Juan Elenter

Ph.D. Candidate
University of Pennsylvania

elenter [AT] seas.upenn.edu

Bio

> 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.

My work

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

Paper

Primal Dual Continual Learning: Balancing Stability and Plasticity through Adaptive Memory Allocation

Juan Elenter, Navid NaderiAlizadeh, Tara Javidi, Alejandro Ribeiro

Preprint Under Review

Paper

A Lagrangian Duality Approach to Active Learning

Juan Elenter, Navid NaderiAlizadeh, Alejandro Ribeiro

Neural Information Processing Systems (NeurIPS), 2022.

Paper Code

Neural Networks with Quantization Constraints.

Ignacio Hounie*, Juan Elenter*, Alejandro Ribeiro

IEEE International Conference on Acoustics, Speech, and Signal Processing, 2023.

Paper Code

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.

Paper

Projects

ATAC-seq analysis and motif discovery
@ Stanford, KundajeLab
Undergrad Capstone Project: Prediction of complex traits in agriculture.
@ UdelaR, FarielBerry Lab
I find this case very confusing, and have not thoroughly checked the result. R.A.Fisher
CMS Open Data Initiative
@ CERN, CMS

Vitæ

  • Spotify 2024
    Research Scientist Intern
  • Flatiron Institute @ Simons Foundation 2022

    Computational Mathematics Intern
  • University of Pennsylvania Fall 2021 - now
    Ph.D. Candidate
    Machine Learning, Optimization, Signal Processing,
  • Stanford University Spring 2021
    Visiting Student at KundajeLab
    ATAC-seq analysis, motif discovery
  • CERN 2020
    Intern
    Compact Muon Solenoid
  • IBM 2018-2019
    Full Stack Developer
  • ProteanTecs Summer 2019
    Signal Processing Intern
    Chip Predictive Maintenance
  • Universidad de la República 2016-2021
    Bsc. Electrical Engineering
    Signal Processing

Miscelaneous

  • Uruguay
  • Water

Some stuff I like about Uruguay.

Mate: 1/2 Moncayo + 1/2 Baldo
My only real conversation is with this green gourd. Julio Cortázar
The uruguayan
We're kind of chill, obsessed with soccer, skeptical of authority and fixated on social welfare.
La Negra Tomasa
The best pizza in Uruguay, provably.
Jorge Drexler
No le hagas caso a tanto misterio
vos ya sabés la verdad
que no hay nada peor para esta seriedad
que tomársela en serio.
Asado
Typical sunday meal at family gatherings.
Murga
Asaltantes Con Patentes 2013

Water is my natural environment.


Involuntarily drinking water in Punta Ballena.

Glassy morning in one of my favourite uruguayan spots.

Involuntarily drinking frozen, cristalyzed water.

West Santa Lucia River by the way.

Me and my uncle Ernesto, with whom I crossed the Atlantic in 2016.

In 2013, while playing for Uruguay's U-17 national team I lost 3-23 to the US.
The blueprint for this website can be found in this GitHub repo. Feel free to use it.
``
Juan Elenter
elenter [AT] seas.upenn.edu