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, a library for nonconvex constrained optimization in PyTorch that I co-founded.

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: Nonconvex Constrained Optimization, Min-Max Optimization, Deep Learning, Sparsity, Fairness.

Contact: juan43ramirez (at) gmail (dot) com


News

2024

2023

Previous

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 the 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. Unfortunately, I did not obtain an Andrés Bello prize.

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


Publications

Conference

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

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

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

Workshop

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

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

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


Libraries

  1. Cooper: Constrained Optimization for Deep Learning. J. Gallego-Posada*, Juan Ramirez*, M. Hashemizadeh and Simon Lacoste-Julien. Computer software, 2024.



Service


Juan Ramirez © - Last updated on