Introduces decision-alignment to evaluate uncertainty metrics against downstream decision utilities and proposes prior-weighted proper scoring rules that align better in benchmarks and case studies.
Iris [dataset],
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
verdicts
UNVERDICTED 11roles
dataset 1polarities
use dataset 1representative citing papers
Empirical audit of LAION-2B-en and LAION-2B-multi finds overrepresentation of young adults, White people, and males plus stereotypical emotion associations across two attribute classifiers.
As alpha approaches 0, normalized generalized energy distances in separable Hilbert spaces converge to a logarithmic energy distance that characterizes equality of distributions and supports a new logarithmic Gini covariance with asymptotic theory for the k-sample problem.
A survey of on-device learning in TinyML organized by distribution change regimes, highlighting influences on applications, hardware, and solutions plus a gap between benchmarks and deployments.
QNAS applies multi-objective NAS with a SuperCircuit and NSGA-II to discover compact HQNN architectures that trade off accuracy against runtime and cutting overhead, achieving 97.16% on MNIST (8 qubits), 87.38% on Fashion-MNIST (5 qubits), and 100% on Iris (4 qubits).
The thesis presents Pino, an end-to-end pipeline that supervises reinforcement learning agents with argumentation-based normative advisors, introduces an algorithm for automatic argument extraction, and defines a mitigation strategy for norm avoidance.
Quantum neuromorphic kernels outperform parameterized quantum kernels on low-dimensional datasets like Iris but underperform on high-dimensional SDSS data in spectral clustering tasks.
Simulations show physical neural networks need nonlinearity, amplification, and suppression for learning, with physically plausible circuit designs presented.
Gini MDS replaces Euclidean distance in multidimensional scaling with a rank-and-value-based pseudo-distance controlled by a hyperparameter, claimed to yield more robust embeddings on noisy data than standard MDS.
Reformulates MST as PUBO, applies FALQON to optimize prototypes for OPF classifiers, and reports accuracies comparable to classical Prim's algorithm on real datasets.
A network of optomechanical oscillators is modeled as a platform for neuromorphic computing, with a demonstration that five nodes in all-to-all coupling can implement an XOR gate.
citing papers explorer
-
Decision-Aligned Evaluation of Uncertainty Quantification
Introduces decision-alignment to evaluate uncertainty metrics against downstream decision utilities and proposes prior-weighted proper scoring rules that align better in benchmarks and case studies.
-
What changes after deployment? A survey on On-device Learning in TinyML
A survey of on-device learning in TinyML organized by distribution change regimes, highlighting influences on applications, hardware, and solutions plus a gap between benchmarks and deployments.
-
Optimizing Multidimensional Scaling in Gini Metric Spaces
Gini MDS replaces Euclidean distance in multidimensional scaling with a rank-and-value-based pseudo-distance controlled by a hyperparameter, claimed to yield more robust embeddings on noisy data than standard MDS.