Claims Browser

A framework combining row-wise PCA with linearly-constrained multi-output GP can effectively model constrained multi-field data while treating all fields symmetrically

"we propose a robust framework for jointly modeling constrained multi-field data. Our approach first leverages a specific PCA procedure for multi-field data, coined row-wise PCA, which has the interesting property of preserving the constraint in the latent space"

The proposed framework has been validated on population dynamics problems and industrial CFD applications involving Reynolds stress tensor prediction

"The proposed framework is validated on a population dynamics problem and on an industrial CFD application, which involves the prediction of Reynolds stress tensor components under the incompressibility constraint"

M-HySMap reduces routed multicast hops by 10.6-19.6% over Activity+QAP and 19.7-41.1% over Edge+QAP across a 115-job evidence suite on Potjans-inspired recurrent SNNs and mesh NoCs from 4x4 to 6x6, plus a 7x7 stress case

"Across a 115-job evidence suite on Potjans-inspired recurrent SNNs and mesh NoCs from 4 x 4 to 6 x 6, plus a 7 x 7 stress case, M-HySMap reduces routed multicast hops by 10.6-19.6% over Activity+QAP and 19.7-41.1% over Edge+QAP."

Incremental updates in M-HySMap accelerate refinement by 4.7-12.7x while matching full recomputation to numerical precision

"Incremental updates accelerate refinement by 4.7-12.7x while matching full recomputation to numerical precision."

Kolmogorov-Arnold Networks with geometry-constrained edge activations match or outperform fixed-basis methods on symbolic regression tasks, achieving median NRMSE of 0.030 on AI Feynman benchmarks

"Across 50 symbolic-regression targets ($40$ from the AI Feynman benchmark plus $10$ synthetic stress tests), geometry-constrained KANs match or beat every fixed-basis baseline on median NRMSE (Banach-KAN $0.030$, tying Chebyshev and improving on splines)"

Geometry-constrained KANs are significantly more robust to measurement noise than unregularized splines, degrading only 3.7x compared to 21.6x as noise increases from 0 to 1

"as $σ$ grows from $0$ to $1$, $\ell^p$-KAN degrades only $3.7\times$ -- below even a cross-validated spline ($\approx 11\times$) -- while an unregularised spline degrades $21.6\times$"

Learned geometry exponents in KANs provide interpretable signals that reveal consistent, target-dependent geometric ordering across equation families

"Learned exponents provide an interpretable, relative signal: at a fixed initialisation they reveal a consistent, target-dependent geometric ordering across equation families and input dimensions."

Banach-KAN performs best in small-sample regimes, with fixed-basis models only catching up as training set size increases

"Banach-KAN also takes the most per-equation wins in the small-sample regime, with fixed-basis models catching up only as the training set grows."

Driver behavior has three key properties that shape traffic phenomena: it is heterogeneous, context-dependent, and changes over time.

"Driver behavior is heterogeneous, context-dependent, and changes over time, and these properties shape the traffic phenomena we observe."

A quantum-inspired representation of driver behavior can combine properties usually treated separately: continuous, probabilistic, context-dependent, history-dependent representation with learned interactions among behavioral variables.

"We introduce a quantum-inspired representation of driver behavior that combines properties usually treated separately or in part: it is continuous, probabilistic, context-dependent, history-dependent, and represents interactions among behavioral variables as learned from data."

When trained without supervision on the I-24 MOTION dataset, the quantum-inspired framework recovers three interpretable driving profiles representing free flow, transition, and congestion regimes.

"Trained without supervision on the I-24 MOTION dataset, the framework recovers three interpretable driving profiles representing three regimes: free flow, transition, and congestion."

The quantum-inspired driver representation reproduces known macroscopic traffic phenomena, aligning with the fundamental diagram and reproducing hysteresis loops.

"The same representation also reproduces known macroscopic phenomena, aligning with the fundamental diagram and reproducing hysteresis loops."

There was a surge of public interest in AI between 2021 and 2023

"57 semi-structured interviews with AI professionals in 2021 and 2023--before and after the recent surge of public interest"

There are three primary debates in AI: the method of development (top-down vs bottom-up), the nature of AI mind (passive tool vs humanlike), and the morality of AI development speed

"We develop a framework of three primary debates across which frames are adopted and contested: (i) the $\textit{method}$ of AI development, between frames of top-down expert systems and bottom-up emergent capabilities, (ii) the $\textit{mind}$ of an AI system, ranging from a passive tool to a humanlike "digital mind," and (iii) the $\textit{morality}$ of how AI is used, particularly the decision of whether to slow down or speed up AI development."

AI professionals use sociological frames to address cognitive challenges such as assigning responsibility for societal impacts of AI

"We identify a range of sociological frames (interpretive schemas that structure collective cognition) and show how AI professionals use frames to address significant cognitive challenges, such as assigning responsibility for societal impacts."

A matching lower bound of Ω(d log(1+T/d)) shows that the Ω(log T) factor is unavoidable for general OCO

"We also prove a matching lower bound of $Ω(d\log (1+T/d))$, showing that the $Ω(\log T)$ factor is unavoidable."

For general OCO over a d-dimensional compact convex set, an algorithm achieves O(d log(1+T/d)) alternating regret, improving the previous best of O-tilde(d^(2/3) T^(1/3))

"For general OCO over a $d$-dimensional compact convex set, we give an algorithm with $O(d\log (1+T/d))$ alternating regret, improving the previous best of $\widetilde{O}(d^{2/3}T^{1/3})$."

This is the first uncoupled learning dynamics with O(1/T) convergence to CCE in two-player general-sum games, while all prior works suffer additional log T factors

"This is the first uncoupled learning dynamics with $O(1/T)$ convergence to CCE in two-player general-sum games, while all prior works suffer additional $\log T$ factors."