Skip to content
View nicomele1's full-sized avatar
3 followers · 12 following

Block or report nicomele1

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 is supported. This note will only be visible to you.
Report abuse

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

Report abuse
nicomele1/README.md

Hi, I'm Nicolás Meléndez, a mathematics student at Universidad de los Andes in Bogotá.

My main mathematical interest is spectral theory. I'm currently studying Sturm-Liouville operators and working on a formal verification of the spectral theorem in Lean 4.

I also spend a lot of time with the mathematical and computational foundations of machine learning, with a particular focus on large language models. My interests include probabilistic modeling, empirical risk minimization, stochastic optimization, transformer architectures, and implementing small-scale models from scratch.

On the technical side, I work with Python for scientific computing and machine learning, especially NumPy, SciPy, PyTorch, and scikit-learn. I also use R, SQL, and some Rust. I enjoy Linux, Bash, and anything close to the system.

Spanish native, fluent in English, getting by in German. Feel free to reach out at nicolasmelendez30@gmail.com

Popular repositories Loading

  1. trafico-chapinero trafico-chapinero Public

    Traffic modeling, Wardrop equilibria and optimization in Chapinero.

    Jupyter Notebook

  2. spectral-thm-lean spectral-thm-lean Public

    We carry out a complete formalization of the spectral theorem in Lean, for both bounded and unbounded linear operators over some Hilbert space H.

    Lean

  3. nicomele1 nicomele1 Public

  4. nicolas-lm nicolas-lm Public

    nicolas-lm is a small research-oriented language modeling lab. It focuses on character-level autoregressive models and on the tools needed to train, evaluate, and analyze them in a controlled setting.

    TeX