Presents a quantum soft PCA framework with Fermi-Dirac filter for principal subspace scoring without eigenvector recovery, claiming dimension-independent sample complexity O(η^{-2}).
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
The authors propose target-space recovery profiles to diagnose which reproducible dimensions of fMRI brain responses are captured by model predictions, showing that accuracy alone can mask alignment mismatches in visual cortex.
OSCAR achieves near-BF16 accuracy for 2-bit KV cache quantization by using offline spectral covariance-aware rotations aligned with attention, plus a custom deployable INT2 kernel compatible with paged serving.
The paper introduces singular value functions for C*-algebras that generalize singular values of compact operators and establishes their basic properties with examples.
A spectral generalized covariance measure enables conditional independence testing on non-Euclidean data with uniform bootstrap validity and power guarantees under doubly robust conditions.
citing papers explorer
-
Quantum principal component analysis without eigenvector recovery
Presents a quantum soft PCA framework with Fermi-Dirac filter for principal subspace scoring without eigenvector recovery, claiming dimension-independent sample complexity O(η^{-2}).
-
Beyond Prediction Accuracy: Target-Space Recovery Profiles for Evaluating Model-Brain Alignment
The authors propose target-space recovery profiles to diagnose which reproducible dimensions of fMRI brain responses are captured by model predictions, showing that accuracy alone can mask alignment mismatches in visual cortex.
-
OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization
OSCAR achieves near-BF16 accuracy for 2-bit KV cache quantization by using offline spectral covariance-aware rotations aligned with attention, plus a custom deployable INT2 kernel compatible with paged serving.
-
Singular value functions for C\(^*\)-algebras
The paper introduces singular value functions for C*-algebras that generalize singular values of compact operators and establishes their basic properties with examples.
-
Testing Conditional Independence via the Spectral Generalized Covariance Measure: Beyond Euclidean Data
A spectral generalized covariance measure enables conditional independence testing on non-Euclidean data with uniform bootstrap validity and power guarantees under doubly robust conditions.