image 1

Shahar Kovalsky

I am an Assistant Professor of Mathematics at the University of North Carolina at Chapel Hill.
I am a member of the Carolina Center for Interdisciplinary Applied Mathematics (CCIAM).

Previously, I was a Phillip Griffiths Assistant Research Professor at the Department of Mathematics of Duke University, where I worked with Prof. Ingrid Daubechies at the Rhodes Information Initiative at Duke (iID).

I completed my PhD under the supervision of Prof. Ronen Basri and Prof. Yaron Lipman at the Weizmann Institute of Science, Israel.

My research is in optimization, discrete computational geometry, computer graphics and vision, machine learning, and their applications in biology and medicine.

Email: shaharko (at) unc.edu
Address: 306 Phillips Hall, Chapel Hill, NC 27599

Publications

image 1

Deep-Learning–Based Screening and Ancillary Testing for Thyroid Cytopathology

David Dov, Danielle Elliott Range, Jonathan Cohen, Jonathan Bell, Daniel Rocke, Russel Kahmke, Ahuva Weiss-Meilik, Walter Lee, Ricardo Henao, Lawrence Carin and Shahar Kovalsky
The American Journal of Pathology 2023

Abstract Paper Paper (alt)
image 1

Thyroid Cytopathology Cancer Diagnosis from Smartphone Images Using Machine Learning

Serge Assaad, David Dov, Richard Davis, Shahar Kovalsky, Walter Lee, Russel Kahmke, Daniel Rocke, Jonathan Cohen, Ricardo Henao, Lawrence Carin and Danielle Elliott Range
Modern Pathology 2023

Abstract Paper Paper (alt)
image 1

Isometric Energies for Recovering Injectivity in Constrained Mapping

Xingyi Du, Danny M. Kaufman, Qingnan Zhou, Shahar Kovalsky, Yajie Yan, Noam Aigerman and Tao Ju
ACM Transactions on Graphics (SIGGRAPH Asia) 2022

Abstract Paper Project
image 1

Neural Network Approximation of Refinable Functions

Ingrid Daubechies, Ronald DeVore, Nadav Dym, Shira Faigenbaum-Golovin, Shahar Kovalsky, Kung-Ching Lin, Josiah Park, Guergana Petrova and Barak Sober
IEEE Transactions on Information Theory 2022

Abstract Paper arXiv
image 1

Use of Machine Learning–Based Software for the Screening of Thyroid Cytopathology Whole Slide Images

David Dov, Shahar Kovalsky, Qizhang Feng, Serge Assaad, Jonathan Cohen, Jonathan Bell, Ricardo Henao, Lawrence Carin and Danielle Elliott Range
Archives of Pathology & Laboratory Medicine 2022

Abstract Paper
image 1

Optimizing Global Injectivity for Constrained Parameterization

Xingyi Du, Danny Kaufman, Qingnan Zhou, Shahar Kovalsky, Yajie Yan, Noam Aigerman and Tao Ju
ACM Transactions on Graphics (SIGGRAPH Asia) 2021

Abstract Paper Project Code
image 1

Detection and Classification of Neurons and Glial Cells in the MADM Mouse Brain using RetinaNet

Yuheng Cai, Xuying Zhang, Shahar Kovalsky, Troy Ghashghaei and Alon Greenbaum
Plos One 2021

Abstract Paper
image 1

Insights from Macroevolutionary Modelling and Ancestral State Reconstruction into the Radiation and Historical Dietary Ecology of Lemuriformes (Primates, Mammalia)

Ethan Fulwood, Shan Shan, Julia Winchester, Henry Kirveslahti, Robert Ravier, Shahar Kovalsky, Ingrid Daubechies and Doug Boyer
MBMC Ecology and Evolution 2021

Abstract Paper
image 1

Affinitention Nets: Kernel Perspective on Attention Architectures for Set Classification with Applications to Medical Text and Images

David Dov, Serge Assaad, Shijing Si, Rui Wang, Hongteng Xu, Shahar Kovalsky, Jonathan Bell, Danielle Elliott Range, Jonathan Cohen, Ricardo Henao and Lawrence Carin
Conference on Health, Inference, and Learning (CHIL) 2021

Abstract Paper
image 1

Weakly Supervised Instance Learning for Thyroid Malignancy Prediction from Whole Slide Cytopathology Images

David Dov, Shahar Kovalsky, Serge Assaad, Avani Pendse, Jonathan Cohen, Danielle Elliott Range, Ricardo Henao and Lawrence Carin
Medical Image Analysis 2021

Abstract Paper arXiv
image 1

Lifting Simplices to Find Injectivity

Xingyi Du, Noam Aigerman, Qingnan Zhou, Shahar Kovalsky, Yajie Yan, Danny M. Kaufman and Tao Ju
ACM SIGGRAPH 2020

Abstract PDF PDF (high res) Project Code Dataset
image 1

Non-Convex Planar Harmonic Maps

Shahar Kovalsky, Noam Aigerman, Ingrid Daubechies, Michael Kazhdan, Jianfeng Lu and Stefan Steinerberger
arXiv

Abstract arXiv
image 1

Application of a Machine Learning Algorithm to Predict Malignancy in Thyroid Cytopathology

Danielle Elliott Range, David Dov, Shahar Kovalsky, Ricardo Henao, Lawrence Carin and Jonathan Cohen
Cancer Cytopathology 2020

Abstract Paper Extended Abstract (ASC)
image 1

Linearly Converging Quasi Branch and Bound Algorithms for Global Rigid Registration

Nadav Dym and Shahar Kovalsky
International Conference on Computer Vision (ICCV) 2019
(* oral presentation)

Abstract Paper arXiv Code (GitHub)
image 1

Thyroid Cancer Malignancy Prediction From Whole Slide Cytopathology Images

David Dov, Shahar Kovalsky, Jonathan Cohen, Danielle Elliott Range, Ricardo Henao and Lawrence Carin
Machine Learning for Healthcare (MLHC) 2019

Abstract Paper arXiv
image 1

Gaussian Process Landmarking for Three-Dimensional Geometric Morphometrics

Tingran Gao, Shahar Kovalsky, Doug Boyer, and Ingrid Daubechies
SIAM Journal on Mathematics of Data Science 2019

Abstract Paper arXiv Code (GitHub)
image 1

Gaussian Process Landmarking on Manifolds

Tingran Gao, Shahar Kovalsky, and Ingrid Daubechies
SIAM Journal on Mathematics of Data Science 2019

Abstract Paper arXiv
image 1

ariaDNE: A Robustly Implemented Algorithm for Dirichlet Normal Energy

Shan Shan, Shahar Kovalsky, Julie Winchester, Doug Boyer and Ingrid Daubechies
Methods in Ecology and Evolution 2019

Abstract Paper Project Code (GitHub)
image 1

Geometric Optimization via Composite Majorization

Anna Shtengel, Roi Poranne, Olga Sorkine-Hornung, Shahar Kovalsky and Yaron Lipman
ACM SIGGRAPH 2017

Abstract PDF PDF (high res) Code (GitHub)
image 1

Spherical Orbifold Tutte Embeddings

Noam Aigerman, Shahar Kovalsky and Yaron Lipman
ACM SIGGRAPH 2017

Abstract PDF PDF (high res)
image 1

Accelerated Quadratic Proxy for Geometric Optimization

Shahar Kovalsky, Meirav Galun and Yaron Lipman
ACM SIGGRAPH 2016

Abstract PDF PDF (high res) Project (+code)
image 1

Point Registration via Efficient Convex Relaxation

Haggai Maron, Nadav Dym, Itay Kezurer, Shahar Kovalsky and Yaron Lipman
ACM SIGGRAPH 2016

Abstract PDF PDF (high res) Code (zip)
image 1

Learning 3D Deformation of Animals from 2D Images

Angjoo Kanazawa, Shahar Kovalsky, Ronen Basri and David Jacobs
Eurographics 2016 (Günter Enderle best paper award)

Abstract PDF Code (GitHub)
image 1

Large-Scale Bounded Distortion Mappings

Shahar Kovalsky, Noam Aigerman, Ronen Basri and Yaron Lipman
ACM SIGGRAPH Asia 2015

Abstract PDF PDF (high res) Project (+code) Slides
image 1

Identification of Structured LTI MIMO State-Space Models

Chengpu Yu, Michel Verhaegen, Shahar Kovalsky and Ronen Basri
IEEE Conference on Decision and Control (CDC) 2015

Abstract PDF
image 1

Tight Relaxation of Quadratic Matching

Itay Kezurer*, Shahar Kovalsky*, Ronen Basri and Yaron Lipman
Computer Graphics Forum (Proc. of SGP) 2015 (best paper award)
(* equal contributors)

Abstract PDF Slides
image 1

A Global Approach for Solving Edge-Matching Puzzles

Shahar Kovalsky, Daniel Glasner and Ronen Basri
SIAM J. Imaging Sciences, Vol. 8, Issue 2, 2015

Abstract PDF
image 1

Controlling Singular Values with Semidefinite Programming

Shahar Kovalsky*, Noam Aigerman*, Ronen Basri and Yaron Lipman
ACM SIGGRAPH 2014
(* equal contributors)

Abstract PDF PDF (high res) Project (+code) Slides
image 1

Global Motion Estimation from Point Matches

Mica Arie-Nachimson, Shahar Kovalsky, Ira Kemelmacher-Shlizerman, Amit Singer and Ronen Basri
3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT), 2012

Abstract PDF
image 1

Strongly Consistent Estimation of the Sample Distribution of Noisy Continuous-Parameter Fields

Shahar Kovalsky, Guy Cohen, and Joseph M. Francos
IEEE Transactions on Information Theory, 2011

Abstract PDF
image 1

Decoupled Linear Estimation of Affine Geometric Deformations and Non-Linear Intensity Transformations of Images

Shahar Kovalsky, Guy Cohen, Rami Hagege and Joseph M. Francos
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2010

Abstract PDF
image 1

Registration of Joint Geometric and Radiometric Image Deformations in the Presence of Noise

Shahar Kovalsky, Guy Cohen and Joseph M. Francos
IEEE Workshop on Statistical Signal Processing (SSP), 2007

Abstract PDF
image 1

Registration of Joint Geometric and Radiometric Image Deformations

Shahar Kovalsky, Rami Hagege and Joseph M. Francos
IASTED International Conference on Signal and Image Processing (SIP), 2007

Abstract PDF

Mentoring

Graduate Students

image 1

Fengyu Yang

image 1

Connor Magoon

image 1

Aaron Jacobson

Co-advised with Caroline Moosmüller

Undergraduate Students

image 1

Maddy Vinal

Co-advised with Jeremy Marzuola and Caroline Moosmüller

Teaching

image 1

Optimization with Application in Machine Learning

UNC-CH (MATH 590/560): SP21, SP22, SP23
Slides (email to request)
image 1

Linear Algebra for Applications

UNC-CH (MATH 347): FA22, SP23
Slides (email to request)
image 1

First Course in Differential Equations

UNC-CH (MATH 383): FA20
Slides (email to request)
image 1

Mathematics of Machine Learning

Duke (MATH 466): FA19
Website
image 1

Math Everywhere

Duke (MATH 181): SP18, SP19, SP20
Website
image 1

Minicourse: Convex Majorization with Applications

Duke (MATH 790-90): FA2017
Slides (email to request)

Others

image 1

Computational Aspects of Mappings

Tutorial given at the IGS 2016 summer school (with Noam Aigerman)
Slides (Powerpoint) Slides (PDF)
image 1

Mappings

Tutorial given at the SGP 2015 graduate school (with Roi Poranne)
Part A (Roi Poranne) Part B (Shahar Kovalsky)
image 1

Tour of Image Denoising

Tutorial given at the Weizmann Institute of Science 2011 (with Alon Faktor)
Slides (Powerpoint) Slides (PDF)