[Preprints] [Book chapters] [Journals] [Conferences] [Workshops] [Thesis] [Talks] [Patents]

The list of publications are also available on Google scholar and Semantic scholar.

Preprints

A. Han, B. Mishra, P. Jawanpuria, and J. Gao. Differentially private Riemannian optimization. Technical report, arXiv preprint, arXiv:2205.09494, 2022.
[arXiv:2205.09494]

P. Manupriya, J. Saketha Nath, and P. Jawanpuria. MMD-regularized Unbalanced Optimal Transport. Technical report, arXiv preprint, arXiv:2011.05001, 2021.
[arXiv:2011.05001].

B. Mishra, N. T. V. Satya Dev, H. Kasai, and P. Jawanpuria. Manifold optimization for optimal transport. Technical report, arXiv preprint, arXiv:2103.00902, 2021.
[arXiv:2103.00902][Codes@Github].

Book chapters

H. Kasai, P. Jawanpuria, and B. Mishra. A Riemannian approach to low-rank tensor learning. Chapter in Tensors for Data Processing, 2021.
[Personal copy of chapter]

Journal articles

A. Han, B. Mishra, P. Jawanpuria, P. Kumar, and J. Gao. Riemannian Hamiltonian methods for min-max optimization on manifolds. Accepted in SIAM Journal of Optimization (SIOPT), 2023.
[arXiv:2204.11418]

S. Utpala, A. Han, P. Jawanpuria, and B. Mishra. Improved Differentially Private Riemannian Optimization: Fast Sampling and Variance Reduction. Transactions on Machine Learning Research (TMLR), 2023.
[OpenReview]

A. Han, B. Mishra, P. Jawanpuria, and J. Gao. Riemannian block SPD coupling manifold and its application to optimal transport. Machine Learning Journal (special issue), 2022.
[arXiv:2201.12933][Online html version]

B. Mishra, H. Kasai, P. Jawanpuria, and A. Saroop. A Riemannian gossip approach to decentralized subspace learning on Grassmann manifold. Machine Learning Journal (MLJ), 108:1783-1803, 2019.
[Local copy][Online html version][Matrix completion code][Multitask code].

P. Jawanpuria, A. Balgovind, A. Kunchukuttan, and B. Mishra. Learning multilingual word embeddings in a latent metric space: a geometric approach. Transactions of the Association for Computational Linguistics (TACL), 7:107-120, 2019.
[Local copy][Publisher’s copy][Codes@Github].

P. Jawanpuria, J. S. Nath, and G. Ramakrishnan. Generalized hierarchical kernel learning. Journal of Machine Learning Research (JMLR), 16(Mar):617−652, 2015.
[Local copy][Publisher’s copy][Matlab codes].

Conference proceedings

A. Han, B. Mishra, P. Jawanpuria, and J. Gao. Generalized Bures-Wasserstein Geometry for Positive Definite Matrices. In Geometric Science of Information (GSI), 2023.
[arXiv:2110.10464]

I. Mishra, A. Dasgupta, P. Jawanpuria, B. Mishra, and P. Kumar. Light-weight deep extreme multilabel classification. In IEEE International Joint Conference on Neural Networks (IJCNN), 2023.
[arXiv:2304.11045]

A. Poddar, S. Dey, P. Jawanpuria, J. Mukhopadhyay, and P. K. Biswas. TBM-GAN: Synthetic document generation with degraded background. In International Conference on Document Analysis and Recognition (ICDAR), 2023.

A. Han, B. Mishra, P. Jawanpuria, and J. Gao. Riemannian accelerated gradient methods via extrapolation. In International Conference on Artificial Intelligence and Statistics (AISTATS), 2023.
[arXiv:2208.06619]

S. Banerjee, B. Mishra, P. Jawanpuria, and M. Shrivastava. Generalised spherical text embeddings. In International Conference on Natural Language Processing (ICON), 2022.
[arXiv:2211.16801]

A. R. Chaudhuri, P. Jawanpuria, B. Mishra. ProtoBandit: Efficient prototype selection via multi-armed bandits. In Asian Conference on Machine Learning (ACML), 2022.
[arXiv:2210:01860].

A. Han, B. Mishra, P. Jawanpuria, and J. Gao. On Riemannian optimization over positive definite matrices with the Bures-Wasserstein geometry. In Conference on Neural Information Processing Systems (NeurIPS), 2021.
[arXiv:2106.00286][Codes].

P. Jawanpuria, N. T. V. Satya Dev, and B. Mishra. Efficient robust optimal transport: formulations and algorithms. In IEEE Conference on Decision and Control (IEEE CDC), 2021. A short version presented in NeurIPS workshop on Optimization for Machine Learning, 2020.
[arXiv:2010.11852].

K. Gurumoorthy, P. Jawanpuria, and B. Mishra. SPOT: A framework for selection of prototypes using optimal transport. In European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD), 2021.
[arXiv:2103.10159][Codes@Github].

S. Dey and P. Jawanpuria. Light-weight Document Image Cleanup using Perceptual Loss. In International Conference on Document Analysis and Recognition (ICDAR), 2021.
[Publisher’s copy][arXiv:2105.09076].

J. Saketha Nath and P. Jawanpuria. Statistical Optimal Transport posed as Learning Kernel Embedding. In Conference on Neural Information Processing Systems (NeurIPS), 2020.
[arXiv:2002.03179][Codes@Github].

P. Jawanpuria, M. Meghwanshi, and B. Mishra. A Simple Approach to Learning Unsupervised Multilingual Embeddings. In Conference on Empirical Methods in Natural Language Processing (Short Papers), 2020.
[Local copy][arXiv:2004.05991].

P. Jawanpuria, M. Meghwanshi, and B. Mishra. Geometry-aware domain adaptation for unsupervised alignment of word embeddings. In Annual Meeting of the Association for Computational Linguistics (Short Papers), 2020.
[Publisher’s copy][arXiv:2004.08243][Slides][Matlab codes].

P. Jawanpuria, M. Meghwanshi, and B. Mishra. Low-rank approximations of hyperbolic embeddings. In IEEE Conference on Decision and Control (IEEE CDC), 2019.
[Local copy][arXiv:1903.07307][Matlab codes].

H. Kasai, P. Jawanpuria, and B. Mishra. Riemannian adaptive stochastic gradient algorithms on matrix manifolds. In International Conference on Machine Learning (ICML), 2019.
[Local copy][Publisher’s copy][Matlab codes].
Longer version: [arXiv:1902.01144]

M. Nimishakavi, P. Jawanpuria and B. Mishra. A dual framework for low-rank tensor completion. In Conference on Neural Information Processing Systems (NeurIPS), 2018. A short version presented in NeurIPS workshop on Synergies in Geometric Data Analysis, 2017.
[Local copy][Publisher’s copy][Codes@Github][Slides][Poster].
Longer version: [Local copy][arXiv:1712.01193]

P. Jawanpuria and B. Mishra. A unified framework for structured low-rank matrix learning. In International Conference on Machine Learning (ICML), 2018. A short version presented in NeurIPS workshop on Optimization for Machine Learning, 2017.
[Local copy][Publisher’s copy][Matlab codes][Slides][Poster].
Longer version: [Local copy][arXiv:1704.07352].

P. Jawanpuria, M. Lapin, M. Hein and B. Schiele. Efficient output kernel learning for multiple tasks. In Conference on Neural Information Processing Systems (NeurIPS), 2015 (formerly called Advances in Neural Information Processing Systems).
[Local copy][Publisher’s copy][Long version][Matlab codes].

P. Jawanpuria, M. Varma and J. S. Nath. On p-norm path following in multiple kernel learning for non-linear feature selection. In International Conference on Machine Learning (ICML), 2014.
[Local copy][Publisher’s copy].

P. Jawanpuria and J. S. Nath. A convex feature learning formulation for latent task structure discovery. In International Conference on Machine Learning (ICML), 2012.
[Local copy][Publisher’s copy][Supplementary material][Matlab codes].

P. Jawanpuria, J. S. Nath and G. Ramakrishnan. Efficient rule ensemble learning using hierarchical kernels. In International Conference on Machine Learning (ICML), 2011.
[Local copy][Publisher’s copy][Technical report].

P. Jawanpuria and J. S. Nath. Multi-task multiple kernel learning. In SIAM International Conference on Data Mining (SDM), 2011.
[Local copy][Matlab codes].

Workshop papers

S. Utpala, A. Han, P. Jawanpuria, and B. Mishra. Rieoptax: Riemannian optimization in JAX. Technical report, arXiv preprint, arXiv:2210.04840, 2022. In NeurIPS workshop on Optimization for Machine Learning, 2022.
[arXiv:2210:04840][Codes@Github]

S. Dey and P. Jawanpuria. Confidence Score for Unsupervised Foreground Background Separation of Document Images. In International Workshop on Document Analysis System (DAS), 2022.
[arXiv:2204.04044]

B. Mishra, H. Kasai, and P. Jawanpuria. Riemannian optimization on the simplex of positive definite matrices. In NeurIPS workshop on Optimization for Machine Learning, 2020.
[arXiv:1906.10436].

P. Jawanpuria, N T V Satya Dev, A. Kunchukuttan, and B. Mishra. Learning Geometric Word Meta-Embeddings. In Proceedings of the 5th Workshop on Representation Learning for NLP (RepL4NLP-2020), co-located with ACL 2020.
[Publisher’s copy][arXiv:2004.09219][Slides][Codes].

M. Meghawanshi, P. Jawanpuria, A. Kunchukuttan, H. Kasai, and B. Mishra. McTorch, a manifold optimization library for deep learning. In NeurIPS workshop on Machine Learning Open Source Software (MLOSS), 2018.
[arXiv:1810.01811][Project page].

M. Bhutani, P. Jawanpuria, H. Kasai, and B. Mishra. Low-rank geometric mean metric learning. In ICML workshop on Geometry in Machine Learning (GiMLi), 2018.
[Local copy][arXiv:1806.05454][Poster].

Ph.D. Thesis

P. Jawanpuria. Learning kernels for multiple predictive tasks.
Ph.D. thesis, IIT Bombay, 2015 [Local copy]. The jury included Kilian Q. Weinberger, Harish Karnick, Anirban Dasgupta, Ganesh Ramakrishnan, Sunita Sarawagi, Pushpak Bhattacharya, and Saketh Nath (supervisor).

Presentations

Gave a talk at IIT Research Symposium (2023) on “AI/ML for mobile devices at Microsoft IDC”.

Gave a talk at Microsoft FHL (2022) on “Privacy-preserving machine learning”.

Gave a talk at Microsoft FHL (2022) on “Dimensionality reduction approaches in machine learning”.

Gave a talk at Microsoft’s MLADS-SYNAPSE (2020) on our ACL work “Geometry-aware domain adaptation for unsupervised alignment of word embeddings”.

Gave a talk in the AI-CAT-NLP group within Microsoft on geometry-aware multilingual word embeddings (2020).

Talk at IIT Delhi and IIT Roorkee (2019) on optimization on manifolds and its application to learning multilingual word embeddings.

Talk at machine learning summer school (2019) on learning cross-lingual mappings of word embeddings.

Talk at Microsoft’s MLADS-SYNAPSE (2019) on our TACL work “Learning multilingual word embeddings in a latent metric space: a geometric approach”.

Talk at DiDi AI Lab in Los Angeles (2019) on optimization on manifolds and its application to learning multilingual word embeddings.

Talk at IIIT Hyderabad (2019) on low-rank matrix learning from machine learning a optimization perspective.

In ICML 2018, presented our work “A unified framework for structured low-rank matrix learning” [Slides].

Talks at IIT Madras and IIT Bombay (2018) on large-scale structured low-rank matrix learning [IITM slides][IITB slides].

Gave a talk at Amazon (2017) on dimensionality reduction in machine learning.

In ICML 2014, presented our work “On p-norm path following in multiple kernel learning for non-linear feature selection” [Slides].

In ICML 2012, presented our work “A convex feature learning formulation for latent task structure discovery” [Slides].

Patents

A patent (US11250206B2) granted for a system and method for converting a form to an action card for a chat-based application.

A patent filed on camera application of mobile phones.