Events
Seminar @ Cornell Tech: ECE Candidate, Chinmay Maheshwari
Machine Learning Algorithms for Efficient and Fair Operations in Societal-Scale Systems
The pervasive integration of Machine Learning (ML) and Artificial Intelligence (AI) into societal-scale systems is reshaping our interactions within physical infrastructure and other online services. Unfortunately, the conventional paradigm of ML, relying on i.i.d. data from a stationary environment, proves inadequate in these systems. Specifically, there are two key challenges when using the conventional ML paradigm for design and analysis of algorithms in societal-scale systems. First, these algorithms need to simultaneously learn and adapt in dynamic, uncertain, and resource-constrained environments while interacting in an independent and decentralized manner, without any coordination and communication with others. This results in non-stationarity in the feedback received by each algorithm. Second, the data generated in these systems is used to make consequential decisions, such as designing tolls on transportation networks. As the data in such systems is generated from the strategic responses of reactive users, these datasets are biased and correlated. This underscores the need for a nuanced design of ML algorithms to ensure efficient and fair operations.
Drawing on examples from his research, Chinmay Maheshwari will highlight how to incorporate tools from diverse disciplines, such as algorithmic game theory, market design, optimization, and dynamical systems, to effectively overcome the challenges associated with the standard ML paradigm. Specifically, Maheshwari will discuss design and analysis techniques for novel decentralized learning algorithms in two prevalent frameworks of multi-agent interactions: two-sided matching markets and multi-agent reinforcement learning. Additionally, by leveraging high-fidelity datasets capturing real-world, societal-scale interactions in the San Francisco Bay Area freeway network, Maheshwari will illustrate how game-theoretic modeling can be fused within ML pipeline to design tolling schemes that not only alleviate congestion but also minimize its disproportionate impact based on the income level of travelers.
The talk will conclude by highlighting open directions in the design and analysis of ML algorithms to support efficient and fair decision-making in societal-scale systems.
Speaker Bio
Chinmay Maheshwari is PhD candidate in the Electrical Engineering and Computer Sciences department at University of California Berkeley. He obtained M. Tech and B. Tech degrees from Indian Institute of Technology (IIT) Bombay, both in 2019, where he received institute academic medal. His research focuses on developing theoretical, algorithmic, and methodological foundations for the design and analysis of machine learning algorithms operating in societal-scale systems. On the technical side, his research builds on and extends tools and techniques from machine learning, algorithmic game theory, market design, dynamical systems, control theory and optimization.