J Jayadeva IIT Delhi

Selected Publications

Selected publications from Prof. Jayadeva's research.

Publications are organized by research theme. For current citation information and a broader publication record, see the linked academic profiles in the footer.

Minimal Complexity Machines

  1. Jayadeva. Learning a hyperplane classifier by minimizing an exact bound on the VC dimension. Neurocomputing, 149, pp.683-689, 2015.
  2. Jayadeva, Chandra, S., Batra, S.S. and Sabharwal, S. Learning a hyperplane regressor minimizing the VC dimension. Neurocomputing, 171, pp.1610-1616, 2016.
  3. Gupta, P., Batra, S.S. and Jayadeva. Sparse short-term time series forecasting models via minimum model complexity. Neurocomputing, 243, pp.1-11, 2017.
  4. Mayank, Jayadeva, Sumit and Himanshu. Large-scale minimal complexity machines using explicit feature maps. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 47(10), pp.2653-2662, 2017.
  5. Sharma, M., Soman, S. and Pant, H. Ultra-Sparse Classifiers Through Minimizing the VC Dimension in the Empirical Feature Space. Neural Processing Letters, 2018.
  6. Jayadeva, Soman, S., Pant, H. and Sharma, M. QMCM: Minimizing Vapnik's bound on the VC dimension. Neurocomputing, 399, pp.352-360, 2020.
  7. Sharma, M., Soman, S. and Jayadeva. Minimal Complexity Machines Under Weight Quantization. IEEE Transactions on Computers, 2021.

Hashing, Outliers, and Graphs

  1. Compressed binary search tree for approximate k-NN searches in Hamming space. Big Data Research, 25:100223, 2021.
  2. Guided Random Forest and its application to data approximation. arXiv:1909.00659, 2019.
  3. Linear time identification of local and global outliers. Neurocomputing, 429, pp.141-150, 2021.
  4. Enhash: A Fast Streaming Algorithm For Concept Drift Detection. arXiv:2011.03729, 2020.
  5. Fast and Scalable Hashing-Based Universal Graph Coarsening. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026.
  6. Leap of FAITH from GNN-to-MLP: Fairness Aware Inference via Distillation of Graph Knowledge. AAAI Conference on Artificial Intelligence, 2026.
  7. A novel coarsened graph learning method for scalable single-cell data analysis. Computers in Biology and Medicine, 188:109873, 2025.

Swarm Intelligence and Silicon

  1. Ants find the shortest path: a mathematical proof. Swarm Intelligence, 2013.
  2. Design methodology for configurable analog to digital conversion using support vector machines. Microelectronics Journal, 39(5), pp.822-827, 2008.

Healthcare and Applications

  1. Discovery of rare cells from voluminous single cell expression data. Nature Communications, 9(1):4719, 2018.
  2. A new deep learning technique reveals the exclusive functional contributions of individual cancer mutations. Journal of Biological Chemistry, 298(8), 2022.
  3. Molecular signature comprising 11 platelet-genes enables accurate blood-based diagnosis of NSCLC. BMC Genomics, 21(1):744, 2020.
  4. EigenSample: A non-iterative technique for adding samples to small datasets. Applied Soft Computing, 70, pp.1064-1077, 2018.
  5. Core-bold: Cross-domain robust and equitable ensemble for BOLD signal analysis. Machine Learning for Health, pp.961-975, 2025.

Material Properties

  1. Artificial intelligence for information extraction from cement literature. In Binding Materials for Sustainable Construction, pp.819-832, 2025.
  2. Discovering symbolic laws directly from trajectories with Hamiltonian graph neural networks. Machine Learning: Science and Technology, 5(3):035049, 2024.
  3. Interpretable machine learning for understanding compositional and testing condition effects on inorganic melts and glasses. Frontiers in Materials, 11:1412701, 2024.
  4. Brognet: Momentum-conserving graph neural stochastic differential equation for learning Brownian dynamics. ICLR, 2024.
  5. MaScQA: investigating materials science knowledge of large language models. Digital Discovery, 3(2), pp.313-327, 2024.
  6. Predicting oxide glass properties with low complexity neural network and physical and chemical descriptors. Journal of Non-Crystalline Solids, 616:122488, 2023.
  7. Cementron: Machine learning the alite and belite phases in cement clinker from optical images. Construction and Building Materials, 397:132425, 2023.