While recent advances in natural language processing (NLP) have greatly enhanced our ability to analyze online text, distilling broad social-oriented research questions into tasks concrete enough for NLP models remains challenging. In this work, we develop state-of-the-art NLP models grounded in frameworks from social theory in order to analyze...
Carnegie Mellon University and University of Washington
Building Language Technologies for Analyzing Online Activism
Meta-learning or learning to learn has been shown to be a powerful tool for fast learning over unseen tasks by efficiently extracting the knowledge from a range of observed tasks. Such empirical success thus highly motivates theoretical understanding of the performance guarantee of meta-learning, which will serve to guide the better design of meta...
Department of Electrical and Computer Engineering, The Ohio State University
Predicting life outcomes is a challenging task even for advanced machine learning (ML) algorithms. At the same time, accurately predicting these outcomes has important implications in providing targeted assistance and in improving policy making.
Problems of algorithmic bias are often framed in terms of lack of representative data or formal fairness optimization constraints to be applied to automated decision-making systems. However, these discussions sidestep deeper issues with data used in AI, including problematic categorizations and the extractive logics of crowdwork and data mining....
Beyond Bias: Algorithmic Unfairness, Infrastructure, and Genealogies of Data
Matt is an assistant professor at Princeton University in the Department of Computer Science. His primary research interest is in Algorithmic Mechanism Design: algorithm design in settings where users have their own incentives. He is also interested more broadly in Algorithmic Game Theory, Algorithms Under Uncertainty, and Theoretical Computer...
The Princeton Dialogues in AI and Work is a research agenda investigating what algorithmic and predictive data-driven tools mean to stakeholders across society. Building on prior work in the Dialogues in AI and Ethics case study series, the current phase of research takes an empirical, sociotechnical focus on how the different communities will...
Elizabeth Anne Watkins
Introducing Dialogues in AI and Work: Three Works-in-Progress and a Call to Action
Whether operating in a manufacturing plant or assisting within the home, many robotic tasks require safe and controlled interaction with a complex and changing world. However, state-of-the-art approaches to both learning and control are most effective when this interaction either occurs in highly structured settings or at slow speeds unsuitable...
Many data-driven problems in the modern world involve solving nonconvex optimization problems. The large-scale nature of many of these problems also necessitates the use of first-order optimization methods, i.e., methods that rely only on the gradient information, for computational purposes. But the first-order optimization methods, which include...
Visiting Fellow, Center for Statistics and Machine Learning | Department of Statistics, Rutgers University
Computer vision models trained on unparalleled amounts of data have revolutionized many applications. However, more and more historical societal biases are making their way into these seemingly innocuous systems.
Fairness in Visual Recognition: Redesigning the Datasets, Improving the Models and Diversifying the AI Leadership
Nuclear fusion power is a potential source of safe, non-carbon-emitting and virtually limitless energy. The tokamak is a promising approach to fusion based on magnetic plasma confinement, constituting a complex physical system with many control challenges. However, plasma instabilities pose an existential threat to a reactor, which has not yet...
Real-Time Remote Sensing and Fusion Plasma Control: A Reservoir Computing Approach
Nonsmooth regularisers are widely used in machine learning for enforcing solution structures (such as the l1 norm for sparsity or the nuclear norm for low rank). State of the art solvers are typically first order methods or coordinate descent methods which handle nonsmoothness by careful smooth approximations and support pruning. In this work, we...
Inspired by the proposal of tangent kernels of neural networks (NNs), a recent research line aims to design kernels with a better generalization performance on standard datasets. Indeed, a few recent works showed that certain kernel machines perform as well as NNs on certain datasets, despite their separations in specific cases implied by...
Department of Statistics at UC Berkeley
The efficiency of kernel methods on structured datasets
VisualAI lab focuses on bringing together the fields of computer vision, machine learning, human-machine interaction as well as fairness, accountability and transparency. In this talk, we will introduce the general goal of the lab, and how to build an agent that can understand and follow human’s language to perform tasks.
While exciting progress has been made in understanding the global convergence of vanilla gradient methods for solving challenging nonconvex problems in statistical estimation and machine learning, their computational efficacy is still far from satisfactory for ill-posed or ill-conditioned problems. In this talk, we discuss how the trick of...
Carnegie Mellon University
Preconditioning Helps: Faster Convergence in Statistical and Reinforcement Learning
In this talk we study the problem of signal recovery for group models. More precisely for a given set of groups, each containing a small subset of indices, and for given linear sketches of the true signal vector which is known to be group-sparse in the sense that its support is contained in the union of a small number of these groups, we study...
Research Chair of Data Science, African Institute of Mathematical Sciences and Stellenbosch University, South Africa
Discrete Optimization Methods for Group Model Selection in Compressed Sensing