Related papers: $\alpha$-TCAV: A Unified Framework for Testing wit…
We evaluate whether features extracted from the activation of a deep convolutional network trained in a fully supervised fashion on a large, fixed set of object recognition tasks can be re-purposed to novel generic tasks. Our generic tasks…
While disentangled representations have shown promise in generative modeling and representation learning, their downstream usefulness remains debated. Recent studies re-defined disentanglement through a formal connection to symmetries,…
A general framework is that the estimators of a distribution are obtained by minimizing a function (the estimating function) and they are assessed through another function (the assessment function). The estimating and assessment functions…
Counterfactuals, or modified inputs that lead to a different outcome, are an important tool for understanding the logic used by machine learning classifiers and how to change an undesirable classification. Even if a counterfactual changes a…
This paper investigates the properties of the Generalized Covariance (GCov) estimator under misspecification and constraints with application to processes with local explosive patterns, such as causal-noncausal and double autoregressive…
Factor analysis (FA) is a statistical tool for studying how observed variables with some mutual dependences can be expressed as functions of mutually independent unobserved factors, and it is widely applied throughout the psychological,…
Interpreting neural network decisions and the information learned in intermediate layers is still a challenge due to the opaque internal state and shared non-linear interactions. Although (Kim et al, 2017) proposed to interpret intermediate…
Due to the mechanism of recording, the presence of multiple transactions at each recording time becomes a common feature for high-frequency data in financial market. Using random matrix theory, this paper considers the estimation of…
Cross-validation (CV) is one of the main tools for performance estimation and parameter tuning in machine learning. The general recipe for computing CV estimate is to run a learning algorithm separately for each CV fold, a computationally…
Connected autonomous vehicles (CAVs) must simultaneously perform multiple tasks, such as object detection, semantic segmentation, depth estimation, trajectory prediction, motion prediction, and behaviour prediction, to ensure safe and…
Concept Activation Vectors (CAVs) are widely used to model human-understandable concepts as directions within the latent space of neural networks. They are trained by identifying directions from the activations of concept samples to those…
Coordination among connected and autonomous vehicles (CAVs) is advancing due to developments in control and communication technologies. However, much of the current work is based on oversimplified and unrealistic task-specific assumptions,…
Canonical Correlation Analysis (CCA) is widely used for multimodal data analysis and, more recently, for discriminative tasks such as multi-view learning; however, it makes no use of class labels. Recent CCA methods have started to address…
Conformal prediction provides rigorous distribution-free finite-sample guarantees for marginal coverage under the assumption of exchangeability, but may exhibit systematic undercoverage or overcoverage for specific subpopulations. Assessing…
Classical analysis of variance requires that model terms be labeled as fixed or random and typically culminate by comparing variability from each batch (factor) to variability from errors; without a standard methodology to assess the…
With the rapid development of Connected and Automated Vehicle (CAV) technology, limited self-driving vehicles have been commercially available in certain leading intelligent transportation system countries. When formulating the…
It is increasingly suggested to identify Software Vulnerabilities (SVs) in code commits to give early warnings about potential security risks. However, there is a lack of effort to assess vulnerability-contributing commits right after they…
Many modern data analyses benefit from explicitly modeling dependence structure in data -- such as measurements across time or space, ordered words in a sentence, or genes in a genome. A gold standard evaluation technique is structured…
Deep generative models such as conditional variational autoencoders (CVAEs) have shown great promise for predicting trajectories of surrounding agents in autonomous vehicle planning. State-of-the-art models have achieved remarkable accuracy…
Connected and Automated Vehicles (CAVs) offer a promising solution to the challenges of mixed traffic with both CAVs and Human-Driven Vehicles (HDVs). A significant hurdle in such scenarios is traffic oscillation, or the "stop-and-go"…