Shubham Agarwal

Research Associate


I work in the area of Machine Learning for Systems and Systems for Machine Learning, with a primary focus on enhancing the reliability and scalability of systems. My recent projects have involved developing predictive models to anticipate cloud outages and creating systems that enhance the resource efficiency of generative models. My goal is to bridge the growing resource demands of emerging technologies while optimizing system performance.


ScaleViz: Scaling Visualization Recommendation Models on Large Data

Ahmad, G., Agarwal, S., Mitra, S., Rossi, R., Doshi, M., Paila, S. (May. 7, 2024)

Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD)

Approximate Caching for Efficiently Serving Diffusion Models

Agarwal, S., Mitra, S., Chakraborty, S., Karanam, S., Mukherjee, K., Saini, S. (Apr. 16, 2024)

USENIX Symposium on Networked Systems Design and Implementation (NSDI)

Outage-Watch: Early Prediction of Outages using Extreme Event Regularizer

Agarwal, S., Chakraborty, S., Garg, S., Bisht, S., Jain, C., Gonuguntla, A., Saini, S. (Dec. 6, 2023)

Foundations of Software Engineering (ESEC/FSE)

ESRO: Experience Assisted Service Reliability against Outages

Chakraborty, S., Agarwal, S., Garg, S., Sethia, A., Pandey, U., Aggarwal, V., Saini, S. (Sep. 14, 2023)

Automated Software Engineering (ASE)

Fast Natural Language Based Data Exploration with Samples

Agarwal, S., Chan, G., Garg, S., Yu, T., Mitra, S. (Jun. 18, 2023)

International Conference on Management of Data (SIGMOD)

CausIL: Causal Graph for Instance Level Microservice Data

Chakraborty, S., Agarwal, S., Garg, S., Chauhan, A., Saini, S. (Apr. 30, 2023)

Proceedings of the Web Conference (WWW)