29 citations · 57 across the 14 of their papers we have counts for
16 papers
dOPT: Differentiating Conic Optimization via Geometric Reduction
Fengyu Yang, Connor W. Magoon, Tyler Watts +1
Optimization layers enable the incorporation of structured constraints and decision problems into learning systems. Training such systems requires differentiating through the embed…
De-Individualizing fMRI Signals via Mahalanobis Whitening and Bures Geometry
Aaron Jacobson, Tingting Dan, Martin Styner +3
Functional connectivity has been widely investigated to understand brain disease in clinical studies and imaging-based neuroscience, and analyzing changes in functional connectivit…
Differentiation Through Black-Box Quadratic Programming Solvers
Connor W. Magoon, Fengyu Yang, Noam Aigerman +1
Differentiable optimization has attracted significant research interest, particularly for quadratic programming (QP). Existing approaches for differentiating the solution of a QP w…
Re-Think and Re-Design Graph Neural Networks in Spaces of Continuous Graph Diffusion Functionals
Tingting Dan, Jiaqi Ding, Ziquan Wei +4
Graph neural networks (GNNs) are widely used in domains like social networks and biological systems. However, the locality assumption of GNNs, which limits information exchange to…
Symmetrized Robust Procrustes: Constant-Factor Approximation and Exact Recovery
Tal Amir, Shahar Kovalsky, Nadav Dym
The classical problem is to find a rigid motion (orthogonal transformation and translation) that best aligns two given point-sets in the least-squares sense.…
Neural Network Approximation of Refinable Functions
Ingrid Daubechies, Ronald DeVore, Nadav Dym +6
In the desire to quantify the success of neural networks in deep learning and other applications, there is a great interest in understanding which functions are efficiently approxi…
Non-Convex Planar Harmonic Maps
Shahar Z. Kovalsky, Noam Aigerman, Ingrid Daubechies +3
We formulate a novel characterization of a family of invertible maps between two-dimensional domains. Our work follows two classic results: The Radó-Kneser-Choquet (RKC) theorem, w…
Linearly Converging Quasi Branch and Bound Algorithms for Global Rigid Registration
Nadav Dym, Shahar Ziv Kovalsky
In recent years, several branch-and-bound (BnB) algorithms have been proposed to globally optimize rigid registration problems. In this paper, we suggest a general framework to imp…
Weakly Supervised Instance Learning for Thyroid Malignancy Prediction from Whole Slide Cytopathology Images
David Dov, Shahar Ziv Kovalsky, Serge Assaad +4
We consider machine-learning-based thyroid-malignancy prediction from cytopathology whole-slide images (WSI). Multiple instance learning (MIL) approaches, typically used for the an…
Thyroid Cancer Malignancy Prediction From Whole Slide Cytopathology Images
David Dov, Shahar Kovalsky, Jonathan Cohen +3
We consider preoperative prediction of thyroid cancer based on ultra-high-resolution whole-slide cytopathology images. Inspired by how human experts perform diagnosis, our approach…
ariaDNE: A Robustly Implemented Algorithm for Dirichlet Energy of the Normal
Shan Shan, Shahar Z. Kovalsky, Julie M. Winchester +2
Point 1: Shape characterizers are metrics that quantify aspects of the overall geometry of a 3D digital surface. When computed for biological objects, the values of a shape charact…
Gaussian Process Landmarking for Three-Dimensional Geometric Morphometrics
Tingran Gao, Shahar Z. Kovalsky, Doug M. Boyer +1
We demonstrate applications of the Gaussian process-based landmarking algorithm proposed in [T. Gao, S.Z. Kovalsky, and I. Daubechies, SIAM Journal on Mathematics of Data Science (…
Gaussian Process Landmarking on Manifolds
Tingran Gao, Shahar Z. Kovalsky, Ingrid Daubechies
As a means of improving analysis of biological shapes, we propose an algorithm for sampling a Riemannian manifold by sequentially selecting points with maximum uncertainty under a…
Identification of Structured LTI MIMO State-Space Models
Chengpu Yu, Michel Verhaegen, Shahar Kovalsky +1
The identification of structured state-space model has been intensively studied for a long time but still has not been adequately addressed. The main challenge is that the involved…
Learning 3D Deformation of Animals from 2D Images
Angjoo Kanazawa, Shahar Kovalsky, Ronen Basri +1
Understanding how an animal can deform and articulate is essential for a realistic modification of its 3D model. In this paper, we show that such information can be learned from us…
A Global Approach for Solving Edge-Matching Puzzles
Shahar Z. Kovalsky, Daniel Glasner, Ronen Basri
We consider apictorial edge-matching puzzles, in which the goal is to arrange a collection of puzzle pieces with colored edges so that the colors match along the edges of adjacent…