{"list":"other","total":53,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"2002.10957","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","created":"2020-02-25","cited_by_count":1463},{"id":"1703.00564","title":"MoleculeNet: A Benchmark for Molecular Machine Learning","created":"2017-03-02","cited_by_count":1051},{"id":"1407.7722","title":"OpenML: networked science in machine learning","created":"2014-07-29","cited_by_count":526},{"id":"1903.08560","title":"Surprises in High-Dimensional Ridgeless Least Squares Interpolation","created":"2019-03-19","cited_by_count":513},{"id":"1908.05355","title":"The generalization error of random features regression: Precise asymptotics and double descent curve","created":"2019-08-14","cited_by_count":413},{"id":"2002.06715","title":"BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning","created":"2020-02-17","cited_by_count":371},{"id":"1910.12656","title":"Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration","created":"2019-10-28","cited_by_count":364},{"id":"2010.09885","title":"ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction","created":"2020-10-19","cited_by_count":337},{"id":"1909.10155","title":"Verified Uncertainty Calibration","created":"2019-09-23","cited_by_count":309},{"id":"2002.10118","title":"Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks","created":"2020-02-24","cited_by_count":231},{"id":"1808.00387","title":"Just Interpolate: Kernel \"Ridgeless\" Regression Can Generalize","created":"2018-08-01","cited_by_count":190},{"id":"1905.00076","title":"Ensemble Distribution Distillation","created":"2019-04-30","cited_by_count":158},{"id":"1511.02476","title":"Statistical physics of inference: Thresholds and algorithms","created":"2015-11-08","cited_by_count":128},{"id":"1708.03395","title":"Optimal Errors and Phase Transitions in High-Dimensional Generalized Linear Models","created":"2017-08-10","cited_by_count":116},{"id":"2008.06786","title":"The Neural Tangent Kernel in High Dimensions: Triple Descent and a Multi-Scale Theory of Generalization","created":"2020-08-15","cited_by_count":101},{"id":"1803.06964","title":"A modern maximum-likelihood theory for high-dimensional logistic regression","created":"2018-03-19","cited_by_count":81},{"id":"2006.10564","title":"Distribution-free binary classification: prediction sets, confidence intervals and calibration","created":"2020-06-18","cited_by_count":79},{"id":"1508.05154","title":"Posterior calibration and exploratory analysis for natural language processing models","created":"2015-08-21","cited_by_count":76},{"id":"2202.08832","title":"Universality of empirical risk minimization","created":"2022-02-17","cited_by_count":75},{"id":"2008.08037","title":"Moment Multicalibration for Uncertainty Estimation","created":"2020-08-18","cited_by_count":63},{"id":"1811.06817","title":"Evaluating Uncertainty Quantification in End-to-End Autonomous Driving Control","created":"2018-11-16","cited_by_count":55},{"id":"2105.02180","title":"A unifying tutorial on Approximate Message Passing","created":"2021-05-05","cited_by_count":50},{"id":"1804.09753","title":"The phase transition for the existence of the maximum likelihood estimate in high-dimensional logistic regression","created":"2018-04-25","cited_by_count":46},{"id":"2002.01586","title":"A Precise High-Dimensional Asymptotic Theory for Boosting and Minimum-$\\ell_1$-Norm Interpolated Classifiers","created":"2020-02-05","cited_by_count":44},{"id":"2007.13716","title":"The Lasso with general Gaussian designs with applications to hypothesis testing","created":"2020-07-27","cited_by_count":40},{"id":"2102.07856","title":"Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification","created":"2021-02-15","cited_by_count":39},{"id":"1508.02757","title":"De-biasing the Lasso: Optimal Sample Size for Gaussian Designs","created":"2015-08-11","cited_by_count":35},{"id":"2001.04694","title":"Hydra: Preserving Ensemble Diversity for Model Distillation","created":"2020-01-14","cited_by_count":31},{"id":"1909.03725","title":"Isotonic Distributional Regression","created":"2019-09-09","cited_by_count":28},{"id":"2005.01757","title":"Sample Complexity of Uniform Convergence for Multicalibration","created":"2020-05-04","cited_by_count":24},{"id":"2010.03460","title":"Approximate Message Passing with Spectral Initialization for Generalized Linear Models","created":"2020-10-07","cited_by_count":22},{"id":"2311.12436","title":"Classifier Calibration with ROC-Regularized Isotonic Regression","created":"2023-11-21","cited_by_count":19},{"id":"2404.01233","title":"Optimal Ridge Regularization for Out-of-Distribution Prediction","created":"2024-04-01","cited_by_count":19},{"id":"2405.15480","title":"Fundamental computational limits of weak learnability in high-dimensional multi-index models","created":"2024-05-24","cited_by_count":19},{"id":"2202.03295","title":"Theoretical characterization of uncertainty in high-dimensional linear classification","created":"2022-02-07","cited_by_count":18},{"id":"2003.10431","title":"Universality of Approximate Message Passing Algorithms","created":"2020-03-23","cited_by_count":16},{"id":"2406.13944","title":"Generalization error of min-norm interpolators in transfer learning","created":"2024-06-20","cited_by_count":16},{"id":"1706.01191","title":"The Likelihood Ratio Test in High-Dimensional Logistic Regression Is Asymptotically a Rescaled Chi-Square","created":"2017-06-05","cited_by_count":15},{"id":"2001.09351","title":"The Asymptotic Distribution of the MLE in High-dimensional Logistic Models: Arbitrary Covariance","created":"2020-01-25","cited_by_count":15},{"id":"1902.08885","title":"De-Biasing The Lasso With Degrees-of-Freedom Adjustment","created":"2019-02-24","cited_by_count":12},{"id":"2303.02644","title":"Expectation consistency for calibration of neural networks","created":"2023-03-05","cited_by_count":10},{"id":"2305.10886","title":"Minimum-Risk Recalibration of Classifiers","created":"2023-05-18","cited_by_count":10},{"id":"2305.00070","title":"Online Platt Scaling with Calibeating","created":"2023-04-28","cited_by_count":8},{"id":"2204.06990","title":"Observable adjustments in single-index models for regularized M-estimators","created":"2022-04-14","cited_by_count":5},{"id":"2205.10198","title":"A New Central Limit Theorem for the Augmented IPW Estimator: Variance Inflation, Cross-Fit Covariance and Beyond","created":"2022-05-20","cited_by_count":5},{"id":"2410.18144","title":"Using Platt's scaling for calibration after undersampling -- limitations and how to address them","created":"2024-10-22","cited_by_count":5},{"id":"2406.11666","title":"ROTI-GCV: Generalized Cross-Validation for right-ROTationally Invariant Data","created":"2024-06-17","cited_by_count":4},{"id":"2404.12481","title":"Understanding Optimal Feature Transfer via a Fine-Grained Bias-Variance Analysis","created":"2024-04-18","cited_by_count":2},{"id":"2406.11184","title":"HEDE: Heritability estimation in high dimensions by Ensembling Debiased Estimators","created":"2024-06-17","cited_by_count":1}],"next_cursor":null}