I am a second year PhD at Rice with Dr. Anshumali. My research deals with solving challenges that appear in large scale machine learning with focus on hashing and sketching techniques.

PUBLICATIONS

Desai, Aditya, Li Chou, and Anshumali Shrivastava. "Random Offset Block Embedding (ROBE) for compressed embedding tables in deep learning recommendation systems." Proceedings of Machine Learning and Systems 4 (2022): 762-778. [Outstanding paper award] (link)

Desai, Aditya, Zhaozhuo Xu, Menal Gupta, Anu Chandran, Antoine Vial-Aussavy, and Anshumali Shrivastava. "Raw Nav-merge Seismic Data to Subsurface Properties with MLP based Multi-Modal Information Unscrambler." In Thirty-Fifth Conference on Neural Information Processing Systems. 2021. (link)

Dai, Zhenwei, Aditya Desai, Reinhard Heckel, and Anshumali Shrivastava. "Active Sampling Count Sketch (ASCS) for Online Sparse Estimation of a Trillion Scale Covariance Matrix." In Proceedings of the 2021 International Conference on Management of Data, pp. 352-364. 2021.) (link)

Desai, Aditya, Sumit Gulwani, Vineet Hingorani, Nidhi Jain, Amey Karkare, Mark Marron, and Subhajit Roy. "Program synthesis using natural language." In Proceedings of the 38th International Conference on Software Engineering, pp. 345-356. 2016. ).(link)

Desai, Aditya, Era Jain, and Subhajit Roy. "Facilitating Verification in Program Loops by Identification of Static Iteration Patterns." In 2013 20th Asia-Pacific Software Engineering Conference (APSEC), vol. 1, pp. 83-90. IEEE, 2013.) (link)

PREPRINTS

Desai, Aditya, Keren Zhou, and Anshumali Shrivastava. "Efficient model compression with Random Operation Access Specific Tile (ROAST) hashing." arXiv preprint arXiv:2207.10702 (2022).

Desai, Aditya, and Anshumali Shrivastava. "The trade-offs of model size in large recommendation models: A 10000$\times $ compressed criteo-tb DLRM model (100 GB parameters to mere 10MB)." arXiv preprint arXiv:2207.10731 (2022).

Desai, Aditya, Benjamin Coleman, and Anshumali Shrivastava. "Density Sketches for Sampling and Estimation." arXiv preprint arXiv:2102.12301 (2021).

Desai, Aditya, Shashank Sonkar, Anshumali Shrivastava and Richard Baranuik “Embedding Models through the lens of stable coloring” open review

Desai, Aditya, Yanzhou Pan, Kuangyuan Sun, Li Chou, and Anshumali Shrivastava. "Semantically Constrained Memory Allocation (SCMA) for Embedding in Efficient Recommendation Systems." arXiv preprint arXiv:2103.06124 (2021).