Computer Science Lecture Series

Towards Adaptive Intelligence

Aditya Kusupati (University of Washington)

Tuesday, Feb 20, 2024

Intelligent systems powered by machine learning are ubiquitous today. However, their current rigid design fails and requires dedicated efforts to cater to ever-changing data, use cases, and deployment settings. In this talk, I will present my work towards enabling adaptive machine learning solutions for flexible and seamless deployment across widely changing scenarios through the lens of web search. First, I present Matryoshka embeddings for adaptive data representations that can power web-scale adaptive retrieval. Next, I extend these principles to the neural networks, crafting MatFormer models that adapt their computational footprint based on input and device with minimal overhead during deployment. Further, to address the inherent rigidity in the design of web search systems, I will dive into differentiable search solutions, fundamentally rethinking how large-scale AI pipelines harness data for continuous improvement. Finally, I conclude with future works directed towards adaptive contextual and continual intelligence across disciplines.

Speaker Bio

Aditya Kusupati is a final year PhD student at the University of Washington advised by Ali Farhadi and Sham Kakade. He is also a Student Researcher at Google Research in the Perception team. His research focuses on designing fundamental Machine Learning algorithms with strong empirical performance & real-world deployability geared towards enabling efficient, elastic, and contextual intelligence. Some of his algorithms are deployed at Google, OpenAI, Pinterest, and Microsoft serving over a billion users daily, and his work has been awarded a Google Research grant. He also has won several awards including a Best Paper award at the NeurIPS ENLSP workshop and a Best Paper Runner-up award at BuildSys. Previously, he was a Research Fellow at Microsoft Research and completed his undergraduate degree from IIT Bombay.


Sham Kakade and Milind Tambe


Ester Ramirez