I received my PhD Industrial Engineering & Management Sciences at Northwestern University. My research focuses on adaptive experimental design, applied machine learning, Gaussian processes, and uncertainty quantification.

Linkedin: https://www.linkedin.com/in/suraj-yerramilli/

Kaggle: https://www.kaggle.com/syerramilli/code

Google Scholar: https://scholar.google.com/citations?user=rIDtPLcAAAAJ&hl=en

Gists: https://gist.github.com/syerramilli

1. fcvopt: FCVOpt is a Python package for "Fractional Cross-Validation"in hyperparameter optimization. It implements efficient hyperparameter tuning by evaluating only a fraction of cross-validation folds using hierarchical Gaussian processes. Related publication: https://doi.org/10.1080/00401706.2025.2515926
2. lvgp-bayes: A python library for estimating latent variable Gaussian process regression models using either point estimation or fully Bayesian (i.e. MCMC) methods. Related publication: https://doi.org/10.1137/22M1525600
3. sysid: An R library for system-identification. The library contains routines for input design, simulation and standard estimation methods for understanding the subject of and developing data-driven models for linear-time invariant (LTI) systems. Related publication: https://doi.org/10.1109/INDIANCC.2017.7846451
4. gp-bo: A python library for Bayesian optimization (BO) using Gaussian process as the surrogate model, built on top of BoTorch. While BoTorch has functions and classes for implementing BO, this library contains settings and models that I found to be useful in practice and in my research. The library can also be used with Optuna. See https://www.kaggle.com/code/syerramilli/ps3e11-catboost-bayesopt for an example.

1. LSTMs for Hangman game: LSTM based approach for guessing the letters in the classic Hangman game.
2. Shiny apps: Repository containing R shiny apps that I developed for showcasing various visualization aspects
3. BNN project: Course project for evaluating several scalable approaches for Bayesian Neural Networks in terms of prediction accuracy, uncertainty quantification, and computation time.

1. msia420-w2023-lab: Python labs for the Winter 2023 iteration of MSIA 420 Predictive Analytics II
2. iems308-lab: Python tutorial for the Winter 2019 iteration of IEMS 308 Data Science & Analytics
3. Scrapy tutorial: Web scraping tutorial prepared for the Spring 2023 iteration of DATA_ENG 300 Data Engineering Studio

1. Kaggle notebooks: A collection of (mostly Python) notebooks run on the Kaggle platform.