Accurate simulations of physical phenomena governed by partial differential equations (PDEs) are foundational to scientific computing. While traditional numerical methods have proven effective, they remain computationally intensive, particularly for complex, large-scale systems. This talk introduces the neural operator, a machine learning framework that approximates solution operators in infinite-dimensional spaces, enabling efficient and scalable PDE simulations […]
IDEAS
Calendar of Events
S
Sun
|
M
Mon
|
T
Tue
|
W
Wed
|
T
Thu
|
F
Fri
|
S
Sat
|
---|---|---|---|---|---|---|
0 events,
|
0 events,
|
1 event,
-
|
0 events,
|
1 event,
-
The remarkable recent success of Machine Learning (ML) is driven by our ability to develop and deploy interactive models that can solve complicated tasks by understanding and adapting to the ever-changing state of the world. However, the development of such models demands significant data and computing resources. Moreover, as these models increasingly interact with humans, […] |
0 events,
|
0 events,
|
0 events,
|
0 events,
|
0 events,
|
0 events,
|
1 event,
-
Zoom link https://upenn.zoom.us/j/98220304722 Abstract We present computational tools for analyzing and designing first-order methods in parametric convex optimization. These methods are popular for their low per-iteration cost and warm-starting capabilities. However, precisely quantifying the number of iterations required to compute high-quality solutions remains a key challenge, especially in real-time applications. First, we introduce a […] |
0 events,
|
0 events,
|
0 events,
|
0 events,
|
0 events,
|
0 events,
|
0 events,
|
0 events,
|
0 events,
|
0 events,
|
0 events,
|
1 event,
-
Machine learning is transforming numerous aspects of modern society, and its expanding use in high-stakes applications calls for responsible development. In this talk, I will present my research on the foundations and methodologies for building trustworthy ML, centered on three interconnected challenges: generalization, memorization, and privacy. First, I will show how information-theoretic tools can be […] |
0 events,
|
2 events,
-
Over the past decade, large-scale pre-training followed by alignment has revolutionized natural language processing and computer vision. Yet, robotics remains constrained by the scarcity of real-world data. In this talk, I will present our systematic approach to overcoming this bottleneck by building increasingly rich world models from data. I will first introduce our distilled feature […]
-
Zoom link: https://upenn.zoom.us/j/98220304722 Abstract: Modern ML models produce valuable predictions across various applications, influencing people’s lives, opportunities, and scientific advancements. However, these systems can fail in unexpected ways, generating unreliable inferences and perpetuating biases present in the data. These issues are particularly troubling in high-stakes applications, where models are trained on increasingly diverse, incomplete, and […] |
0 events,
|
0 events,
|
0 events,
|
0 events,
|
0 events,
|
0 events,
|
1 event,
-
Zoom link: https://upenn.zoom.us/j/98220304722 Abstract: We study the generalization properties of neural networks through the lens of data complexity. Recent work by Buzaglo et al. (2024) shows that random (nearly) interpolating networks generalize, provided there is a small ``teacher'' network that achieves small excess risk. We give a short single-sample PAC-Bayes proof of this result and […] |
0 events,
|
0 events,
|
0 events,
|
0 events,
|
0 events,
|
0 events,
|
1 event,
-
Zoom link: https://upenn.zoom.us/j/98220304722 Abstract I will present recent work by my research group on the design and analysis of stochastic-gradient-based algorithms for solving nonconvex constrained optimization problems, which may arise, for example, in informed supervised learning. I will focus in particular on algorithmic strategies that have consistently been shown to exhibit the best practical […] |
0 events,
|
0 events,
|