Farzana Beente Yusuf
Knight Foundation School of Computing and Information Sciences
Farzana Beente Yusuf is a Ph.D. candidate in the Knight Foundation School of Computing and Information Sciences (KFSCIS) at Florida International University (FIU). Under the supervision of Prof. Giri Narasimhan, her dissertation focused on adapting techniques from the emerging field of Explainable AI (XAI) to problems from two disparate fields, i.e., storage systems and public policy analysis. She received a B.Sc degree in Computer Science and Engineering from the Bangladesh University of Engineering and Technology in 2013. She worked as a Software Engineer in Bangladesh from 2013 to 2016 before joining FIU. She received a Master’s degree in Computer Science from FIU in 2019 and worked as a Research intern at Google Inc. in Summer 2020. She has published papers at several top conferences and workshops, including FAST’21, DG.O’21, and NeurIPS LXAI’19. She was awarded a Fellowship from CRA-W to join Grad Cohort in 2018 and 2019.
Advances in Artificial Intelligence (AI) have led to spectacular innovations and sophisticated systems for tasks that were thought to be capable only by humans. Examples include playing chess and Go, face and voice recognition, driving of vehicles, and more. In recent years, the impact of AI has moved beyond offering mere predictive models into building explainable models that appeal to human logic and intuition because they ensure transparency and simplicity and can be used to make meaningful decisions in real-world applications. A second trend in AI is characterized by important advancements in the realm of causal reasoning. Identifying causal relationships is an important aspect of scientific endeavor in a variety of fields. Causal models and Bayesian inference can help us gain better domain-specific insight and make better data-driven decisions. The main objective of this dissertation was to adapt theoretically sound AI-based data-analytic approaches to solve domain-specific problems in the two unrelated fields of Storage Systems and Public Policy. For the first task, we considered the well-studied problem of cache replacement problem in computing systems, which can be modeled as a variant of the well-known Multi-Armed Bandit (MAB) problem with delayed feedback and decaying costs, and developed an algorithm called EXP4-DFDC. We proved theoretically that EXP4-DFDC exhibits an important feature called vanishing regret. Based on the theoretical analysis, we designed a machine learning algorithm called ALeCaR, with adaptive hyperparameters. We used extensive experiments on a wide range of workloads to show that ALeCaR performed better than LeCaR, the best machine learning algorithm for cache replacement at that time. We concluded that reinforcement machine learning can offer an outstanding approach for implementing cache management policies. For the second task, we used Bayesian networks to analyze the service request data from three 311 centers providing non-emergency services in the cities of Miami-Dade, New York City, and San Francisco. Using a causal inference approach, this study investigated the presence of inequities in the quality of the 311 service to neighborhoods with varying demographics and socioeconomic status. We concluded that the services provided by the local governments showed no detectable biases on the basis of race, ethnicity, or socioeconomic status.