The earth mover’s distance (EMD) is a scalar measure of dissimilarity between histograms. Introduced over 200 years ago, the EMD has played a central role in linear programming, information retrieval, and is emerging as useful objective in machine learning. During the 1990’s, the EMD was generalized from a functional that acts …
Uncertainty penetrates in every corner of machine learning, ranging from data and adversary uncertainty, model uncertainty, all the way to dynamics uncertainty, even task uncertainty, and beyond. When faced with complicated machine learning tasks under various forms of uncertainty, the traditional empirical risk minimization framework, along with the rich off-the-shelf …
Through recent advances in machine learning (ML) technology, we are getting closer to realizing the broadly stated goal of “arti cially intelligent”, autonomous agents. In many cases — like cognitive radio, swarm robotics, and e-commerce — these agents will not be acting in isolation, and it is critical for them to …
When there is insufficient data to learn a globally accurate model, successful learning can still be possible if we take into account the particular task for which the learned model will be employed. Learning a possibly incorrect or incomplete model, which performs well in the subsequent prediction (classi cation or decision …
Billions of passwords are compromised in the last few years and are available online. Attackers are using these leaked passwords to compromise user accounts on other not-yet-leaked web services. Because many users reuse their passwords across different web services, such attacks are the most imminent threat to users’ account security …
Abstract: This talk will discuss a variety of recent papers, mostly from 2019. The talk will be organized around four “themes” of deep learning: Domain Independence Information theory Moore’s Law of AI Self-Supervised Pretraining Vector Quantization Mutual Information Objectives
The estimation of evolutionary trees (called phylogenies) is an essential step in biological research; however large-scale phylogeny estimation continues to be computationally challenging. Many of the current leading methods are heuristics for NP-hard optimization problems, and these methods typically have limited parallelism for improving scalability to larger numbers of species. In this talk, I …
Abstract: In this talk I will introduce two new subspace models: Mixture Matrix Completion, and Subspace Splitting. Both models are motivated by metagenomics, recommender systems, and dimensionality reduction, and are tightly related to low-rank matrix completion, subspace clustering, robust matched subspace detection, and the maximum feasible subsystem problem. I will …