Tal Shnitzer

I am a senior machine learning scientist at the Machine Learning for Health (ML4H) group at the Broad Institute. Before joining the Broad, I was a postdoctoral researcher at CSAIL MIT in the Geometric Data Processing Group with Prof. Justin Solomon. I received my PhD in 2020 from the faculty of Electrical and Computer Engineering at the Technion, under the supervision of Prof. Ronen Talmon.

My research focuses on developing and applying machine learning methods to large-scale biomedical data, with a particular focus on disease risk prediction using wearable sensors, electronic health records, and clinical imaging. I work closely with clinicians, researchers, and engineers to design rigorous studies, build reproducible analytical pipelines, and assess whether advanced models provide meaningful value beyond established clinical predictors.

My earlier research focused on manifold learning and geometric methods for multimodal and temporal data analysis.

Research interests: Clinical ML, digital health, wearable sensing, disease risk prediction, multimodal biomedical data, and geometric machine learning.

Email / CV / Google Scholar / Github

Selected Publications

	Few-Sample Feature Selection via Feature Manifold Learning David Cohen, Tal Shnitzer, Yuval Kluger, Ronen Talmon ICML, 2023 arXiv / paper / code
	Log-Euclidean signatures for intrinsic distances between unaligned datasets Tal Shnitzer, Mikhail Yurochkin, Kristjan Greenewald, Justin Solomon ICML, 2022 arXiv / paper / code

Clinical ML and Digital Health Publications

Geometric Machine Learning and Manifold Methods Publications

	Spatiotemporal analysis using riemannian composition of diffusion operators Tal Shnitzer, Hau-Tieng Wu, Ronen Talmon ACHA Elsevier, 2023 arXiv / code
	Graph of graphs analysis for multiplexed data with application to imaging mass cytometry Ya-Wei Lin, Tal Shnitzer, Ronen Talmon, Franz Villarroel-Espindola, Shruti Desai, Kurt Schalper, Yuval Kluger PLoS computational biology, 2021 bioRXiv / paper / code
	Diffusion maps kalman filter for a class of systems with gradient flows Tal Shnitzer, Ronen Talmon, Jean-Jacques Slotine IEEE TSP, 2020 arXiv / paper / code
	Layer- and cell-specific recruitment dynamics during epileptic seizures in vivo Fadi Aeed Tal Shnitzer, Ronen Talmon, Yitzhak Schiller Annals of Neurology, 2019 paper / code
	Diffusion maps particle filter Lukas Forster, Alexander Schmidt, Walter Kellermann, Tal Shnitzer, Ronen Talmon Eusipco, 2019 arXiv / paper
	Recovering hidden components in multimodal data with composite diffusion operators Tal Shnitzer, Mirela Ben-Chen, Leonidas Guibas, Ronen Talmon, Hau-Tieng Wu SIAM Journal on Mathematics of Data Science, 2019 arXiv / paper / code
	Alternating diffusion maps for dementia severity assessment Tal Shnitzer, Maya Rapaport, Noga Cohen, Natalya Yarovinsky, Ronen Talmon, Judith Aharon-Peretz ICASSP, 2017 arXiv / paper
	Direction modulation of muscle synergies in a hand-reaching task Sharon Israely, Gerry Leisman, Chay Machluf, Tal Shnitzer, Eli Carmeli IEEE TNSRE, 2017 arXiv / paper
	Manifold learning with contracting observers for data-driven time-series analysis Tal Shnitzer, Ronen Talmon, Jean-Jacques Slotine IEEE TSP, 2016 arXiv / paper / code

Book Chapters

	Manifold learning for data-driven dynamical system analysis Tal Shnitzer, Ronen Talmon, Jean-Jacques Slotine The Koopman Operator in Systems and Control, 2020 chapter / code
	Diffusion operators for multimodal data analysis Tal Shnitzer, Roy Lederman, Gi-Ren Liu, Ronen Talmon, Hau-Tieng Wu Handbook of Numerical Analysis v20, 2019 chapter

This website is based on Jon Barron's template (source code)