships, and visual presentation, then solves continuous optimization problems with user-defined spatial constraints and objectives to automatically arrange diagram elements. The system separates diagram content from visual style using distinct declarative languages, and provides a typed domain language with subtype hierarchies for mathematical objects. It supports embedding compi
Defines continuous objective functions encoding spatial relationships for diagram optimization.