location: Researchers' Link
SILO: Forgetting sensitive data on open-weight models with guarantees
Abstract: The proliferation of open-weight models trained on vast, public datasets (that often include sensitive data) introduces a critical privacy challenge: how do we erase the influence of sensitive incorrect, or obsolete data after a model is pre-trained? While machine unlearning offers a promising direction, we argue that current methods …
SILO: Characterizing the power of MCMC methods for sparse estimation
Abstract: Markov Chain Monte Carlo (MCMC) and local-search optimization methods have been extensively used in the practice of statistical research for many decades now. However, their exact theoretical performance has been strikingly eluding even for simple parametric estimation tasks. This is in stark contrast to other classes of estimators such …
SILO: Minimizing quadratics over integers
Abstract: Mixed integer quadratic programming is the problem of minimizing a quadratic polynomial over points in a polyhedral region with some integer components. It is a natural extension of mixed integer linear programming, and it has a wide array of applications. In this talk, I will survey some recent theoretical …
SILO: Optimal vintage factor analysis with deflation varimax
Abstract: Vintage factor analysis is one important type of factor analysis that aims to first find a low-dimensional representation of the original data, and then to seek a rotation such that the rotated low-dimensional representation is scientifically meaningful. The most widely used vintage factor analysis is the Principal Component Analysis …
SILO: Characterizing structure in deep classifiers through Neural Collapse
Abstract: In this talk I will describe recent progress in characterizing structure that emerges during the training of deep neural networks for classification. Neural Collapse is a phenomenon that emerges during the training of deep classifiers in which the top-layer feature embeddings of samples from the same class tend to …
Efficient Compressed Sensing with L0 Projections
Many applications concern sparse signals, for example, detecting anomalies from the differences between consecutive images taken by surveillance cameras. In general, anomaly events are sparse. This talk focuses on the problem of recovering a K-sparse signal in N dimensions (coordinates). Classical theories in compressed sensing say the required number of …