{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"2011.06225","title":"A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges","created":"2020-11-12","cited_by_count":819},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"id":"1902.06720","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","created":"2019-02-18","cited_by_count":738},{"id":"1809.11165","title":"GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration","created":"2018-09-28","cited_by_count":609},{"id":"1405.4980","title":"Convex Optimization: Algorithms and Complexity","created":"2014-05-20","cited_by_count":575},{"id":"1902.02476","title":"A Simple Baseline for Bayesian Uncertainty in Deep Learning","created":"2019-02-07","cited_by_count":560},{"id":"1608.04636","title":"Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-\\L{}ojasiewicz Condition","created":"2016-08-16","cited_by_count":539},{"id":"1904.01685","title":"Measuring Calibration in Deep Learning","created":"2019-04-02","cited_by_count":446},{"id":"2002.06715","title":"BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning","created":"2020-02-17","cited_by_count":371},{"id":"2106.14806","title":"Laplace Redux -- Effortless Bayesian Deep Learning","created":"2021-06-28","cited_by_count":365},{"id":"1502.05336","title":"Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks","created":"2015-02-18","cited_by_count":295},{"id":"2003.00307","title":"Loss landscapes and optimization in over-parameterized non-linear systems and neural networks","created":"2020-02-29","cited_by_count":233},{"id":"2102.11582","title":"Deep Deterministic Uncertainty: A Simple Baseline","created":"2021-02-23","cited_by_count":200},{"id":"2011.14522","title":"Feature Learning in Infinite-Width Neural Networks","created":"2020-11-30","cited_by_count":190},{"id":"2010.15110","title":"Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel","created":"2020-10-28","cited_by_count":187},{"id":"2010.06610","title":"Training independent subnetworks for robust prediction","created":"2020-10-13","cited_by_count":177},{"id":"2301.11235","title":"Handbook of Convergence Theorems for (Stochastic) Gradient Methods","created":"2023-01-26","cited_by_count":163},{"id":"2306.00826","title":"In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation","created":"2023-06-01","cited_by_count":134},{"id":"1901.10513","title":"Adversarial Examples Are a Natural Consequence of Test Error in Noise","created":"2019-01-29","cited_by_count":114},{"id":"2007.05864","title":"Bayesian Deep Ensembles via the Neural Tangent Kernel","created":"2020-07-11","cited_by_count":90},{"id":"1906.01930","title":"Approximate Inference Turns Deep Networks into Gaussian Processes","created":"2019-06-05","cited_by_count":89},{"id":"1906.11537","title":"'In-Between' Uncertainty in Bayesian Neural Networks","created":"2019-06-27","cited_by_count":80},{"id":"1910.09529","title":"Adaptive Gradient Descent without Descent","created":"2019-10-21","cited_by_count":79},{"id":"2202.06985","title":"Deep Ensembles Work, But Are They Necessary?","created":"2022-02-14","cited_by_count":63},{"id":"2402.03478","title":"Estimating Epistemic and Aleatoric Uncertainty with a Single Model","created":"2024-02-05","cited_by_count":54},{"id":"2106.02395","title":"DOCTOR: A Simple Method for Detecting Misclassification Errors","created":"2021-06-04","cited_by_count":53},{"id":"2403.14606","title":"The Elements of Differentiable Programming","created":"2024-03-21","cited_by_count":43},{"id":"2202.03101","title":"Nonparametric Uncertainty Quantification for Single Deterministic Neural Network","created":"2022-02-07","cited_by_count":36},{"id":"2110.04286","title":"Is MC Dropout Bayesian?","created":"2021-10-08","cited_by_count":35},{"id":"1811.02564","title":"On exponential convergence of SGD in non-convex over-parametrized learning","created":"2018-11-06","cited_by_count":33},{"id":"2210.12642","title":"Accelerated Linearized Laplace Approximation for Bayesian Deep Learning","created":"2022-10-23","cited_by_count":28},{"id":"2105.13283","title":"Deep Ensembles from a Bayesian Perspective","created":"2021-05-27","cited_by_count":27},{"id":"2305.04933","title":"Uncertainty Quantification in Machine Learning for Engineering Design and Health Prognostics: A Tutorial","created":"2023-05-07","cited_by_count":27},{"id":"2111.03577","title":"Mixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learning","created":"2021-11-05","cited_by_count":25},{"id":"2012.02818","title":"Encoding the latent posterior of Bayesian Neural Networks for uncertainty quantification","created":"2020-12-04","cited_by_count":18},{"id":"2210.04994","title":"Sampling-based inference for large linear models, with application to linearised Laplace","created":"2022-10-10","cited_by_count":18},{"id":"2302.12565","title":"Variational Linearized Laplace Approximation for Bayesian Deep Learning","created":"2023-02-24","cited_by_count":18},{"id":"2201.13011","title":"On the Power-Law Hessian Spectrums in Deep Learning","created":"2022-01-31","cited_by_count":16},{"id":"2306.01710","title":"A Data-Driven Measure of Relative Uncertainty for Misclassification Detection","created":"2023-06-02","cited_by_count":14},{"id":"2307.07785","title":"The Interpolating Information Criterion for Overparameterized Models","created":"2023-07-15","cited_by_count":12},{"id":"2306.05674","title":"Efficient Uncertainty Quantification and Reduction for Over-Parameterized Neural Networks","created":"2023-06-09","cited_by_count":10},{"id":"2110.12922","title":"On quantitative Laplace-type convergence results for some exponential probability measures, with two applications","created":"2021-10-25","cited_by_count":5},{"id":"2306.12497","title":"Density Uncertainty Layers for Reliable Uncertainty Estimation","created":"2023-06-21","cited_by_count":4},{"id":"1910.09573","title":"Detecting Underspecification with Local Ensembles","created":"2019-10-21","cited_by_count":3},{"id":"2410.16901","title":"Bayes without Underfitting: Fully Correlated Deep Learning Posteriors via Alternating Projections","created":"2024-10-22","cited_by_count":3},{"id":"2406.06968","title":"Beyond the Norms: Detecting Prediction Errors in Regression Models","created":"2024-06-11","cited_by_count":2}],"next_cursor":null}