Ignacio Hounie
Ph.D. Candidate
University of Pennsylvania
ihounie [AT] seas.upenn.edu
Bio
I'm a 4th year Ph.D. student at the University of Pennsylvania, advised by Prof. Ribeiro. I am broadly interested in machine learning, signal processing and optimization. The focus of my current research is on adapting pre-trained generative models under constraints. I leverage tools from my previous work on constrined learning during the first years of my PhD. In this line of work I have tackled problems ranging from invariance and data augmentation to model quantization and federated learning.
I earned my BSc. in Electrical Engineering from Udelar in Montevideo, Uruguay, which is my hometown. During my time there, I worked on various ML aplications including environmental sound monitoring, image restoration, and genome enabled prediction. I interned at Amazon in the summer of 2024, where I applied my skills in order to tackle challenges in large scale classification systems under distribution shift.
Publications
Full list of publications on Google Scholar.
A word cloud representation of my most recent publications, for aesthetic purposes only.
LoRTA: Low Rank Tensor Adaptation of Large Language Models
Ignacio Hounie, Charilaos Kanatsoulis, Arnuv Tandon, Alejandro Ribeiro
Under review.
Loss Shaping Constraints for Long-Term Time Series Forecasting
Ignacio Hounie, Javier Porras-Valenzuela, Alejandro Ribeiro
ICML 2024.
Resilient Constrained Learning
Ignacio Hounie, Alejandro Ribeiro, Luiz F. O. Chamon
NeuRIPS 2023.
Automatic Data Augmentation via Invariance Constrained Learning
Ignacio Hounie, Luiz F. O. Chamon, Alejandro Ribeiro
ICML 2023.
Neural Networks with Quantization Constraints
Ignacio Hounie, Juan Elenter, Alejandro Ribeiro
ICASSP 2023.
Image inpainting using patch consensus and DCT priors.
Ignacio Ramírez Paulino, Ignacio Hounie
Image Processing On Line 2021.
DCASE-models: a Python library for computational environmental sound analysis using deep-learning models
Pablo Zinemanas, Ignacio Hounie, Pablo Cancela, Frederic Font Corbera, Martín Rocamora, Xavier Serra
DCASE 2020.
Graph Neural Networks for genome enabled prediction of complex traits.
Ignacio Hounie, Juan Elenter, Guillermo Etchebarne, María Inés Fariello, Federico Lecumberry
Probabilistic Modeling in Genomics 2021.
LoRTA: Low Rank Tensor Adaptation of Large Language Models
Ignacio Hounie, Charilaos Kanatsoulis, Arnuv Tandon, Alejandro Ribeiro
Under review.
Loss Shaping Constraints for Long-Term Time Series Forecasting
Ignacio Hounie, Javier Porras-Valenzuela, Alejandro Ribeiro
ICML 2024.
Resilient Constrained Learning
Ignacio Hounie, Alejandro Ribeiro, Luiz F. O. Chamon
NeuRIPS 2023.
Automatic Data Augmentation via Invariance Constrained Learning
Ignacio Hounie, Luiz F. O. Chamon, Alejandro Ribeiro
ICML 2023.
Neural Networks with Quantization Constraints
Ignacio Hounie, Juan Elenter, Alejandro Ribeiro
ICASSP 2023.
Image inpainting using patch consensus and DCT priors.
Ignacio Ramírez Paulino, Ignacio Hounie
Image Processing On Line 2021.
DCASE-models: a Python library for computational environmental sound analysis using deep-learning models
Pablo Zinemanas, Ignacio Hounie, Pablo Cancela, Frederic Font Corbera, Martín Rocamora, Xavier Serra
DCASE 2020.
Paco and paco-dct: Patch consensus and its application to inpainting
Ignacio Ramírez Paulino, Ignacio Hounie
ICASSP 2020.
Something old, something new, something borrowed: Evaluation of different neural network architectures for genomic prediction.
Maria Inés Fariello, Lucía Arboleya, Diego Belzarena, Leonardo De Los Santos, Juan Elenter, Guillermo Etchebarne, Ignacio Hounie, Gabriel Ciappesoni, Elly Navajas, Federico Lecumberry
Plant & Animal Genome Conference 2023
Graph Neural Networks for genome enabled prediction of complex traits.
Ignacio Hounie, Juan Elenter, Guillermo Etchebarne, María Inés Fariello, Federico Lecumberry
Probabilistic Modeling in Genomics 2021.
On two dimensional mappings of SNP marker data and CNNs: Overcoming the limitations of existing methods using Fermat distance.
Juan Elenter, Guillermo Etchebarne, Ignacio Hounie, María Inés Fariello, Federico Lecumberry
Probabilistic Modeling in Genomics 2021.
Vitæ
Full Resume in PDF.