Subhadip

Subhadip Mukherjee

Biography

Subhadip Mukherjee is an Assistant Professor in the Department of Electronics and Electrical Communication Engineering at the Indian Institute of Technology Kharagpur. His research interests lie at the intersection of signal processing, machine learning, optimization, and inverse problems, with a particular focus on medical image reconstruction and analysis. His work aims to develop robust, self-supervised, and theoretically grounded learning algorithms for imaging applications, especially in applications such as low-dose X-ray computed tomography.

Dr. Mukherjee’s research spans diffusion models for inverse problems, data-driven regularization, bilevel optimization, and learning-to-optimize methods, with an emphasis on robustness to noise, distribution shifts, and limited supervision. A central theme of his work is bridging the gap between proof-of-concept machine learning models and deployable clinical systems, combining algorithmic innovation with theoretical guarantees.

Prior to joining IIT Kharagpur, he was an Assistant Professor at the University of Bath, UK, and held a postdoctoral position at the University of Cambridge, where he worked on learning-based approaches for imaging inverse problems and observed firsthand the challenges of translating advanced algorithms into real clinical workflows. He has taught undergraduate and graduate courses in signal processing, optimization, and mathematical foundations of machine learning, and actively supervises research projects at the undergraduate and postgraduate levels.

Publications

2022

  1. IJWMIP 22
    Quantization-aware phase retrieval
    , and 
    International Journal of Wavelets, Multiresolution and Information Processing, 2022
    Cite Download .bib
    @article{mukherjee2022quantization, author = {Mukherjee, S. and Seelamantula, C. S.}, journal = {International Journal of Wavelets, Multiresolution and Information Processing}, title = {Quantization-aware phase retrieval}, url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&cstart=100&pagesize=100&citation_for_view=1g1i1B4AAAAJ:KUbvn5osdkgC}, year = {2022} }

2020

  1. SPCOM 20
    PhaseSense—Signal Reconstruction from Phase-Only Measurements via Quadratic Programming
    V. Kishore , , and 
    In International Conference on Signal Processing and Communications (SPCOM), 2020
    Cite Download .bib
    @inproceedings{kishore2020phasesense, author = {Kishore, V. and Mukherjee, S. and Seelamantula, C. S.}, booktitle = {International Conference on Signal Processing and Communications (SPCOM)}, title = {PhaseSense—Signal Reconstruction from Phase-Only Measurements via Quadratic Programming}, url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&cstart=100&pagesize=100&citation_for_view=1g1i1B4AAAAJ:kh2fBNsKQNwC}, year = {2020} }
  2. APSIPA Trans. Signal Inf. Process. 20
    Signal denoising using the minimum-probability-of-error criterion
    , , and 
    APSIPA Transactions on Signal and Information Processing, 2020
    Cite Download .bib
    @article{sadasivan2020signal, author = {Sadasivan, J. and Mukherjee, S. and Seelamantula, C. S.}, journal = {APSIPA Transactions on Signal and Information Processing}, pages = {e3}, title = {Signal denoising using the minimum-probability-of-error criterion}, url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&cstart=100&pagesize=100&citation_for_view=1g1i1B4AAAAJ:Fu2w8maKXqMC}, volume = {9}, year = {2020} }

2018

  1. IEEE SPL 18
    Phase retrieval from binary measurements
    , and 
    IEEE Signal Processing Letters, 2018
    Cite Download .bib
    @article{mukherjee2018phase, author = {Mukherjee, S. and Seelamantula, C. S.}, journal = {IEEE Signal Processing Letters}, number = {3}, pages = {348--352}, title = {Phase retrieval from binary measurements}, url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&pagesize=100&citation_for_view=1g1i1B4AAAAJ:z_wVstp3MssC}, volume = {25}, year = {2018} }
  2. ICASSP 18
    Phasesplit: A variable splitting framework for phase retrieval
    , , and 
    In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018
    Cite Download .bib
    @inproceedings{mukherjee2018phasesplit, author = {Mukherjee, S. and Shit, S. and Seelamantula, C. S.}, booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, title = {Phasesplit: A variable splitting framework for phase retrieval}, url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&cstart=100&pagesize=100&citation_for_view=1g1i1B4AAAAJ:g3aElNc5_aQC}, year = {2018} }
  3. INTERSPEECH 18
    Speech Enhancement Using the Minimum-probability-of-error Criterion
    , , and 
    In INTERSPEECH, 2018
    Cite Download .bib
    @inproceedings{sadasivan2018speech, author = {Sadasivan, J. and Mukherjee, S. and Seelamantula, C. S.}, booktitle = {INTERSPEECH}, pages = {1141--1145}, title = {Speech Enhancement Using the Minimum-probability-of-error Criterion}, url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&cstart=100&pagesize=100&citation_for_view=1g1i1B4AAAAJ:EYYDruWGBe4C}, year = {2018} }
  4. SPCOM 18
    Binary compressive sensing and super-resolution with unknown threshold
    , , and 
    In International Conference on Signal Processing and Communications (SPCOM), 2018
    Cite Download .bib
    @inproceedings{mukherjee2018binary, author = {Mukherjee, S. and Sekuboyina, A. K. and Seelamantula, C. S.}, booktitle = {International Conference on Signal Processing and Communications (SPCOM)}, title = {Binary compressive sensing and super-resolution with unknown threshold}, url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&cstart=200&pagesize=100&citation_for_view=1g1i1B4AAAAJ:-FonjvnnhkoC}, year = {2018} }
  5. SPCOM 18
    A singular value relaxation technique for learning sparsifying transforms
    , and 
    In International Conference on Signal Processing and Communications (SPCOM), 2018
    Cite Download .bib
    @inproceedings{mukherjee2018singular, author = {Mukherjee, S. and Seelamantula, C. S.}, booktitle = {International Conference on Signal Processing and Communications (SPCOM)}, title = {A singular value relaxation technique for learning sparsifying transforms}, url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&cstart=200&pagesize=100&citation_for_view=1g1i1B4AAAAJ:e_rmSamDkqQC}, year = {2018} }

2017

  1. arXiv 17
    Deep sparse coding using optimized linear expansion of thresholds
    , , and 
    arXiv preprint arXiv:1705.07290, 2017
    Cite Download .bib
    @article{mahapatra2017deep, author = {Mahapatra, D. and Mukherjee, S. and Seelamantula, C. S.}, journal = {arXiv preprint arXiv:1705.07290}, title = {Deep sparse coding using optimized linear expansion of thresholds}, url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&pagesize=100&citation_for_view=1g1i1B4AAAAJ:ZfRJV9d4-WMC}, year = {2017} }
  2. Sci. Rep. 17
    Super-resolved nuclear magnetic resonance spectroscopy
    , A. Singh , V. P. Brahmkhatri , K. Chandra , T. Raza , S. P. Mukherjee , and  others
    Scientific reports, 2017
    Cite Download .bib
    @article{mulleti2017super, author = {Mulleti, S. and Singh, A. and Brahmkhatri, V. P. and Chandra, K. and Raza, T. and Mukherjee, S. P. and others}, journal = {Scientific reports}, number = {1}, pages = {9651}, title = {Super-resolved nuclear magnetic resonance spectroscopy}, url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&pagesize=100&citation_for_view=1g1i1B4AAAAJ:9Nmd_mFXekcC}, volume = {7}, year = {2017} }
  3. NeurIPS-W 17
    DNNs for sparse coding and dictionary learning
    , , and 
    In NIPS Bayesian Deep Learning Workshop, 2017
    Cite Download .bib
    @inproceedings{mukherjee2017dnns, author = {Mukherjee, S. and Mahapatra, D. and Seelamantula, C. S.}, booktitle = {NIPS Bayesian Deep Learning Workshop}, title = {DNNs for sparse coding and dictionary learning}, url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&cstart=100&pagesize=100&citation_for_view=1g1i1B4AAAAJ:uc_IGeMz5qoC}, year = {2017} }
  4. arXiv 17
    Online Reweighted Least Squares Algorithm for Sparse Recovery and Application to Short-Wave Infrared Imaging
    , H. Chen , A. Veeraraghavan , and 
    arXiv preprint arXiv:1706.09585, 2017
    Cite Download .bib
    @article{mukherjee2017online, author = {Mukherjee, S. and Chen, H. and Veeraraghavan, A. and Seelamantula, C. S.}, journal = {arXiv preprint arXiv:1706.09585}, title = {Online Reweighted Least Squares Algorithm for Sparse Recovery and Application to Short-Wave Infrared Imaging}, url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&cstart=200&pagesize=100&citation_for_view=1g1i1B4AAAAJ:j8SEvjWlNXcC}, year = {2017} }

2016

  1. Signal Process. 16
    ℓ₁-K-SVD: A robust dictionary learning algorithm with simultaneous update
    , , and 
    Signal Processing, 2016
    Cite Download .bib
    @article{mukherjee2016l1, author = {Mukherjee, S. and Basu, R. and Seelamantula, C. S.}, journal = {Signal Processing}, pages = {42--52}, title = {ℓ₁-K-SVD: A robust dictionary learning algorithm with simultaneous update}, url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&pagesize=100&citation_for_view=1g1i1B4AAAAJ:D_sINldO8mEC}, volume = {123}, year = {2016} }
  2. ICASSP 16
    Joint dictionary training for bandwidth extension of speech signals
    , , and 
    In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016
    Cite Download .bib
    @inproceedings{sadasivan2016joint, author = {Sadasivan, J. and Mukherjee, S. and Seelamantula, C. S.}, booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, title = {Joint dictionary training for bandwidth extension of speech signals}, url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&pagesize=100&citation_for_view=1g1i1B4AAAAJ:bnK-pcrLprsC}, year = {2016} }
  3. NCC 16
    Convergence rate analysis of smoothed LASSO
    , and 
    In Twenty second national conference on communication (NCC), 2016
    Cite Download .bib
    @inproceedings{mukherjee2016convergence, author = {Mukherjee, S. and Seelamantula, C. S.}, booktitle = {Twenty second national conference on communication (NCC)}, pages = {1--6}, title = {Convergence rate analysis of smoothed LASSO}, url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&cstart=100&pagesize=100&citation_for_view=1g1i1B4AAAAJ:WqliGbK-hY8C}, year = {2016} }
  4. ICASSP 16
    A divide-and-conquer dictionary learning algorithm and its performance analysis
    , and 
    In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016
    Cite Download .bib
    @inproceedings{mukherjee2016divide, author = {Mukherjee, S. and Seelamantula, C. S.}, booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, title = {A divide-and-conquer dictionary learning algorithm and its performance analysis}, url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&cstart=100&pagesize=100&citation_for_view=1g1i1B4AAAAJ:XiVPGOgt02cC}, year = {2016} }
  5. arXiv 16
    Super-Resolution From Binary Measurements With Unknown Threshold
    , , and 
    arXiv preprint arXiv:1606.03472, 2016
    Cite Download .bib
    @article{mukherjee2016super, author = {Mukherjee, S. and Sekuboyina, A. K. and Seelamantula, C. S.}, journal = {arXiv preprint arXiv:1606.03472}, title = {Super-Resolution From Binary Measurements With Unknown Threshold}, url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&cstart=200&pagesize=100&citation_for_view=1g1i1B4AAAAJ:t6usbXjVLHcC}, year = {2016} }

2014

  1. IEEE TSP 14
    Fienup algorithm with sparsity constraints: Application to frequency-domain optical-coherence tomography
    , and 
    IEEE Transactions on Signal Processing, 2014
    Cite Download .bib
    @article{mukherjee2014fienup, author = {Mukherjee, S. and Seelamantula, C. S.}, journal = {IEEE Transactions on Signal Processing}, number = {18}, pages = {4659--4672}, title = {Fienup algorithm with sparsity constraints: Application to frequency-domain optical-coherence tomography}, url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&pagesize=100&citation_for_view=1g1i1B4AAAAJ:g5m5HwL7SMYC}, volume = {62}, year = {2014} }
  2. ICASSP 14
    An optimum shrinkage estimator based on minimum-probability-of-error criterion and application to signal denoising
    , , and 
    In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2014
    Cite Download .bib
    @inproceedings{sadasivan2014optimum, author = {Sadasivan, J. and Mukherjee, S. and Seelamantula, C. S.}, booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, title = {An optimum shrinkage estimator based on minimum-probability-of-error criterion and application to signal denoising}, url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&pagesize=100&citation_for_view=1g1i1B4AAAAJ:pqnbT2bcN3wC}, year = {2014} }
  3. arXiv 14
    A split-and-merge dictionary learning algorithm for sparse representation
    , and 
    arXiv preprint arXiv:1403.4781, 2014
    Cite Download .bib
    @article{mukherjee2014split, author = {Mukherjee, S. and Seelamantula, C. S.}, journal = {arXiv preprint arXiv:1403.4781}, title = {A split-and-merge dictionary learning algorithm for sparse representation}, url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&cstart=100&pagesize=100&citation_for_view=1g1i1B4AAAAJ:J_g5lzvAfSwC}, year = {2014} }
  4. CoRR 14
    A Robust Dictionary Learning Algorithm for Image Denoising
    , , and 
    CoRR, 2014
    Cite Download .bib
    @article{mukherjee2014robust, author = {Mukherjee, S. and Basu, R. and Seelamantula, C. S.}, journal = {CoRR}, title = {A Robust Dictionary Learning Algorithm for Image Denoising}, url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&cstart=200&pagesize=100&citation_for_view=1g1i1B4AAAAJ:dfsIfKJdRG4C}, volume = {abs/1403.4781}, year = {2014} }
  5. DSP 14
    A split-and-merge dictionary learning algorithm for sparse representation: Application to image denoising
    , and 
    In 19th International Conference on Digital Signal Processing (DSP), 2014
    Cite Download .bib
    @inproceedings{mukherjee2014split_merge, author = {Mukherjee, S. and Seelamantula, C. S.}, booktitle = {19th International Conference on Digital Signal Processing (DSP)}, pages = {310--315}, title = {A split-and-merge dictionary learning algorithm for sparse representation: Application to image denoising}, url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&cstart=200&pagesize=100&citation_for_view=1g1i1B4AAAAJ:u_35RYKgDlwC}, year = {2014} }

2012

  1. ICASSP 12
    An iterative algorithm for phase retrieval with sparsity constraints: application to frequency domain optical coherence tomography
    , and 
    In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2012
    Cite Download .bib
    @inproceedings{mukherjee2012iterative, author = {Mukherjee, S. and Seelamantula, C. S.}, booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, title = {An iterative algorithm for phase retrieval with sparsity constraints: application to frequency domain optical coherence tomography}, url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&pagesize=100&citation_for_view=1g1i1B4AAAAJ:4TOpqqG69KYC}, year = {2012} }
  2. STSIP 12
    A non-iterative phase retrieval algorithm for minimum-phase signals using the annihilating filter
    , and 
    Sampling Theory in Signal and Image Processing, 2012
    Cite Download .bib
    @article{mukherjee2012non, author = {Mukherjee, S. and Seelamantula, C. S.}, journal = {Sampling Theory in Signal and Image Processing}, pages = {165--193}, title = {A non-iterative phase retrieval algorithm for minimum-phase signals using the annihilating filter}, url = {https://scholar.google.com/citations?view_op=view_citation&hl=en&user=1g1i1B4AAAAJ&pagesize=100&citation_for_view=1g1i1B4AAAAJ:70eg2SAEIzsC}, volume = {11}, year = {2012} }