ASSET

ABSTRACT: As predictive and generative models are increasingly being deployed in various high-stakes applications in critical domains including healthcare, law, policy and finance, it becomes important to ensure that relevant stakeholders understand the behaviors and outputs of these models so that they can determine if and when to intervene. To this end, several techniques have […]

ABSTRACT: From robotics to autonomous vehicles, machine learning agents deployed in the physical world (“physical agents”) promise to revolutionize endeavors ranging from manufacturing to agriculture to domestic labor. In this talk, we will develop mathematical foundations, from the ground up, for how to carry out this vision. We will begin our investigation by examining linear […]

ABSTRACT: The rapid advance of AI driven by Large Language Models (LLMs), like ChatGPT, has led to impressive results across a range of different use cases. This has included several models developed for the medical domain which have exhibited surprising behaviors, such as answering medical questions and performing well on medical licensing exams. These results have demonstrated the coming transformation of medicine by […]

ABSTRACT:  Despite ML models' impressive performance, training and deploying them is currently a somewhat messy endeavor. But does it have to be? In this talk, I overview my work on making ML “predictably reliable”---enabling developers to know when their models will work, when they will fail, and why. To begin, we use a case study […]

ABSTRACT:  Despite the widespread proliferation of neural networks, the mechanisms through which they operate so successfully are not well understood.  In this talk, we will first explore empirical and theoretical investigations into neural network training and generalization and what they can tell us about why deep learning works.  Then, we will examine a recent line […]

ABSTRACT: Artificial Intelligence is being increasingly relied on in safety-critical domains. But the predictive models underlying these systems are notoriously brittle, and trustworthy deployment remains a significant challenge. In this talk, I give an overview of my work towards a rigorous foundation for robust machine learning (ML). Using a case study of invariant prediction, we […]

ABSTRACT: "Trustworthy Machine Learning" has become a buzz-word in recent years. But what exactly are the semantics of the promise that we are supposed to trust? In this talk we will make a proposal, through the lens of downstream decision makers using machine learning predictions of payoff relevant states: Predictions are "Trustworthy" if it is in the interests of the downstream decision […]

ABSTRACT:  The rapid progress made over the last few years in generating linguistically coherent natural language has blurred, in the mind of many, the difference between natural language generation, understanding, and the ability to reason with respect to the world. Nevertheless, robust support of high-level decisions that depend on natural language understanding, and one that […]

ABSTRACT: Language models work well, but they are far from trustworthy. Major open questions remain on high-stakes issues such as detecting benchmark contamination, identifying LM-generated text, and reliably generating factually correct outputs. Addressing these challenges will require us to build more precise, reliable algorithms and evaluations that provide guarantees that we can trust. Despite the […]

ABSTRACT: Research in lifelong or continual machine learning has advanced rapidly over the past few years, primarily focusing on enabling learned models to acquire new tasks over time while avoiding catastrophic forgetting of previous tasks. However, autonomous systems still lack the ability to rapidly learn new generalizable skills by building upon and continually refining their […]