Claims Browser

Homo-RAG is established as a practical and robust framework for reliable, evidence-grounded gene function prediction in understudied organisms

"These findings establish Homo-RAG as a practical and robust framework for reliable, evidence-grounded gene function prediction in understudied organisms"

More corners of hypercube can be programmed as stable states in Hopfield Neural Networks regardless of whether the number of neurons is even or odd

"it is proved that more corners of hypercube can be programmed as stable states (whether the number of neurons is even or odd)"

A new perspective has been presented to the Programming Problem of Hopfield Neural Networks

"The research paper presents a new perspective to the so called "Programming Problem" of Hopfield Neural Network"

Random feature methods provide scalable approximation to kernel ridge regression with a neighboring early-stopping rule that can adaptively select regularization parameters without prior knowledge of smoothness and capacity parameters

"Random feature methods provide a scalable approximation to kernel ridge regression (KRR), but the regularization parameter that yields the oracle learning rate depends on unknown smoothness and capacity parameters. In this work, we propose a neighboring early-stopping rule for adaptive regularization in KRR with random features (KRR-RF)."

The neighboring early-stopping method reduces computational complexity by using a uniform grid in inverse regularization and comparing only adjacent estimators, avoiding construction of the exact kernel Gram matrix

"The method uses a grid that is uniform in inverse regularization and compares only adjacent estimators, reducing the number of discrepancy comparisons relative to standard all-pairs Lepskii-type procedures. Both the neighboring discrepancy and its empirical complexity term can be computed directly in the random feature space, without constructing the exact kernel Gram matrix."

Under standard source and capacity conditions with suitable grid and random feature budget conditions, the selected estimator attains the oracle polynomial learning rate up to logarithmic factors

"under standard source and capacity conditions together with suitable grid and random feature budget conditions, the selected estimator attains the oracle polynomial learning rate up to logarithmic factors"

The regularization parameter can be selected without prior knowledge of source and capacity exponents and works in both well-specified and partially misspecified regimes

"The result allows the regularization parameter to be selected without prior knowledge of the source and capacity exponents and covers both well-specified and partially misspecified regimes."

ChatGPT for Teachers is expanding to 55 U.S. school systems, reaching over 100,000 more educators and staff

"ChatGPT for Teachers is expanding to 55 U.S. school systems, bringing secure AI tools, training, and support to over 100,000 more educators and staff."

Generative reconstruction has emerged as a promising paradigm for reconstructing continuous physical fields from sparse measurements by learning data-driven physical priors

"Generative reconstruction has recently emerged as a promising paradigm for this task by learning data-driven physical priors that complete plausible full fields from limited observations."

TRACE matches or surpasses frame-wise generative reconstructors, offline spatiotemporal methods, and streaming data-assimilation baselines in reconstruction quality under temporally sparse and spatially localized sensing protocols

"Experiments on active matter, ocean sound-speed fields, and supernova simulations show that TRACE matches or surpasses frame-wise generative reconstructors, offline spatiotemporal methods, and streaming data-assimilation baselines in reconstruction quality under temporally sparse and spatially localized sensing protocols."

Existing generative reconstruction methods largely assume fixed batch conditioning and cannot handle structured streams from real sensing systems

"existing methods largely assume fixed, batch conditioning, whereas real sensing systems often produce structured streams: probes scan local regions, instruments observe moving fields of view, and communication constraints may leave entire frames missing."

The deductive approach for enforcing physical constraints in GP models is sensitive to the arbitrary choice of which output to deduce, affecting both predictive accuracy and uncertainty quantification

"we show that this deductive approach is sensitive to the arbitrary choice of which output to deduce, affecting both predictive accuracy and uncertainty quantification"

Row-wise PCA for multi-field data has the property of preserving physical constraints in the latent space, unlike standard PCA strategies

"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. Since standard PCA strategies for multi-field data do not preserve such constraints"

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"

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."