Cache Miss Rate Predictability via Neural Networks
Rishikesh Jha, Saket Tiwari, Arjun Kuravally, Eliot Moss. (2018). "Cache Miss Rate Predictability via Neural Networks." NeurIPS 2018 Workshop on ML in Systems
CV
Education
- B.Tech. in Computer Science, IIT Bombay
- M.S. in Computer Science, University of Massachusetts, Amherst
- Ph.D in Computer Science, Brown University, 2025 (expected)
Work experience
- Summer 2018: Data Science Intern
- Researched the causal effects of user connections in social networks using deep variational auto-encoders for a large data set with millions of connections
- Selected as top 5 master’s students at UMass Amherst, from all the applicants.
- August 2016 - July 2017: Senior Machine Learning Engineer at LinkedIn
- Led the video classification project. Trained Deep Learning models and deployed them to production to handle more than 1000 fps, using asynchronous processing on GPU clusters
- Researched the training of Hierarchical Neural Auto-Encoders by introducing Neural Machine Translation type architecture and Tensorflow. Achieved 2x speed up.
- Experimented with multiple implementations of a popularity based model, to achieve significant improvements in user engagement. Applied a Thompson sampling based explore-exploit model to engage cold users with companies
- July 2014 - July 2016: Machine Learning Engineer at LinkedIn
- Developed and maintained a high QPS service, which classified ALL the content created on LinkedIn (millions of entities every day) to filter out spam. Designed various parts of the system: training pipelines for machine learning models, deployment, synchronous and asynchronous classification
- Worked on a Hackday project to auto-classify advertisements posted on LinkedIn using SVM. The work lead to reduced wait time for ads to go live on LinkedIn.
- May 2013 - July 2013: Software Engineering Intern at Amazon
- Developed internal tool for seamless remote compilation and deployment
Publications
Natural Option Critic
Saket Tiwari, & Philip Thomas. (2019). "Natural Option Critic." AAAI 2019
Effects of Data Geometry in Early Deep Learning
Saket Tiwari, & George Konidaris. "Effects of Data Geometry in Early Deep Learning." NeurIPS 2022
A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems
Megan M. Baker, Alexander New, Mario Aguilar-Simon, Ziad Al-Halah, Sébastien M. R. Arnold, Ese Ben-Iwhiwhu, Andrew P. Brna, Ethan Brooks, Ryan C. Brown, Zachary Daniels, Anurag Daram, Fabien Delattre, Ryan Dellana, Eric Eaton, Haotian Fu, Kristen Grauman, Jesse Hostetler, Shariq Iqbal, Cassandra Kent, Nicholas Ketz, Soheil Kolouri, George Konidaris, Dhireesha Kudithipudi, Erik Learned-Miller, Seungwon Lee, Michael L. Littman, Sandeep Madireddy, Jorge A. Mendez, Eric Q. Nguyen, Christine D. Piatko, Praveen K. Pilly, Aswin Raghavan, Abrar Rahman, Santhosh Kumar Ramakrishnan, Neale Ratzlaff, Andrea Soltoggio, Peter Stone, Indranil Sur, Zhipeng Tang, Saket Tiwari, Kyle Vedder, Felix Wang, Zifan Xu, Angel Yanguas-Gil, Harel Yedidsion, Shangqun Yu, Gautam K. Vallabha. (2023). "A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems" Neural Networks Volume 160, 2023.
Meta-Learning Parameterized Skills
Haotian Fu, Shangqun Yu, Saket Tiwari, Michael Littman, George Konidaris. (2023). "Meta-Learning Parameterized Skills." ICML 2023
Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces
Saket Tiwari, Omer Gottesman, & George Konidaris. (2025). "Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces." ICLR 2025
Skills
- Python, PyTorch, JAX, tensorflow
- Distributed systems engineering
- Remote procedure call (RPC)
- Kafka
- Spark, Hadoop
- Java, C++, C#