Its Me

Don Dennis

Ph.D. Student
Machine Learning Department
Carnegie Mellon University
  donkdennis [at] gmail [dot] com
  dondennis [at] cmu [dot] edu

I am a fifth year PhD student in the Machine Learning Department at CMU, advised by Prof. Virginia Smith. I am broadly interested in the areas of machine learning (ML), optimization and systems.

My research focus is on developing algorithms that can make ML more resource efficient, allowing us to, for instance, (a) run ML inference on tiny microcontrollers, (b) run one-shot clustering on federated device networks, and (c) improve inference latency for cloud inference settings.

In Summer '21, I was an intern working with Kazuhito Koishida at Microsoft Redmond. Prior to starting grad-school, I spent two wonderful years as a Research Fellow at Microsoft Research India, working with Prateek Jain and Harsha Simhadri. I did my undergraduate at Indian Institute of Technology, Patna.


Publications

Revisiting Cascaded Ensembles for Efficient Inference
Steven Kolawole, Don Dennis, Ameet Talwalkar, Virginia Smith
arXiv preprint arXiv:2407.02348

Progressive Knowledge Distillation: Building Ensembles for Efficient Inference
Don Dennis, Abhishek Shetty, Anish Sevekari, Kazuhito Koishida, Virginia Smith
Neural Information Processing Systems (NeurIPS), 2023.

Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts
Amrith Setlur, Don Dennis, Benjamin Eysenbach, Aditi Raghunathan, Chelsea Finn, Virginia Smith and Sergey Levine
International Conference on Learning Representations (ICLR), 2023.

Heterogeneity for the Win: Communication Efficient Distributed Clustering
Don Dennis, Tian Li, Virginia Smith
International Conference on Machine Learning (ICML), 2021.

Shallow RNN: Accurate Time-series Classification on Resource Constrained Devices
Don Dennis, Durmus Alp Emre Acar, Vikram Mandikal, Vinu Sankar Sadasivan, Harsha Vardhan Simhadri, Venkatesh Saligrama, Prateek Jain
Neural Information Processing Systems (NeurIPS), 2019
[PDF] [BibTeX] [Code] [Slides] [Demo Video]

Multiple Instance Learning for Sequential Data Classification on Resource Constrained Devices
Don Dennis, Chirag Pabbaraju, Harsha Vardhan Simhadri, Prateek Jain
Neural Information Processing Systems (NeurIPS), 2018
[PDF] [BibTeX] [Code] [Slides] [Poster] [Video]

EdgeML: Edge of Machine Learning --- Demonstration of Low Resource Keyword Spotting
Don Dennis, Harsha Simhadri, Prateek Jain
Workshop on Machine Learning on the Phone and other Consumer Devices (MLPCD 2), NeurIPS 2018

GesturePod: Programmable Gesture Recognition for Augmenting Assistive Devices
Shishir Patil, Don Dennis, Chirag Pabbaraju, Rajanikant Deshmukh, Harsha Vardhan Simhadri, Manik Varma, Prateek Jain
ACM User Interface Software and Technology Symposium (UIST), 2019
[PDF] [BibTeX] [Code] [Microsoft Technical Report] [Demo Video]

Single Cycle RISC-V Micro Architecture Processor and its FPGA Prototype
Don Dennis, Ayushi Priyam, Sukhpreet Singh Virk, Sajal Agrawal, Tanuj Sharma, Arijit Mondal, Kailash Chandra Ray
International Symposium on Embedded Computing and System Design (ISED), 2017
[PDF] [Code]