FOLDS SEMINAR: The Hidden Width of Deep ResNets
Zoom link: https://upenn.zoom.us/j/6130182858 We present a mathematical framework to analyze the training dynamics of deep ResNets that rigorously captures practical architectures (including Transformers) trained from standard random initializations. Our […]
ASSET Seminar: “Testing AI’s Implicit World Models”
Many of the robustness properties that are required for real-world applications of AI would be realized by a model that has understood the world. But it is unclear how to […]
ASSET Seminar: “When Is a Conformal Set, a Conformal Set?”
The two most popular vehicles for communicating uncertainty in the estimates of an unknown quantity are confidence sets and conformal sets. The set produced and its corresponding probability guarantee (conditional […]
ASSET Seminar: “Unpacking the Unintended Consequences of AI in Education”
The rapid integration of AI into educational settings presents opportunities and challenges—this talk will discuss findings from three large-scale field studies investigating the impact of AI on student learning. First, […]
FOLDS seminar: Function Space Perspectives on Neural Networks
Zoom link: https://upenn.zoom.us/j/98220304722 This talk reviews a theory of the functions learned by neural networks with Rectified Linear Unit (ReLU) activations. At its core is the observation that deep ReLU […]
FOLDS seminar: Learning in Strategic Queuing
Zoom link: https://upenn.zoom.us/j/98220304722 Over the last two decades we have developed good understanding how to quantify the impact of strategic user behavior on outcomes in many games (including traffic routing […]
FOLDS Seminar: ACS: An interactive framework for machine-assisted selection with model-free guarantees
Zoom link: https://upenn.zoom.us/j/98220304722 In this talk, I will introduce adaptive conformal selection (ACS), an interactive framework for model-free selection with guaranteed error control. Building on conformal selection (Jin and Candès, […]
FOLDS seminar: Weak to Strong Generalization in Random Feature Models
Zoom link: https://upenn.zoom.us/j/98220304722 Weak-to-Strong Generalization (Burns et al., 2023) is the phenomenon whereby a strong student, say GPT-4, learns a task from a weak teacher, say GPT-2, and ends up […]
FOLDS seminar: An Information Geometric Understanding of Deep Learning
Zoom link: https://upenn.zoom.us/j/98220304722 I will argue that properties of natural data are what predominantly make deep networks so effective. To that end, I will show that deep networks work well […]
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 […]