Vitriflow is a new explicit calibration framework for melt-quench MD that produces statistically converged, screened amorphous ensembles demonstrated on a-SiO2, a-Si3N4 and a-Sm2O3.
hub
Graphical models for processing missing data
19 Pith papers cite this work. Polarity classification is still indexing.
19
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
fields
cs.LG 6 stat.ME 4 cs.IR 2 astro-ph.HE 1 cond-mat.mtrl-sci 1 cs.CL 1 eess.SY 1 math.OC 1 math.ST 1 stat.ML 1roles
background 3polarities
background 3representative citing papers
Fuzzing via Gaussian noise on weights or residual activations elicits hidden backdoor behaviors more often than temperature sampling on four of six models, with proxy-task hyperparameter selection via Thompson sampling improving results over uniform sweeps.
Models regimes in temporal graphs as geodesic trajectories and detects changes as drifts from estimated geodesics, outperforming baselines on synthetic data and showing better alignment with external events on COVID mobility data.
Develops MrPlew to express MrP as locally equivalent to calibration weights near observed responses, enabling diagnostics and variance estimation for nonlinear models.
Averaging output distributions across 3-5 LLMs recovers the unwatermarked distribution, suppressing detection z-scores below threshold while improving quality.
NOMAD unifies shrinkage and thresholding estimation by minimizing a data-driven approximate risk criterion derived via Stein's identity and Tweedie's formula, recovering James-Stein and lasso as special cases.
Proposes score-test-based J and MJ statistics for non-nested cure-fraction survival models that reduce to a Vuong-like form for two models while extending to M models and providing a model-selection criterion.
Amortized neural posterior estimation reproduces nested sampling constraints on RMF couplings for neutron-star EOS with no bias and generates 30,000 samples in 2.5 seconds.
The saturation index S(K)=erank(pooled within-class covariance)/K tracks when few-shot labels become redundant for fixed linear probes, with within-task median Spearman ρ≈0.81 on 17 binary tasks.
Derives three EVPI-based stopping policies for document screening and shows higher net utility than recall-target methods on CLEF-IP and medical review datasets.
Develops a posterior-informed two-stage stochastic multi-objective optimization framework for exploration well portfolio selection under uncertainty, solved via sample average approximation and NSGA-II.
DMW is a scalable Wasserstein statistic over random distance-matrix laws that provably lower-bounds and converges to Gromov–Wasserstein.
MONET models multi-task optimization as a task graph and combines neighbor crossover with local mutation, matching or exceeding MAP-Elites baselines on up to 5,000 tasks.
ShrinkageTrees is an R package implementing regularized Bayesian tree ensembles for survival outcomes and causal inference via AFT models, including the first Horseshoe Forest implementation.
A Fréchet-based random-effects algorithm with M-estimation consistency guarantees is proposed for modeling non-Euclidean random objects in general metric spaces.
The Wilcoxon signed-rank test routinely loses Type I error control in IR benchmarking and should be abandoned.
Single-seed CRPS estimates in limited-data BDL show high variance and peaks for heteroscedastic methods, with local variance correlating above 0.96 to single-seed error.
The paper proposes and analyzes a distributed perception mechanism in Friedkin-Johnsen networks that enables convergence to true social power through local interactions in static and reflected-appraisal settings.
Complete-case TMLE that includes an outcome-missingness model shows lower bias and greater robustness to positivity violations than multiple imputation approaches, while MI with CART yields lower RMSE and nominal coverage in simulations based on five missingness DAGs and a real epidemiological data.
citing papers explorer
-
Vitriflow: calibrated amorphous structure ensembles from melt-quench simulation
Vitriflow is a new explicit calibration framework for melt-quench MD that produces statistically converged, screened amorphous ensembles demonstrated on a-SiO2, a-Si3N4 and a-Sm2O3.
-
Fuzzing Large Language Models to Elicit Hidden Behaviours
Fuzzing via Gaussian noise on weights or residual activations elicits hidden backdoor behaviors more often than temperature sampling on four of six models, with proxy-task hyperparameter selection via Thompson sampling improving results over uniform sweeps.
-
Geodesics of Dynamic Graphs for Regime Change Detection
Models regimes in temporal graphs as geodesic trajectories and detects changes as drifts from estimated geodesics, outperforming baselines on synthetic data and showing better alignment with external events on COVID mobility data.
-
Locally Equivalent Weights for Multilevel Regression and Poststratification
Develops MrPlew to express MrP as locally equivalent to calibration weights near observed responses, enabling diagnostics and variance estimation for nonlinear models.
-
Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMs
Averaging output distributions across 3-5 LLMs recovers the unwatermarked distribution, suppressing detection z-scores below threshold while improving quality.
-
Approximate Risk Minimization Over Shrinking-Thresholding Rules in Normal Mean Estimation
NOMAD unifies shrinkage and thresholding estimation by minimizing a data-driven approximate risk criterion derived via Stein's identity and Tweedie's formula, recovering James-Stein and lasso as special cases.
-
J- and MJ-Type Tests for Non-Nested Parametric Survival Models with a Cure Fraction: A Score Test Approach
Proposes score-test-based J and MJ statistics for non-nested cure-fraction survival models that reduce to a Vuong-like form for two models while extending to M models and providing a model-selection criterion.
-
Amortized Simulation-Based Inference of Relativistic Mean-Field Couplings for Neutron-Star Equations of State
Amortized neural posterior estimation reproduces nested sampling constraints on RMF couplings for neutron-star EOS with no bias and generates 30,000 samples in 2.5 seconds.
-
The Geometry of Saturation: Effective Rank Predicts When Labels Stop Helping in Few-Shot Classification
The saturation index S(K)=erank(pooled within-class covariance)/K tracks when few-shot labels become redundant for fixed linear probes, with within-task median Spearman ρ≈0.81 on 17 binary tasks.
-
Decision-Theoretic Stopping Rules for Document Screening
Derives three EVPI-based stopping policies for document screening and shows higher net utility than recall-target methods on CLEF-IP and medical review datasets.
-
A two-stage stochastic programming framework for oil and gas exploration well portfolio optimization under geological and economic uncertainty
Develops a posterior-informed two-stage stochastic multi-objective optimization framework for exploration well portfolio selection under uncertainty, solved via sample average approximation and NSGA-II.
-
Distance-Matrix Wasserstein Statistics for Scalable Gromov--Wasserstein Learning
DMW is a scalable Wasserstein statistic over random distance-matrix laws that provably lower-bounds and converges to Gromov–Wasserstein.
-
Multi-Task Optimization over Networks of Tasks
MONET models multi-task optimization as a task graph and combines neighbor crossover with local mutation, matching or exceeding MAP-Elites baselines on up to 5,000 tasks.
-
ShrinkageTrees: An R Package for Bayesian Tree Ensembles for Survival Analysis and Causal Inference
ShrinkageTrees is an R package implementing regularized Bayesian tree ensembles for survival outcomes and causal inference via AFT models, including the first Horseshoe Forest implementation.
-
Random-Effects Algorithm for Random Objects in Metric Spaces
A Fréchet-based random-effects algorithm with M-estimation consistency guarantees is proposed for modeling non-Euclidean random objects in general metric spaces.
-
Stop Using the Wilcoxon Test: Myth, Misconception and Misuse in IR Research
The Wilcoxon signed-rank test routinely loses Type I error control in IR benchmarking and should be abandoned.
-
A Tale of Two Variances: When Single-Seed Benchmarks Fail in Bayesian Deep Learning
Single-seed CRPS estimates in limited-data BDL show high variance and peaks for heteroscedastic methods, with local variance correlating above 0.96 to single-seed error.
-
Dynamical models for distributed social power perception in Friedkin-Johnsen influence networks
The paper proposes and analyzes a distributed perception mechanism in Friedkin-Johnsen networks that enables convergence to true social power through local interactions in static and reflected-appraisal settings.
-
Causal Effect Estimation with TMLE: Handling Missing Data and Near-Violations of Positivity
Complete-case TMLE that includes an outcome-missingness model shows lower bias and greater robustness to positivity violations than multiple imputation approaches, while MI with CART yields lower RMSE and nominal coverage in simulations based on five missingness DAGs and a real epidemiological data.