PWO is a trust-region optimizer for autoregressive NQS that improves stability over Adam and stochastic reconfiguration methods while scaling to 1.5B-parameter models on spin systems.
Cambridge University Press, Cambridge (1985)
11 Pith papers cite this work, alongside 10,192 external citations. Polarity classification is still indexing.
11
Pith papers citing it
10.2k
external citations · OpenAlex
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
SASA replaces single-vector decoders in SAEs with learned subspaces plus block sparsity and nuclear-norm regularization, proving that a single group becomes the global minimizer once block size meets intrinsic dimension and yielding polynomial rather than exponential sample complexity.
Polyconvexity implies true-stress-true-strain monotonicity in incompressible isotropic hyperelasticity, which is enforced in four PANN architectures that show varying extrapolation behavior on experimental data.
Anchor PCA recovers a maximal invariant subspace for multi-domain data via PCA on a modified target matrix that trades off explained variance with domain agreement.
Augmented Krylov subspaces jointly approximate quadratic forms and log-dets for faster MLE-based hyperparameter tuning in kernel-based linear system identification.
New degree-sequence lower bounds on hard-core independent set sizes via multivariate local occupancy and spectral analysis.
A derivative-free ensemble Kalman-Bucy smoother is developed for continuous-time data assimilation that supports Bayesian causal inference and iterative model structure identification with small ensemble sizes under partial observations.
A spectral generalized covariance measure enables conditional independence testing on non-Euclidean data with uniform bootstrap validity and power guarantees under doubly robust conditions.
Binomial p-ary sequences form a basis for the vector space over F_p of all p-ary sequences with period a power of p.
Defines multiple digraph Laplacian matrices and proves spectral relations, a radius bound with equality case, and a determinantal identity linking regular digraphs to their line digraphs.
This paper discusses observational, calibration, and imaging requirements for solar and heliospheric science with the SKA radio telescope.
citing papers explorer
-
One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective
PWO is a trust-region optimizer for autoregressive NQS that improves stability over Adam and stochastic reconfiguration methods while scaling to 1.5B-parameter models on spin systems.
-
Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability
SASA replaces single-vector decoders in SAEs with learned subspaces plus block sparsity and nuclear-norm regularization, proving that a single group becomes the global minimizer once block size meets intrinsic dimension and yielding polynomial rather than exponential sample complexity.
-
Concurrent enforcement of polyconvexity and true-stress-true-strain monotonicity in incompressible isotropic hyperelasticity: application to neural network constitutive models
Polyconvexity implies true-stress-true-strain monotonicity in incompressible isotropic hyperelasticity, which is enforced in four PANN architectures that show varying extrapolation behavior on experimental data.
-
Anchor PCA
Anchor PCA recovers a maximal invariant subspace for multi-domain data via PCA on a modified target matrix that trades off explained variance with domain agreement.
-
Kernel-based linear system identification using augmented Krylov subspaces
Augmented Krylov subspaces jointly approximate quadratic forms and log-dets for faster MLE-based hyperparameter tuning in kernel-based linear system identification.
-
Degree-sequence bounds for independent sets via multivariate local occupancy
New degree-sequence lower bounds on hard-core independent set sizes via multivariate local occupancy and spectral analysis.
-
A Continuous-Time Ensemble Kalman-Bucy Smoother for Causal Inference and Model Discovery
A derivative-free ensemble Kalman-Bucy smoother is developed for continuous-time data assimilation that supports Bayesian causal inference and iterative model structure identification with small ensemble sizes under partial observations.
-
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.
-
Binomial sequences over prime fields
Binomial p-ary sequences form a basis for the vector space over F_p of all p-ary sequences with period a power of p.
-
On the Spectra of Digraph Laplacians
Defines multiple digraph Laplacian matrices and proves spectral relations, a radius bound with equality case, and a determinantal identity linking regular digraphs to their line digraphs.
-
State-of-the-art Observation, Calibration, and Imaging Framework for Solar and Heliospheric Sciences with SKA
This paper discusses observational, calibration, and imaging requirements for solar and heliospheric science with the SKA radio telescope.