Certifying some distributional robustness with principled adversarial training
Neural networks are vulnerable to adversarial examples and researchers have proposed
many heuristic attack and defense mechanisms. We address this problem through the …
many heuristic attack and defense mechanisms. We address this problem through the …
Scalable end-to-end autonomous vehicle testing via rare-event simulation
While recent developments in autonomous vehicle (AV) technology highlight substantial
progress, we lack tools for rigorous and scalable testing. Real-world testing, the de facto …
progress, we lack tools for rigorous and scalable testing. Real-world testing, the de facto …
Learning kernels with random features
Randomized features provide a computationally efficient way to approximate kernel machines
in machine learning tasks. However, such methods require a user-defined kernel as input. …
in machine learning tasks. However, such methods require a user-defined kernel as input. …
Visualizing the very-large-scale motions in turbulent pipe flow
Time-resolved stereoscopic particle image velocimetry is used to investigate the structure of
the very-large-scale motions (VLSMs) in fully developed turbulent pipe flow. The motions …
the very-large-scale motions (VLSMs) in fully developed turbulent pipe flow. The motions …
Efficient black-box assessment of autonomous vehicle safety
While autonomous vehicle (AV) technology has shown substantial progress, we still lack
tools for rigorous and scalable testing. Real-world testing, the $\textit{de-facto}$ evaluation …
tools for rigorous and scalable testing. Real-world testing, the $\textit{de-facto}$ evaluation …
C-net: Contextual network for sarcasm detection
Automatic Sarcasm Detection in conversations is a difficult and tricky task. Classifying an
utterance as sarcastic or not in isolation can be futile since most of the time the sarcastic nature …
utterance as sarcastic or not in isolation can be futile since most of the time the sarcastic nature …
Objective measurement of function following lumbar spinal stenosis decompression reveals improved functional capacity with stagnant real-life physical activity
Background Context Lumbar spinal stenosis (LSS) is a prevalent and costly condition
associated with significant dysfunction. Alleviation of pain and improvement of function are the …
associated with significant dysfunction. Alleviation of pain and improvement of function are the …
Neural bridge sampling for evaluating safety-critical autonomous systems
Learning-based methodologies increasingly find applications in safety-critical domains like
autonomous driving and medical robotics. Due to the rare nature of dangerous events, real-…
autonomous driving and medical robotics. Due to the rare nature of dangerous events, real-…
FormulaZero: Distributionally robust online adaptation via offline population synthesis
Balancing performance and safety is crucial to deploying autonomous vehicles in multi-agent
environments. In particular, autonomous racing is a domain that penalizes safe but …
environments. In particular, autonomous racing is a domain that penalizes safe but …
Adaptive sampling probabilities for non-smooth optimization
Standard forms of coordinate and stochastic gradient methods do not adapt to structure in
data; their good behavior under random sampling is predicated on uniformity in data. When …
data; their good behavior under random sampling is predicated on uniformity in data. When …