Any n-qubit QC Hamiltonian sparsifies to Õ(n/ε²) terms preserving all state energies within 1±ε using invariant subspace decomposition and the Alon-Kozma operator inequality.
10 Conditional KRR: Injecting Unpenalized Features into Kernel Methods with Applications to Kernel Thresholding Takhanov, R
8 Pith papers cite this work, alongside 161 external citations. Polarity classification is still indexing.
8
Pith papers citing it
161
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
years
2026 8verdicts
UNVERDICTED 8roles
background 1polarities
background 1representative citing papers
Any unital quantum channel on d dimensions admits exact simulation with ancilla dimension k and success probability Ω(k/log d) via randomization and postselection; the bound is tight and fails for strongly non-unital channels.
A Gaussian mean width bound in weighted geometry yields a single-letter strong converse for the classical identification capacity of quantum channels, improving known results for depolarizing, Pauli, erasure, and amplitude damping channels.
Introduces budgeted heteroskedastic multi-judge estimation and proves instance-optimality of an adaptive inverse-variance weighted estimator via matching upper and lower bounds.
Many r-local Hamiltonians, including Pauli strings, random high-rank operators, and high-rank operators, admit sparsifications with o(n^r) terms that (1±ε)-approximate the original Hamiltonian on all states.
Conditional KRR reduces to KRR on a residual kernel with an added O(1/sqrt(N)) term in expected test risk and outperforms standard KRR when the F-component is dominant.
Transformers can be built to act as nonlinear featurizers via attention, supporting in-context regression with proven generalization bounds on synthetic tasks.
GSQUEAK produces spectrally accurate sparsifiers for graph Laplacians in a single-pass distributed streaming setting.
citing papers explorer
-
Quantum Cut Sparsifiers
Any n-qubit QC Hamiltonian sparsifies to Õ(n/ε²) terms preserving all state energies within 1±ε using invariant subspace decomposition and the Alon-Kozma operator inequality.
-
Randomized simulation of quantum channels using small ancilla
Any unital quantum channel on d dimensions admits exact simulation with ancilla dimension k and success probability Ω(k/log d) via randomization and postselection; the bound is tight and fails for strongly non-unital channels.
-
Gaussian mean width strong converse bound on the classical identification capacity of quantum channels
A Gaussian mean width bound in weighted geometry yields a single-letter strong converse for the classical identification capacity of quantum channels, improving known results for depolarizing, Pauli, erasure, and amplitude damping channels.
-
Instance-Optimal Estimation with Multiple LLM Judges on a Budget
Introduces budgeted heteroskedastic multi-judge estimation and proves instance-optimality of an adaptive inverse-variance weighted estimator via matching upper and lower bounds.
-
Many Hamiltonians Are Sparsifiable
Many r-local Hamiltonians, including Pauli strings, random high-rank operators, and high-rank operators, admit sparsifications with o(n^r) terms that (1±ε)-approximate the original Hamiltonian on all states.
-
Conditional KRR: Injecting Unpenalized Features into Kernel Methods with Applications to Kernel Thresholding
Conditional KRR reduces to KRR on a residual kernel with an added O(1/sqrt(N)) term in expected test risk and outperforms standard KRR when the F-component is dominant.
-
Understanding In-Context Learning for Nonlinear Regression with Transformers: Attention as Featurizer
Transformers can be built to act as nonlinear featurizers via attention, supporting in-context regression with proven generalization bounds on synthetic tasks.
-
Improved large-scale graph learning through ridge spectral sparsification
GSQUEAK produces spectrally accurate sparsifiers for graph Laplacians in a single-pass distributed streaming setting.