Skip to content
View mmarfinetz's full-sized avatar
:shipit:
:shipit:

Block or report mmarfinetz

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
mmarfinetz/README.md

👋 Hi, I'm @mmarfinetz

Interests: DeFi; building with LLMs; systems that learn via evolution and adaptation with applications to algorithmic trading and agent-based decision systems.

Publications

Evolving Deep Learning Optimizers
arXiv PDF DOI

TL;DR. Evolutionary framework that discovers novel deep learning optimizers by combining primitive gradient operators; produces hybrid update rules that outperform AdamW in low-data regimes.

Hybrid Genetic Algorithm for Optimal User Order Routing: Multi‑Objective Solver Optimization in CoW Protocol Batch Auctions
arXiv PDF DOI

TL;DR. Multi‑objective evolutionary solver (NSGA‑II hybrid) for CoW Protocol batch auctions that balances user surplus, gas, slippage and risk under tight deadlines; outperforms deterministic baselines on small–medium orders and converges within ~0.5s median.


Selected Work

  • Alpha Router — Evolutionary solver
    Implementation of my published hybrid genetic algorithm (NSGA-II + deterministic refinement) for CoW Protocol batch auctions. Handles multi-objective optimization (surplus, gas, slippage, risk) under tight latency constraints; deployed as a production-ready routing engine.
    Repo: https://github.com/mmarfinetz/Alpha-Router

  • evo-optimizer — Evolutionary optimizer discovery for ML
    PyTorch framework that evolves new update rules by combining primitive gradient operators (sign-grad, momentum, normalization terms). Produces hybrid optimizers that outperform AdamW in low-data regimes and accelerate convergence across CIFAR-10, MNIST, and Fashion-MNIST.
    Repo: https://github.com/mmarfinetz/evo-optimizer

  • VinRouge — On-chain trading agent
    Advanced signals/strategies and recommendations (mean reversion, RSI, Bollinger %B, Z-score).
    Repo: https://github.com/mmarfinetz/VinRouge

  • Arbitrage Bot
    TypeScript/Hardhat bot that discovers and executes arbitrage via Flashbots (regular, MEV-Share, WebSocket, hybrid). React dashboard, gas/circuit-breaker logic.
    Repo: https://github.com/mmarfinetz/arbitrage-bot

  • ElizaOS (agent framework) — Contributions
    PRs: #2869 · #2784

  • Tetris AI — Genetic algorithms + Markov-chain learning for gameplay
    Repo: https://github.com/mmarfinetz/Tetris


Languages

Python TypeScript SQL

Tech Stack

Blockchain

Ethereum Arbitrum Hardhat Ethers.js web3.js Flashbots

ML / AI

PyTorch TensorFlow Hugging Face pandas NumPy

Web

React Next.js

Infra / Deploy

Docker GitHub Actions Railway Vercel


Contact

Email: mitchmar@sas.upenn.edu · GitHub: https://github.com/mmarfinetz · X/Twitter: https://twitter.com/mmarfinetz7 · Telegram: https://t.me/mitch0x

Pinned Loading

  1. yyGlobeTrotter/VinRouge yyGlobeTrotter/VinRouge Public template

    This is a hackathon project done at ETHDenver 2025

    Python 2 2

  2. DexStudy DexStudy Public

    Jupyter Notebook

  3. Alpha-Router Alpha-Router Public

    TypeScript 2 2

  4. Tetris Tetris Public

    HTML

  5. polymarketdata polymarketdata Public

    fetch top 50 events + market from polymarket

    TypeScript 4

  6. elizaos-plugins/plugin-arbitrage elizaos-plugins/plugin-arbitrage Public

    Identifies and executes cryptocurrency arbitrage opportunities across multiple exchanges.

    TypeScript 5 2