Computer Engineering Seminar Series

As ML on structured data becomes prevalent across enterprises, improving resource efficiency is crucial to lower costs and energy consumption. Designing systems for learning on structured data is challenging because of the large number of models. Parameters and data access patterns. We identify that current systems are bottlenecked by data movement which results in poor resource utilization and inefficient training.

 To mitigate the bias exhibited by machine learning models, fairness criteria can be integrated into the training process to ensure fair treatment across all demographics, but it often comes at the expense of model performance. Understanding such tradeoffs, therefore, underlies the design of optimal and fair algorithms. In this talk, I will first discuss our recent work on characterizing the inherent tradeoff between fairness and accuracy in both classification and regression problems, where we show that the cost of fairness could be characterized by the optimal value of a Wasserstein-barycenter problem. Then I will show that the complexity of learning the optimal fair predictor is the same as learning the Bayes predictor and present a post-processing algorithm based on the solution to the Wasserstein-barycenter problem that derives the optimal fair predictors from Bayes score functions

Modern cloud-based applications adhere to a microservices architecture, encompassing numerous components interconnected through intricate dependencies, operating within a distributed environment. This talk gives an overview of three recent research projects aimed at solving practical challenges in promptly identifying and diagnosing outages.

Constraint-based program synthesis techniques have been widely used in numerous settings. However, synthesizing programs that use libraries remains a major challenge. To handle complex or black-box libraries, the state of the art is to provide carefully crafted mocks or models to the synthesizer, requiring extra manual work. We address this challenge by proposing Toshokan, a new synthesis framework as an alternative approach in which library-using programs can be generated without any user-provided artifacts at the cost of moderate performance overhead.

Advances in neural network revolutionized modern machine intelligence, but important challenges remain when applying these solutions in IoT contexts; specifically, in cost-sensitive applications on lower-end embedded devices. The talk discusses challenges in offering real-time machine intelligence services at the edge to support applications in resource constrained environments.

Most cloud applications use a large number of smaller sub-components (called microservices) that interact with each other in the form of a complex graph to provide the overall functionality to the user. While the modularity of the microservice architecture is beneficial for rapid software development, maintaining and debugging such a system quickly in cases of failure is challenging.