Bahareh Tolooshams
Bahareh Tolooshams

Postdoctoral Researcher,
CMS Department,
Caltech

Our knowledge can only be finite, while our ignorance must necessarily be infinite.
- Karl Popper

Publications
Journals and Conferences

  1. A unified model for compressed sensing MRI across undersampling patterns
    A. S. Jatyani*, J. Wang*, A. Chandrashekar, Z. Wu, M. Liu-Schiaffini, B. Tolooshams, and A. Anandkumar
    Submitted to CVPR 2025 [paper]
  2. Diffusion state-guided projected gradient for inverse problems
    R. Zirvi*, B. Tolooshams*, and A. Anandkumar
    Submitted to ICLR 2025 [paper]
  3. Fourier neural operators for learning dynamics in quantum spin systems
    F. Shah, T. L. Patti, J. Berner, B. Tolooshams, J. Kossaifi, and A. Anandkumar
    Submitted to Nature Communications Physics 2024 [paper]
  4. Interpretable deep learning for deconvolutional analysis of neural signals
    B. Tolooshams*, S. Matias*, H. Wu, S. Temereanca, N. Uchida, V. N. Murthy, P. Masset, and D. Ba
    Submitted to Neuron 2024 [paper]
  5. Discriminative reconstruction via simultaneous dense and sparse coding
    A. Tasissa, E. Theodosis, B. Tolooshams, and D. Ba
    TMLR 2024 [paper] [code1, code2]
  6. Unrolled compressed blind-deconvolution
    B. Tolooshams*, S. Mulleti*, D. Ba, and Y. C. Eldar
    IEEE Transactions on Signal Processing 2023 [paper]
  7. Probabilistic unrolling: scalable, inverse-free maximum likelihood estimation of latent Gaussian models
    A. Lin, B. Tolooshams, Y. Atchadé, and D. Ba
    ICML 2023 [paper]
  8. Stable and interpretable unrolled dictionary learning
    B. Tolooshams and D. Ba
    TMLR 2022 [paper] [code]
  9. A training framework for stereo-aware speech enhancement using deep neural networks
    B. Tolooshams and K. Koishida
    IEEE ICASSP 2022 [paper] [slides] [poster]
  10. On the convergence of group-sparse autoencoders
    E. Theodosis, B. Tolooshams*, P. Tankala*, A. Tasissa, and D. Ba
    arXiv 2021 [paper]
  11. Gaussian process convolutional dictionary learning
    A. H. Song, B. Tolooshams, and D. Ba
    IEEE Signal Processing Letters 2021 [paper]
  12. Unfolding neural networks for compressive multichannel blind deconvolution
    B. Tolooshams*, S. Mulleti*, D. Ba, and Y. C. Eldar
    IEEE ICASSP 2021 [paper] [slides] [poster]
  13. Deep residual autoencoders for expectation maximization-inspired dictionary learning
    B. Tolooshams, S. Dey, and D. Ba
    IEEE Transactions on Neural Networks and Learning Systems 2021 [paper] [code]
  14. Convolutional dictionary learning based auto-encoders for natural exponential-family distributions
    B. Tolooshams*, A. H. Song*, S. Temereanca, and D. Ba
    ICML 2020 [paper] [code] [slides] [talk]
  15. Channel-attention dense u-net for multichannel speech enhancement
    B. Tolooshams, R. Giri, A. H. Song, U. Isik, and A. Krishnaswamy
    IEEE ICASSP 2020 [paper]
  16. Convolutional dictionary learning in hierarchical networks
    J. Zazo, B. Tolooshams, and D. Ba
    IEEE CAMSAP 2019 [paper]
  17. RandNet: deep learning with compressed measurements of images
    T. Chang*, B. Tolooshams*, and D. Ba
    IEEE MLSP 2019 [paper] [code] [poster]
  18. Scalable convolutional dictionary learning with constrained recurrent sparse auto-encoders
    B. Tolooshams, S. Dey, and D. Ba
    IEEE MLSP 2018 [paper] [code]
  19. Robustness of frequency division technique for online myoelectric pattern recognition against contraction-level variation
    B. Tolooshams and N. Jiang
    Frontiers in Bioengineering and Biotechnology 2017 [paper]
Workshops

  1. Unifying subsampling pattern variations for compressed sensing MRI with neural operators
    A. S. Jatyani*, J. Wang*, Z. Wu, M. Liu-Schiaffini, B. Tolooshams, and A. Anandkumar
    Machine Learning and Compression at NeurIPS 2024 [paper]
  2. Projected low-rank gradient in diffusion-based models for inverse problems
    R. Zirvi*, B. Tolooshams*, and A. Anandkumar
    D3S3: Data-driven and Differentiable Simulations, Surrogates, and Solvers at NeurIPS 2024 [paper]
Abstracts

  1. A feedback mechanism in generative networks to remove visual degradation
    B. Tolooshams, Y. Shi, A. Anandkumar, and D. Tsao
    Submitted to COSYNE 2025
  2. Sparse autoencoders for mechanistic insights on neural computation in naturalistic experiments
    V. Costa, S. Matias, B. Tolooshams, P. Masset, N. Uchida, and D. Ba
    Submitted to COSYNE 2025
  3. A feedback mechanism in deep generative networks to remove degradation from visual stimuli
    B. Tolooshams, Y. Shi, A. Anandkumar, and D. Tsao
    NAISys 2024
  4. Interpretable deep learning for deconvolution of multiplexed neural signals
    B. Tolooshams, S. Matias, H. Wu, N. Uchida, V. N. Murthy, P. Masset, and D. Ba
    COSYNE 2023 [paper] [talk]
  5. Interpretable unrolled dictionary learning networks
    B. Tolooshams and D. Ba
    DeepMath 2022 [paper] [slides]
  6. Unsupervised sparse deconvolutional learning of features driving neural activity
    B. Tolooshams, H. Wu, N. Uchida, V. N. Murthy, P. Masset, and D. Ba
    COSYNE 2022 [paper] [poster]
  7. Unsupervised learning of a dictionary of neural impulse responses from spiking data
    B. Tolooshams, H. Wu, P. Masset, V. N. Murthy, and D. Ba
    COSYNE 2021 [paper] [poster]
  8. Convolutional dictionary learning of stimulus from spiking data
    A. H. Song*, B. Tolooshams*, S. Temereanca, and D. Ba
    COSYNE 2020 [paper] [poster]