Hedda Cohen Indelman

I am a Ph.D. student under the supervision of Professor Tamir Hazan at the Technion - Israel Institute of Technology. My research is focused on learning and inference in high-dimensional structured models, with a special emphasis on learning matching representations. Motivated by structured prediction problems such as graph matching, I study efficient learning of constrained structured spaces, gradients of randomly perturbed structured models, and theory-driven relaxation techniques thereof. I am especially interested in marrying optimization techniques, probability and perturbations models, as well as classical ML to solve discrete data problems. The advantages of my research is demonstrated on well-known structured prediction benchmarks.

I am also an AI research scientist at GE Healthcare, focusing on bridging the gap between AI innovations and medical imaging. Previously, I was a research intern at Amazon, and have more than 10 years of experience in data science and analytics.

heddacohenind dot mail at gmail dot com

Publications

2024

On The Statistical Representation Properties Of The Perturb-Softmax And The Perturb-Argmax Probability Distributions. Hedda Cohen Indelman, Tamir Hazan.

PDF,

BibTeX

                                        
@misc{indelman2024statistical,
      title={On The Statistical Representation Properties Of The Perturb-Softmax And The Perturb-Argmax Probability Distributions}, 
      author={Hedda Cohen Indelman and Tamir Hazan},
      year={2024},
      eprint={2406.02180},
      archivePrefix={arXiv},}

Semantic Segmentation Refiner for Ultrasound Applications with Zero-Shot Foundation Models. Hedda Cohen Indelman, Elay Dahan, Angeles M Perez-Agosto, Carmit Shiran, Doron Shaked, Nati Daniel. Annual International Conference of the IEEE, Engineering in Medicine and Biology Society (EMBC), 2024

PDF,

BibTeX

                                        
 @misc{indelman2024semantic,
      title={Semantic Segmentation Refiner for Ultrasound Applications with Zero-Shot Foundation Models}, 
      author={Hedda Cohen Indelman and Elay Dahan and Angeles M. Perez-Agosto and Carmit Shiran and Doron Shaked and Nati Daniel},
      year={2024},
      eprint={2404.16325},
      archivePrefix={arXiv},}

Learning Latent Partial Matchings with Gumbel-IPF Networks. Hedda Cohen Indelman, Tamir Hazan. International Conference on Artificial Intelligence and Statistics (AISTATS), 2024

PDF,

Code,

BibTeX

                                        
@InProceedings{pmlr-v238-cohen-indelman24a,
  title = 	 { Learning Latent Partial Matchings with {G}umbel-{IPF} Networks },
  author =       {Cohen Indelman, Hedda and Hazan, Tamir},
  booktitle = 	 {Proceedings of The 27th International Conference on Artificial Intelligence and Statistics},
  pages = 	 {1513--1521},
  year = 	 {2024},
  editor = 	 {Dasgupta, Sanjoy and Mandt, Stephan and Li, Yingzhen},
  volume = 	 {238},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {02--04 May},
  publisher =    {PMLR}}

InDi: Informative and Diverse Sampling for Dense Retrieval. Nachshon Cohen, Hedda Cohen Indelman, Yaron Fairstein, Guy Kushilevitz. European Conference on Information Retrieval, (ECIR), 2024

PDF,

BibTeX

                                        
        @InProceedings{10.1007/978-3-031-56063-7_16,
    author="Cohen, Nachshon
    and Cohen-Indelman, Hedda
    and Fairstein, Yaron
    and Kushilevitz, Guy",
    title="InDi: Informative and Diverse Sampling for Dense Retrieval",
    booktitle="Advances in Information Retrieval",
    year="2024",
    publisher="Springer Nature Switzerland",
    pages="243--258",
    isbn="978-3-031-56063-7"
    }

2023

Learning Constrained Structured Spaces with Application to Multi-Graph Matching. Hedda Cohen Indelman, Tamir Hazan. International Conference on Artificial Intelligence and Statistics (AISTATS), 2023

PDF,

Code,

BibTeX

                                        
        
@InProceedings{pmlr-v206-indelman23a,
  title = 	 {Learning Constrained Structured Spaces with Application to Multi-Graph Matching},
  author =       {Indelman, Hedda Cohen and Hazan, Tamir},
  booktitle = 	 {Proceedings of The 26th International Conference on Artificial Intelligence and Statistics},
  pages = 	 {2589--2602},
  year = 	 {2023},
  editor = 	 {Ruiz, Francisco and Dy, Jennifer and van de Meent, Jan-Willem},
  volume = 	 {206},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {25--27 Apr},
  publisher =    {PMLR},}

2021

Learning randomly perturbed structured predictors for direct loss minimization. Hedda Cohen Indelman, Tamir Hazan. International Conference on Machine Learning (ICML), 2021

PDF,

Code,

BibTeX

                                        
@InProceedings{pmlr-v139-indelman21a,
  title = 	 {Learning Randomly Perturbed Structured Predictors for Direct Loss Minimization},
  author =       {Indelman, Hedda Cohen and Hazan, Tamir},
  booktitle = 	 {Proceedings of the 38th International Conference on Machine Learning},
  pages = 	 {4585--4595},
  year = 	 {2021},
  editor = 	 {Meila, Marina and Zhang, Tong},
  volume = 	 {139},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {18--24 Jul},
  publisher =    {PMLR},}