This course explores fundamental tools for analyzing and designing trustworthy machine learning systems through the lens of information theory, statistics, and learning theory. We study reliability guarantees for modern models by quantifying generalization, fairness, and privacy. We will also introduce practical aspects of watermarking and IP protection for large generative models.
This upper‑division course gives students a rigorous, security‑first tour of modern blockchain systems. We begin with the cryptographic building blocks (hash functions, digital signatures, zero‑knowledge proofs) and quickly progress to consensus mechanisms such as Proof‑of‑Work, Proof‑of‑Stake, and BFT‑style protocols. Using Bitcoin and Ethereum as primary case studies, we dissect ledger structures, peer‑to‑peer networking, transaction execution, and economic incentives.
This course provides a rigorous yet accessible introduction to the algorithmic foundations of optimization, with a focus on problems and applications in computer science and engineering. Topics include convex sets and functions; unconstrained methods such as gradient descent and Newton’s method; projection and gradient‐projection; equality and inequality constrained optimization via Lagrange multipliers and KKT conditions; duality theory; stochastic gradient techniques; and subgradient methods for nondifferentiable problems.
Enterprise systems are large-scale software applications to support business operations; they typically include software systems for data management, business process/workflow management, information flows, reporting, and data analytics. Focusing only the data management aspect, a typical enterprise has to struggle with many data integration difficulties, since its data are usually spread around many database systems, workflow systems, file systems, etc. and in a variety of form possibly with no coherent semantics.
This course explores advanced topics in highly scalable Internet services and their underlying systems’ architecture. Software today is primarily delivered as a service: accessible globally via web browsers and mobile applications, and backed by millions of servers.
This course covers advanced topics on neural information retrieval and web search engines. The content to be focused includes indexing, retrieval, ranking, and system optimization for large-scale search services with deep machine learning and NLP models. Recent papers in top conferences will be reviewed, and issues in relevance, efficiency, and scalability will be studied.
Once the quarter starts, instructor approval is required to maintain enrollment in the course.
Artificial intelligence holds enormous promise for accelerating scientific discovery, yet its “black box” nature and data-hungry architectures often hinder adoption in domains where interpretability, physical consistency, and sparse data prevail. This course addresses these challenges by developing a unified framework that integrates three complementary, domain-informed representations—topological features, physics-based constraints, and higher-order relational structures—into end-to-end, scalable AI models.
Networks or graphs are a natural way to represent a variety of interacting complex systems - from disease spreading and brain networks, to social networks and political networks.
In recent years, the application of Machine Learning (ML) tools has extended beyond traditional domains like image classification and Natural Language Processing (NLP) to tackle a variety of classification, detection, and control problems. More notably, the adoption of ML in addressing networking issues has emerged as a significant area of interest. However, implementing ML solutions for networked systems presents unique challenges that go beyond merely adapting tools designed for other fields.
No description currently available