CS Department Colloquium Series

Machine learning systems are not robust—they suffer large drops in accuracy when deployed in different environments from what they were trained on.

In this talk, I will introduce work on fundamental techniques for building and deploying effective natural language processing (NLP) systems that are also efficient and reliable.

Pre-trained models have become a cornerstone of machine learning thanks to the fact that they can provide improved performance with less labeled data on downstream tasks.

Machine learning systems are deployed in consequential domains such as education, employment, and credit, where decisions have profound effects on socioeconomic opportunity and life outcomes. High stakes decision settings present new statistical, algorithmic, and ethical challenges.

Generative language models have recently exploded in popularity, with services such as ChatGPT deployed to millions of users.

Finding a good computational representation for a problem allows us to map high level objectives to low level details and select the appropriate set of algorithmic tools.

As networked systems become critical infrastructure, their design must reflect their new societal role. Today, we build systems with hundreds of heuristics but often do not understand their inherent and emergent behaviors.

Reinforcement learning (RL) promises to harness the power of machine learning to solve sequential decision making problems, with the potential to enable applications ranging from robotics to chemistry.

Our interconnected world is increasingly reliant on distributed systems of unprecedented scale, serving applications which must share state across the globe. And, despite decades of research, we're still not sure how to program them!

Machine learning (ML) models training will continue to grow to consume more cycles, their inference will proliferate on more kinds of devices, and their capabilities will be used on more domains.