Dr Bubacarr Bah’s research outputs span applied mathematics, data science, and public health, with a strong focus on methodological innovation and real-world impact. His publications include peer-reviewed journal articles, conference proceedings, book chapters, and pre-prints, reflecting sustained contributions to both theory and application across interdisciplinary domains.
Publications Breakdown
Discrete optimization methods for group model selection in compressed sensing; accepted in Mathematical Programming, (2020) https://doi.org/10.1007/s10107-020-01529-7 (with J. Kurtz, and O. Schaudt).
Outcome Prediction with Serial Neuron-Specific Enolase and Machine Learning in Anoxic-Ischaemic Disorders of Consciousness; Computers in biology and medicine, 107 (2019), 145–152 (with E. Muller, J. Shock, A. Bender, J. Kleeberger, T. Högen, M. Rosenfelder, and A. Lopez-Rolon).
On the construction of sparse matrices from expander graphs, B. Bah and J. Tanner; Frontiers in Applied Mathematics and Statistics: Mathematics of Computation and Data Science, Vol. 4(39) (2018) 2297-4687.
The sample complexity of weighted sparse approximation, B. Bah and R. Ward; IEEE Transactions on Signal processing, Vol. 64(12) (2016) 3145-3155.
Bounds of restricted isometry constants in extreme asymptotics: formulae for Gaussian matrices, B. Bah and J. Tanner; Linear Algebra and its Applications, Vol. 441(1) (2014) 88-109.
Vanishingly sparse matrices and expander graphs, with application to compressed sensing, B. Bah and J. Tanner; IEEE Transactions on Information Theory, Vol. 59(11) (2013) 7491-7508.
Improved bounds on restricted isometry constants for Gaussian matrices, B. Bah and J. Tanner; SIAM Journal on Matrix Analysis, Vol. 31(5) (2010) 2882-2898.
Improving the Reliability of Pooled Testing with Combinatorial Decoding and Compressed Sensing; accepted at 55th Annual Conference on Information Sciences and Systems (CISS 2021), Online, (2021) (with H. Petersen, S. Agarwal, and P. Jung).
Towards the Localisation of Lesions in Diabetic Retinopathy; accepted at Computing Conference 2021, London, (with S. Mensah, and W. Brink).
An Integer Programming Approach to Deep Neural Networks with Binary Activation Functions; ICML 2020 workshop on “Beyond First Order Methods in Machine Learning” (with J. Kurtz).
On Error Correction Neural Networks for Economic Forecasting; 23rd International Conference on Information Fusion (FUSION 2020), Pretoria, South Africa, (with M. Mvubu, E. Kabuga, C. Plitz, R. Becker, and H-G. Zimmermann).
Using neural networks to identify individual animals from photographs; (extended abstract), South African Forum for Artificial Intelligence Research (FAIR 2019), Cape Town, South Africa, (with E. Kabuga, I. Durbach, and A. Clark).
Weighted sparse recovery with expanders, B. Bah; 5th International Workshop on Compressed Sensing applied to Radar, Multimodal Sensing and Imaging (CoSeRa), Siegen, Germany, 10-13 September 2018.
Convex block-sparse linear regression with expanders, provably, A. Kyrillidis, B. Bah, R. Hasheminezhad, Q. Tran-Dinh, L. Baldassarre, and V. Cevher; 19th International Conference on Artificial Intelligence and Statistics (AISTATS 2016), Cadiz, Spain, 2016.
Metric Learning with Rank and Sparsity Constraints, B. Bah, V. Cevher, S. Becker and B. Gözcü; IEEE International Conference on Acoustics, Speech and Signal Processing, Florence, Italy, 2014.
Model-based Sketching and Recovery with Expanders, B. Bah, L. Baldassarre and V. Cevher; ACM-SIAM Symposium on Discrete Algorithms, Portland, Oregon, USA, 2014.
Construction and analysis of sparse random matrices and expander graphs with applications to compressed sensing, B. Bah and J. Tanner; 10th International Conference on Sampling Theory and Applications (SampTA 2013), Bremen, Germany, 2013.
Energy-aware adaptive bi-Lipschitz embeddings, A. Sadeghian, B. Bah and V. Cevher; 10th International Conference on Sampling Theory and Applications (SampTA 2013), Bremen, Germany, 2013.
Designing Data-driven Learning Algorithms: A Necessity to ensure effective post-genomic Medicine and Biomedical Research; Artificial Intelligence–Applications in Medicine and Biology, IntechOpen, (2019) (with G. Mazandu, I. Kyomugisha, M. Seuneu, and E. Chimusa).
Editorial: Recent Developments in Signal Approximation and Reconstruction; Frontiers in Applied Mathematics and Statistics, (2020) (with J. L. Bouchot).
Learning deep linear neural networks: Riemannian gradient flows and convergence to global minimizers; accepted at Information and Inference: A Journal of the IMA (with H. Rauhut, U. Terstiege, and M. Westdickenberg).
Efficient Tuning–Free l1 -Regression of Nonnegative Compressible Signals; submitted to a journal and on arXiv (with H. Petersen, and P. Jung).
Practical High-Throughput, Non-Adaptive and Noise-Robust SARS-CoV-2 Testing; submitted to a conference and on arXiv (with H. B. Petersen, and P. Jung).
Restricted Isometry Constants in Compressed Sensing (supervised by Jared Tanner and Coralia Cartis).
Diffusion Maps: Analysis and Applications (supervised by Radek Erban).