Show newer

Restricted Boltzmann Machines as Models of Interacting Variables. (arXiv:2103.15917v1 [stat.ML]) arxiv.org/abs/2103.15917

Online Defense of Trojaned Models using Misattributions. (arXiv:2103.15918v1 [cs.CR]) arxiv.org/abs/2103.15918

Modelling Heterogeneity Using Bayesian Structured Sparsity. (arXiv:2103.15919v1 [stat.ME]) arxiv.org/abs/2103.15919

Learning Under Adversarial and Interventional Shifts. (arXiv:2103.15933v1 [cs.LG]) arxiv.org/abs/2103.15933

Strong Optimal Classification Trees. (arXiv:2103.15965v1 [cs.LG]) arxiv.org/abs/2103.15965

Modeling Graph Node Correlations with Neighbor Mixture Models. (arXiv:2103.15966v1 [cs.LG]) arxiv.org/abs/2103.15966

Density Estimation by Monte Carlo and Quasi-Monte Carlo. (arXiv:2103.15976v1 [stat.CO]) arxiv.org/abs/2103.15976

Testing For a Parametric Baseline-Intensity in Dynamic Interaction Networks. (arXiv:2103.14668v1 [stat.ME]) arxiv.org/abs/2103.14668

Generalization capabilities of translationally equivariant neural networks. (arXiv:2103.14686v1 [hep-lat]) arxiv.org/abs/2103.14686

Inapplicability of the TVOR method to USHMM Data Outlier Identification. (arXiv:2103.14693v1 [stat.ME]) arxiv.org/abs/2103.14693

Lower Bounds on the Generalization Error of Nonlinear Learning Models. (arXiv:2103.14723v1 [stat.ML]) arxiv.org/abs/2103.14723

Beyond the adjacency matrix: random line graphs and inference for networks with edge attributes. (arXiv:2103.14726v1 [cs.SI]) arxiv.org/abs/2103.14726

Modeling the Nonsmoothness of Modern Neural Networks. (arXiv:2103.14731v1 [cs.LG]) arxiv.org/abs/2103.14731

Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks. (arXiv:2103.14749v1 [stat.ML]) arxiv.org/abs/2103.14749

Time-to-event regression using partially monotonic neural networks. (arXiv:2103.14755v1 [stat.ML]) arxiv.org/abs/2103.14755

Is it who you are or where you are? Accounting for compositional differences in cross-site treatment variation. (arXiv:2103.14765v1 [stat.ME]) arxiv.org/abs/2103.14765

Learning to Solve the AC-OPF using Sensitivity-Informed Deep Neural Networks. (arXiv:2103.14779v1 [math.OC]) arxiv.org/abs/2103.14779

U.S. Broadband Coverage Data Set: A Differentially Private Data Release. (arXiv:2103.14035v1 [cs.CR]) arxiv.org/abs/2103.14035

Differentially Private Normalizing Flows for Privacy-Preserving Density Estimation. (arXiv:2103.14068v1 [cs.LG]) arxiv.org/abs/2103.14068

Learning landmark geodesics using Kalman ensembles. (arXiv:2103.14076v1 [stat.ML]) arxiv.org/abs/2103.14076

Show older
Qoto Mastodon

QOTO: Question Others to Teach Ourselves
An inclusive, Academic Freedom, instance
All cultures welcome.
Hate speech and harassment strictly forbidden.