MATLAB toolkit for Instance Space Analysis: an automated PRELIM-SIFTED-PILOT-CLOISTER-PYTHIA-TRACE pipeline that projects problem instances into a 2D/3D space and builds algorithm footprints to assess and compare algorithmic power. Powers the MATILDA web platform.

Automated Algorithm Selection with Hyperparameter Optimization

MachSMT: An ML-Driven Algorithm Selection tool for SMT Solvers

This repo holds the code, dataset, and running scripts for fast k-means evaluation

Algorithms to solve and features to characterise TSP problems.

ASF is a flexible Python library for algorithm selection

Sparkle is a Programming by Optimisation (PbO)-based problem-solving platform designed to enable the widespread and effective use of PbO techniques for improving the state-of-the-art in solving a broad range of prominent AI problems, including SAT and AI Planning.

Mosaic: MCTS-based Pipeline Optimization

This repository holds the code for our paper "Run2Survive: A Decision-theoretic Approach to Algorithm Selection based on Survival Analysis" by Alexander Tornede, Marcel Wever, Stefan Werner, Felix Mohr and Eyke Hüllermeier.

An AutoRecSys Library built around LensKit. Performs automatic algorithm selection, hyperparameter optimzation and ensembling on LensKit models.

Uses reinforcement learning to train an algorithm selection model in solving subgraph isomorphism problems.

Federated Meta-Learning: a concept that allows everyone to benefit from the data that is generated through machine learning libraries.

Automated Algorithm Selection for Time-series Forecasting

Papers I've been reading on machine learning (bandits, reinforcement learning, algorithm selection, optimal transport, time series, etc).

Local Streamlit app that suggests and ranks ML, AI, NLP, computer vision, time series, anomaly detection, document intelligence, GenAI, and RAG algorithms for a project.

Code and text for the paper "A Comprehensive Study of k-Portfolios of Recent SAT Solvers".

The idea of this research is based on a novel paradigm for solving complex, NP-hard problems (e.g., schedul- ing, routing) by leveraging Large Language Models (LLMs) as dynamic orchestrators in Agentic solvers, as proposed in a position Paper by professor Roberto Amadini and Simone Gazza.

Finding the best linkage strategy for bottom up clustering algorithms - ICLR 2020.

Pattern-Aware Complexity Framework (PACF) - A Python implementation for analyzing and exploiting structural patterns in NP-hard optimization problems, with a focus on the Traveling Salesman Problem (TSP). Supports extensible domains like genetic sequences and weather forecasting. Licensed under MIT

Nitro Autotuning Framework