About

I am a third year PhD candidate at Mila and DIRO under the supervision of Simon Lacoste-Julien.

I develop constrained learning algorithms for training neural networks, which enable enforcing requirements such as fairness, sparsity and safety in LLMs.

My research aims to ensure that training models with constraints is as easy as training without them.

Check Cooper out, our library for non-convex constrained optimization in PyTorch.

Previously, I was an intern in Simon's group at Mila under the supervision of Jose Gallego-Posada. Before that, I completed a BSc in Mathematical Engineer at Universidad EAFIT. During the BSc, I spent a summer at McKinsey & Co. as a research intern.

Research interests: Non-convex Constrained Optimization, Min-Max Optimization, Machine Unlearning, Sparsity, Fairness.

Contact: juan43ramirez (at) gmail (dot) com


News

2025

  • Apr 1: We just released version 1.0.0 of Cooper, a PyTorch library for non-convex constrained optimization, along with a companion paper.

  • Jan 22: Our latest paper Feasible Learning has been accepted at AISTATS 2025! Feasible Learning is a novel sample-centric learning paradigm where models are trained by solving a feasibility problem that bounds the loss for each training sample.

  • Jan 1: Elated to server as Associate co-Chair for ICML 2025.

2024

Previous

2023

2022

2021

2020 and beyond

  • Jul 2020: Jose Gallego-Posada, PhD student at Mila will be my supervisor for my undergraduate thesis. I will be working on deep generative models.

  • Jun 2019: Now part of McKinsey & Co. in Belgium as a research intern. Working with Antoine Stevens and Patrick Dehout in ML for the agricultural and chemical industries.

  • Jan 2019: Arrived in Louvain-la-Neuve, Belgium for an exchange semestrer at Université Catholique de Louvain.

  • Nov 2017: I have been appointed as president of CIGMA-OE, the Mathematical Engineering chapter of the Student Organization at Universidad EAFIT.

  • Dec 2015: I was awarded a full scholarship for the Bachelor's degree in Mathematical Engineering at Universidad EAFIT.

  • Dec 2015: Scored amongst the best 0.1% on the Colombian high school examination ICFES.

  • Dec 2015: Ranked first in the National Chemistry Olympiads of Universidad de Antioquia.


Publications

Preprints

  1. J. Gallego-Posada*, Juan Ramirez*, M. Hashemizadeh* and S. Lacoste-Julien. Cooper: A Library for Constrained Optimization in Deep Learning. arXiv preprint at arXiv:2504.01212, 2025.

Conference

  1. Juan Ramirez*, I. Hounie*, J. Elenter*, J. Gallego-Posada*, M. Hashemizadeh, A. Ribeiro^ and S. Lacoste-Julien^. Feasible Learning. In AISTATS, 2025.

  2. M. Sohrabi*, Juan Ramirez*, T. H. Zhang, S. Lacoste-Julien and J. Gallego-Posada. On PI Controllers for Updating Lagrange Multipliers in Constrained Optimization. In ICML, 2024.

  3. M. Hashemizadeh*, Juan Ramirez*, R. Sukumaran, G. Farnadi, S. Lacoste-Julien and J. Gallego-Posada. Balancing Act: Constraining Disparate Impact in Sparse Models. In ICLR, 2024.

  4. J. Gallego-Posada, Juan Ramirez, A. Erraqabi, Y. Bengio and S. Lacoste-Julien. Controlled Sparsity via Constrained Optimization or: How I Learned to Stop Tuning Penalties and Love Constraints. In NeurIPS, 2022.

Workshop

  1. Juan Ramirez, R. Sukumaran, Q. Bertrand and G. Gidel. Omega: Optimistic EMA Gradients. LatinX in AI workshop at ICML, 2023.

  2. Juan Ramirez and J. Gallego-Posada. L0onie: Compressing COINs with L0-constraints. Sparsity in Neural Networks Workshop, 2022.

  3. J. Gallego-Posada, Juan Ramirez and A. Erraqabi. Flexible Learning of Sparse Neural Networks via Constrained L0 Regularization. LatinX in AI Workshop at NeurIPS, 2021.



Service


Juan Ramirez © - Last updated on