Masking-based explanations are governed by the information capacity of the query channel, with reliable recovery achievable below capacity via sparse maximum-likelihood decoding but impossible above it.
Ridge regression: Biased estimation for nonorthogonal problems
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 6roles
method 1polarities
use method 1representative citing papers
A sparsity-agnostic DD channel estimator exploits Cartesian-product support structure and BIC-based dimension selection to recover exact support with high probability and achieve near-oracle reconstruction accuracy.
Physically bounded extrapolation models for zero-noise extrapolation reduce unphysical predictions and improve stability compared to unbounded fits on large synthetic benchmarks and real hardware.
ADR achieves theoretically zero-forgetting class-incremental graph learning by combining backpropagation adaptation with ridge-regression-based layer-wise merging of GNN linear transformations.
A new regularized covariance parameterization enables effective direct data-driven LQR control for ill-conditioned data, shown equivalent to indirect Tikhonov-regularized LQR and extended to nonlinear systems via Koopman embedding.
Foundation model embeddings provide no advantage over traditional spectral features for cross-country maize yield generalization in Africa, with all methods yielding negative R² under leave-one-country-out testing due to distribution shifts.
citing papers explorer
-
The Query Channel: Information-Theoretic Limits of Masking-Based Explanations
Masking-based explanations are governed by the information capacity of the query channel, with reliable recovery achievable below capacity via sparse maximum-likelihood decoding but impossible above it.
-
Delay-Doppler Domain Channel Estimation: What if Sparsity is Unknown?
A sparsity-agnostic DD channel estimator exploits Cartesian-product support structure and BIC-based dimension selection to recover exact support with high probability and achieve near-oracle reconstruction accuracy.
-
Improving Zero-Noise Extrapolation via Physically Bounded Models
Physically bounded extrapolation models for zero-noise extrapolation reduce unphysical predictions and improve stability compared to unbounded fits on large synthetic benchmarks and real hardware.
-
Analytic Drift Resister for Non-Exemplar Continual Graph Learning
ADR achieves theoretically zero-forgetting class-incremental graph learning by combining backpropagation adaptation with ridge-regression-based layer-wise merging of GNN linear transformations.
-
On Tikhonov Regularization for Direct and Indirect Data-Driven LQR Control
A new regularized covariance parameterization enables effective direct data-driven LQR control for ill-conditioned data, shown equivalent to indirect Tikhonov-regularized LQR and extended to nonlinear systems via Koopman embedding.
-
Do Foundation Model Embeddings Improve Cross-Country Crop Yield Generalisation? A Leave-One-Country-Out Evaluation in Sub-Saharan Africa
Foundation model embeddings provide no advantage over traditional spectral features for cross-country maize yield generalization in Africa, with all methods yielding negative R² under leave-one-country-out testing due to distribution shifts.