: Generative priors are effective countermeasures to combat the curse of dimensionality, and enable efficient learning and inversion that otherwise are ill-posed, in data science. This talk begins with the classical low-rank prior, and introduces scaled gradient descent (ScaledGD), a simple iterative approach to directly recover the low-rank factors for a wide range of matrix […]
Mass spectrometry-based methods such as covalent labeling, surface induced dissociation (SID) or ion mobility (IM) are increasingly used to obtain information about protein structure. However, in contrast to other high-resolution structure determination methods, this information is not sufficient to deduce all atom coordinates and can only inform on certain elements of structure, such as solvent […]
Abstract: In this talk, we introduce a new class of problems related to integrating inertial measurements obtained from an IMU that play a significant role in navigation combined with visual data. While there have been tremendous technological advances in the precision of instrumentation, integrating acceleration and angular velocity still suffers from drift in the displacement […]
Zoom link: https://upenn.zoom.us/j/98843354016
Algorithms are increasingly integrated into various societal applications, often directly interacting with people and communities. This highlights the importance of understanding the interplay between algorithmic decisions and economic incentives when designing machine learning algorithms. In this talk, I will explore two examples of this dynamic through the lens of privacy in data markets and fairness […]
Deep learning's success stems from the ability of neural networks to automatically discover meaningful representations from raw data. In this talk, I will describe some recent insights into how optimization enables this learning process. First, I will show how optimization algorithms exhibit surprisingly rich dynamics when training neural networks, and how these complex dynamics are […]
Conventional approaches to scientific discovery often prioritize building larger sensors, gathering more data, and scaling up computational power. In this talk, I will present a complementary perspective: extracting insights hidden in the data we already have. The key lies in using AI not as a black-box predictor, but as a tool for interpreting data through […]
As learning algorithms become increasingly capable of acting autonomously, it is important to better understand the behavior that results from their interactions. For example, a pervasive challenge in multi-agent learning settings, which spans both theory and practice and dates back decades, has been the failure of convergence for iterative algorithms such as gradient descent. Accordingly, […]
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 […]
