Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings
@pablo-reyes8
pablo-reyes8
Follow

Pablo Reyes pablo-reyes8

🗣️
Economist🎓→Data Scientist🧠 | ML⚙️·Bayesian Econometrics📊·Time-Series🔄 → valuable data insights

Block or report pablo-reyes8

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
pablo-reyes8 /README.md

Hey 👋, I’m Pablo Reyes

Economist & Data Scientist | PyTorch-first · Bayesian inference · Reproducible, paper-faithful ML builds

LinkedIn badge Email badge CV badge



👨‍💻 About Me

Economist & Data Scientist focused on modern deep learning and Bayesian macro/time series.
I build reproducible, paper-faithful ML systems and apply them to policy-relevant problems.


✨ Highlights

  • Reproducible PyTorch research builds: diffusion, ViTs, Transformers.
  • Bayesian macro & time series: DSGE / SBVAR / SGDLM with posterior inference (IRFs/FEVD) + robustness checks.
  • Econometrics ×ばつ Deep Learning: representation learning with uncertainty + identification for policy-relevant interpretation.
  • Research tooling mindset: clean modular code, configs, and reproducible scripts.

🔎 Research Profile

  • Focus: Bayesian macro/time series (DSGE, SBVAR, SGDLM) and modern deep learning (diffusion, ViTs, Transformers).
  • Current: Research assistant at Banco de la República (Colombia) — monetary policy, causal inference, and financial system analysis.
  • Approach: PyTorch-first · reproducible experiments · paper-faithful implementations · uncertainty-aware analysis.
  • Open to: Collaborations in Bayesian time series / macro-finance, generative modeling, and vision transformers.
  • CV: Download resume
Pablo Reyes — Research Profile

🧭 Featured Research Projects

Bayesian macro/time-series + modern deep learning (generative, vision, LLMs). Reproducible pipelines, clean implementations, and paper-style reporting.

PyDSGEforge bayesian-sgdlm ddpm-diffusion-model

multiscale-vision-transformers implementing-gpt bayesian-structural-var

All Repositories followers total stars


📌 Featured Projects (quick view)

Project One-liner Evidence
PyDSGEforge Full-Python DSGE workflow: state-space, solution, and inference. Reproducible examples + end-to-end scripts (solve → filter → estimate).
Bayesian SGDLM Bayesian dynamic networks for high-dimensional time series. Posterior simulation + sparse dependency learning demos.
DDPM Diffusion Diffusion models with clean training + sampling. Training + DDIM sampling scripts, denoising strips, checkpoints.
Multiscale ViTs Unified benchmark of modern ViT families. Shared pipeline, results table, ablations-ready structure.
implementing-gpt From-scratch GPT training stack. Tokenizer + training/eval scripts, reproducible configs.
Bayesian Structural VAR SBVAR with posterior IRFs/FEVD and identification. IRF/FEVD from posterior draws + stored results.

🛠️ Tools & Technologies

Python RStudio Stata SQL Jupyter GitHub LaTeX
PyTorch TensorFlow scikit-learn PyMC JAX Power BI
Hugging Face spaCy Word2Vec NLTK Pandas NumPy Matplotlib


📊 GitHub Stats


"Building reproducible ML + Bayesian tooling for scientific inference."

Pinned Loading

  1. a2k-style-transfer a2k-style-transfer Public

    StyleTransfer a reproducible pipeline for neural style transfer: attention-driven fusion, perceptual decoding, Hugging Face data tooling, config-based CLIs, Dockerized environments, and tests so te...

    Python 1

  2. pytorch-cnn-architectures pytorch-cnn-architectures Public

    Implementation of iconic convolutional neural networks — LeNet-5, AlexNet, ResNet, U-Net, and Inception — built from scratch using PyTorch. Each model includes custom training loops, evaluation uti...

    Python 3

  3. pytorch-gans pytorch-gans Public

    A collection of GANs in PyTorch, from simple baselines to modern stabilized variants, built for learning and experimentation.

    Python 2

  4. yolov2-implementation yolov2-implementation Public

    A modular YOLOv2 implementation in PyTorch with the Darknet-19 backbone. Includes dataset handling (VOC), letterbox preprocessing, training loop, custom loss, decoding, NMS, and VOC07 mAP evaluatio...

    Python 1

  5. bayesian-var bayesian-var Public

    Standard Bayesian VAR with conjugate priors and Minnesota dummy-observation priors (unit-root and cointegration dummies) for analyzing shock transmission between U.S. 5-year and 3-year T-Bills and ...

    Jupyter Notebook 4 1

  6. inflation-forecasting-arima-lstm inflation-forecasting-arima-lstm Public

    Inflation forecasting pipeline combining ARIMA diagnostics in Stata with LSTM tuning in Python, featuring dynamic forecasts and evaluation metrics (MSE, MAE, R2).

    Jupyter Notebook 3

AltStyle によって変換されたページ (->オリジナル) /