FOLDS seminar: A New Paradigm for Learning with Distribution Shift
Zoom link: https://upenn.zoom.us/j/98220304722 We revisit the fundamental problem of learning with distribution shift, where a learner is given labeled samples from training distribution D, unlabeled samples from test distribution D′ and […]
FOLDS seminar: Theory and practice of LLM quantization
Zoom link: https://upenn.zoom.us/j/98220304722 Modern LLMs process information by repeatedly applying a basic primitive of matrix multiplication. Estimates show that about 60-84% of the energy consumed by LLMs goes into […]
FOLDS seminar: Propagation-of-Chaos in Shallow Neural Networks beyond Logarithmic Time.
Zoom link: https://upenn.zoom.us/j/98220304722 The analysis of gradient-based learning of Neural Networks remains an outstanding challenge, even for the simplest shallow architectures. A powerful mathematical framework that has emerged over recent […]
FOLDS seminar: Heaviside Composite Optimization: A new paradigm of optimization
Zoom link: https://upenn.zoom.us/j/98220304722 A Heaviside function is an indicator function of a semi-infinite interval. A Heaviside composite function is a Heaviside function composed with a multivariate function that may be […]
FOLDS seminar: Algorithmic stability for regression and classification
In a supervised learning setting, a model fitting algorithm is unstable if small perturbations to the input (the training data) can often lead to large perturbations in the output (say, […]
ESE PhD Thesis Defense – “Magnetostatic Surface Wave and Surface Acoustic Wave Devices for Tunable and Energy Efficient Radio Frequency Filters”
Tunable and energy-efficient filters are key components in modern wireless communication, where RF front-end systems must operate across multiple frequency bands while minimizing power consumption. This thesis focuses on the […]
FOLDS Seminar: Positive random walks and positive-semidefinite random matrices
On the real line, a random walk that can only move in the positive direction is very unlikely to remain close to its starting point. After a fixed number of […]
ESE PhD Thesis Defense – “Design and Characterization of AlScN-Based Ferroelectric Devices for Non-Volatile Memory Applications”
Ferroelectric materials have emerged as promising candidates for next-generation non-volatile memory technologies due to their intrinsic remnant polarization and fast switching dynamics. Among them, aluminum scandium nitride (AlScN) stands out […]
ESE Guest Seminar – “The Nonlinear Small-Gain Theory for Networks and Control”
The world is nonlinear and linked. In this talk, I will present the origin of the small-gain theory and show that it serves as an important systematic tool for addressing […]
ESE Fall Seminar – “Engineering with Atomic-Scale Building Blocks: From Complex Properties to Functional Devices”
As the demand for computing power and complexity continues to grow, developing new paradigms of information processing is essential. Unconventional functionalities arising from atomically engineered materials offer pathways to address […]