I am a Ph.D. student at the Silverman Lab in the College of Information Sciences and Technology at Pennsylvania State University, advised by Dr. Justin Silverman. My research focuses on developing robust machine learning models using ideas from Bayesian inference and causal learning, with a current emphasis on understanding omitted variable bias in predictive models. Previously, I worked on scalable Bayesian time series models for multivariate count data, commonly encountered in microbiome studies and econometrics.

Most recently, I completed a Data Science internship at Hartford Steam Boiler (Munich Re) as part of the Data Science Insurance Team, under the mentorship of Dr. Yue Tang. There, I developed predictive models for claim severity by combining probabilistic and machine learning approaches, leveraging features extracted from unstructured claim notes using large language models.

Before my doctoral studies, I worked as a Software Engineer at Tummee.com, focusing on end-to-end software development and user experience optimization. Earlier, I was a Machine Learning Researcher at Trinity College Dublin, where I collaborated with Dr. Ciaran Simms, Dr. Aljosa Smolic, and Dr. Richard Blythman on deep learning models and automated pipelines for predictive analytics and sports injury prevention.

I hold a master’s degree in Informatics (Data Science) from Pennsylvania State University and a bachelor’s degree in Software Engineering from Delhi Technological University (formerly Delhi College of Engineering), India.

My CV can be found here.

Talks

Causal Representation Learning (July 2025)
Data Science Team, Hartford Steam Boiler (Munich Re)

Scalable Inference for Bayesian Multinomial Logistic-Normal Dynamic Linear Model (Oct 2024)
Bioinformatics Method Developers Community Day, Center for Computational Biology and Bioinformatics, Pennsylvania State University

Teaching

• Applied Data Sciences (DS340W)
• Legal and Regulatory Environment of Information Science and Technology (IST432)

Publications and Preprints

Scalable Inference for Bayesian Multinomial Logistic-Normal Dynamic Linear Models

Manan Saxena, Tinghua Chen, Justin D Silverman
Accepted in 28th International conference on artificial intelligence and statistics (AISTATS 2025).
[ArXiv, Fenrir code, Paper Code]

Assessment of deep learning pose estimates for sports collision tracking

Richard Blythman, Manan Saxena, Gregory J Tierney, Chris Richter, Aljosa Smolic, Ciaran Simms
Journal of sports sciences (2022)
[Paper]

Classifying Medical Histology Images Using Computationally Efficient CNNs Through Distilling Knowledge

Aakash Garg*, Karan Aggarwal*, Manan Saxena*, Aruna Bhat
Proceedings of International conference on emerging technologies in data mining and information security, Springer (IEMIS 2020)
[Paper]

Skeleton-based view invariant deep features for human activity recognition

Chhavi Dhiman, Manan Saxena, Dinesh Kumar Vishwakarma
Proceedings of IEEE 5th international conference on multimedia big data (IEEE BigMM 2019)
[Paper]