Victor Faraggi

M.Sc. in Computer Science

My thesis explores state-of-the-art neural network pruning techniques, empirically examining how pruned models converge to various theoretical bounds within controlled environments. Additionally, I assessed the performance and efficiency of these pruned networks in comparison to their fully dense counterparts.
Funded by the Millennium Institute Foundational Research on Data Science (IMFD) and National Center Artificial Intelligence (CENIA).
Department of Computer Science, Universidad de Chile Santiago, Chile

Computer Science Engineering

Department of Computer Science, Universidad de Chile Santiago, Chile

Computer Science Exchange Student

Faculty of Arts & Sciences, University of Toronto Toronto, Canada

B.Sc. in Computer Science

Faculty of Physical & Mathematical Sciences, Universidad de Chile Santiago, Chile

Machine Learning Engineer

Built the first version of the NLP pipelines for automated report generation using LLMs, parsing structured and unstructured data from diverse sources (administrative, legal, operational). Implemented custom evaluation metrics and sophisticated prompt engineering, directly applicable to NLP model evaluation frameworks.
Final version not available. Technologies: Python, Vector DBs, LangChain, Hugging Face Transformers, Pydantic, OpenAI API. PSINET Santiago, Chile

Machine Learning Engineer Intern

Developed and evaluated embedding-based protein language models applied to bioinformatics, providing baseline benchmarks to guide further model improvements.
Technologies: PyTorch, Protein-specific LLMs, Model Evaluation. Protera Santiago, Chile

Teaching Assistant

Courses: Information Theory & Application (Electrical Eng. Dept.), Deep Learning, Data Mining, Algorithm Design and Analysis (CS Dept.), Machine Learning (Mathematical Eng. Dept.), Computing Tools for Engineering, Experimental Methods (Physics Dept.), Programming I (CS Dept.)
Faculty of Physical & Mathematical Sciences, Universidad de Chile Santiago, Chile

IT Student Director

Organized a four man team that was tasked with maintaining and developing different technological solutions for a 50+ student organization. Coordinated and evaluated the work of my team with the ongoing needs of the whole organization.
Redes Beauchef, Student Organization Santiago, Chile

Data Engineer

Analyzed satellite, oceanographic and industrial data in order to detect, prevent harmful algal blooms. Obtained, processed and stored data from different sources to build a recommendation system for mining companies to improve the efficiency of their desalination plants. Data was stored in GCS and processed using BigQuery.
BloomAlert, Startup Santiago, Chile

Data Science Intern

Built an analytics dashboard that presented analytics for the HR team of a major telecom in South America. Connected more than 10 different internal data-sources.
Worldalytics, Analytics & Data ScienceSantiago, Chile

Understanding Encoder-Decoder Structures in Machine Learning Using Information Measures [Submitted and in Review]

Linked information-theoretical concepts to understand effects of encoder-decoder structures in ML architectures. By decomposing the effects of encoder and decoder in a separate manner, we provided theoretical bounds to the performance of models in terms of information measures.
I specifically led the efforts into empirically proving the theoretical results.
 U. Chile

Understanding Encoder-Decoder Structures in Machine Learning Using Information Measures [Accepted in Elsevier Signal Processing Journal]

Developed an information-theoretic analysis of encoder-decoder structures common in NLP and deep learning. Provided theoretical performance bounds based on information measures, contributing insights directly applicable to large-scale NLP models evaluation.
Led empirical validation of theoretical models, relevant for designing robust NLP and deep learning evaluation methods. First version of the paper was accepted in the 2024 IEEE Machine Learning for Signal Processing Workshop where I was the first author. Jorge Silva, Victor Faraggi, et al. Universidad de Chile

Improving Deep Learning Prediction of Cyclone Wind Speeds with Neural ODEs

Applied Neural ODEs to model the Gradient Wind Balance equation, which is used to estimate wind speeds in tropical cyclones.
Victor Faraggi, Gary Tom, Selden Lin  U. Toronto

Investigating Climate Downscaling with Generative Super Resolution methods

Worked on the application of generative models to downscaling problems in climate science. We performed an overview of the differences between different models. In particular, we studied the difficulties in training and the transferability of established super-resolution models.
Victor Faraggi, Dhananjay Ashok, Aparna Gopalakrishnan  U. Toronto

ProjectX 2020: Machine Learning Research Competition: Climate Change

Represented U.Chile in a three-month-long ML research competition, hosted by U.Toronto. The focus of our research went into studying and developing models that could be used for landslide's early warning systems. I particularly worked on data processing and model development. Mentored by three professors: Felipe Tobar (U.Chile), Jorge Perez (U.Chile) and Apurva Narayan(U. Vancouver)
Victor Faraggi, Tomas Rojas, Jose Diaz, Francisco Munoz, Kevin Pinochet, Fabian Lema  Remote

WiFI Hacking Workshop [Presentation]

Attacks on WPS, WEP, WPA/2 and how to mitigate them. Chosen from around 100 submissions.
Victor Faraggi, Philippe Delteil, Ilana Mergudich  Defcon 27, Las Vegas