CIS

Presentation Abstract:  Machine learning provides us with an amazing set of tools to make predictions, but how much should we trust particular predictions? To answer this, we need a way of estimating the confidence we should have in particular predictions of black-box models. Standard tools for doing this give guarantees that are averages over predictions. […]

Presentation Abstract:  Alice submits a number of papers to a machine learning conference and has knowledge of the quality of her papers. Given noisy grades provided by independent reviewers, can Bob obtain accurate estimates of the ground-truth quality of the papers by asking Alice a question about the ground truth? In this talk, we address […]

Abstract: Dawid gives two conceptualizations for models of individual probabilities: “Group to Individual” and “Individual to Group”. A classical concern about the “Group to Individual” view of probability is the reference class problem: Given that we can empirically measure only averages over many individuals, which group or “reference class” do we choose to average over […]

Presentation Abstract: There is a significant interest in developing ML algorithms whose final predictions can be explained in domain-specific terms that are understandable to a human. Providing such an “explanation” can be crucial for the adoption of ML algorithms in risk-sensitive domains such as healthcare. This has motivated a number of approaches that seek to […]

Abstract: In a combinatorial auction there are m items, and each of n players has a valuation function v_i which maps sets of items to non-negative reals. A designer wishes to partition the items into S_1,…,S_n to maximize the welfare (\sum_i v_i(S_i) ), perhaps assuming that all v_i lie in some class V (such as […]

ABSTRACT Traditional convolutional networks exhibit unprecedented robustness to intraclass nuisances when trained on big data. Generalization with respect to geometric transformations has been achieved via expensive data augmentation. It has been shown recently that data augmentation can be avoided if networks are structured such that feature representations are transformed the same way as the input, a desirable property called equivariance. In […]

Abstract Sensing and actuation systems are entrusted with increasing intelligence to perceive the environment and react to it. Their reliability often relies on the trustworthiness of sensors. As process automation and robotics keep evolving, sensing methods such as pressure/temperature/motion sensing are extensively used in conventional systems and rapidly emerging applications. This talk aims to investigate […]