> I'm a 3rd year Ph.D. student at the University of Pennsylvania, where I mostly think about constrained optimization, foundation models and continual learning with Alejandro Ribeiro. This summer I will intern at Paul Bennett's Spotify ML Research team in NYC.
Before graduate school I worked on genomic motif discovery through ATAC-seq analysis with Anshul Kundaje at Stanford's Kundaje-Lab. I also interned at CERN, contributing to the CMS Open Data initiative with Dr. Lassila-Perini.
I hold an MA in Statistics and Data Science from The Wharton School , and I'm originally from the beautiful city of Montevideo, Uruguay, where I obtained a BSc. in Electrical Engineering from UdelaR. During my undergrad, I was a software developer at IBM . If any of this sparks your interest, or if you want share some Mate, feel free to reach out.
On the theory side, I work on duality-based constrained optimization, which is particularly relevant in the context of large model fine tuning. This endeavour is about obtaining models that not only excel at a main task, but also adhere to requirements such as safety, invariance, robustness and fairness. For instance, my last paper shows that, in many learning problems, dual subgradient methods yield near-optimal and near-feasible solutions, without randomization, despite non-convexity.
On the applications side, I have delved into data-centric ML and explored the following questions:
- What area of the sample space should I explore next so that my model improves the most with the lowest labelling cost ?
- How should I continuously finetune my model as new data, with different properties, gets collected ?
These interrogations have led to works on active and continual learning.
I have a particular interest in problems involving biological signals such as Genome Sequences , Medical Images and the Gut Microbiome.
Near-Optimal Solutions of Constrained Learning Problems.
Juan Elenter, Luiz Chamon, Alejandro Ribeiro
International Conference on Learning Representations (ICLR), 2024
Primal Dual Continual Learning: Balancing Stability and Plasticity through Adaptive Memory Allocation
Juan Elenter, Navid NaderiAlizadeh, Tara Javidi, Alejandro Ribeiro
Preprint Under Review
A Lagrangian Duality Approach to Active Learning
Juan Elenter, Navid NaderiAlizadeh, Alejandro Ribeiro
Neural Information Processing Systems (NeurIPS), 2022.
Neural Networks with Quantization Constraints.
Ignacio Hounie*, Juan Elenter*, Alejandro Ribeiro
IEEE International Conference on Acoustics, Speech, and Signal Processing, 2023.
Graph Neural Networks for genome enabled prediction of complex traits.
Juan Elenter, Ignacio Hounie, Guillermo Etchebarne, María Inés Fariello, Federico Lecumberry
Probabilistic Modeling in Genomics, CSHL, 2021.
Some stuff I like about Uruguay.
Water is my natural environment.