{"list":"other","total":51,"rows":[{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1706.00384","title":"Deep Mutual Learning","created":"2017-06-01","cited_by_count":628},{"id":"1706.08947","title":"Exploring Generalization in Deep Learning","created":"2017-06-27","cited_by_count":600},{"id":"1802.10026","title":"Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs","created":"2018-02-27","cited_by_count":588},{"id":"1902.02476","title":"A Simple Baseline for Bayesian Uncertainty in Deep Learning","created":"2019-02-07","cited_by_count":560},{"id":"1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","created":"2017-03-31","cited_by_count":533},{"id":"1912.02178","title":"Fantastic Generalization Measures and Where to Find Them","created":"2019-12-04","cited_by_count":513},{"id":"1905.08094","title":"Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation","created":"2019-05-17","cited_by_count":497},{"id":"1506.02557","title":"Variational Dropout and the Local Reparameterization Trick","created":"2015-06-08","cited_by_count":490},{"id":"1703.04933","title":"Sharp Minima Can Generalize For Deep Nets","created":"2017-03-15","cited_by_count":466},{"id":"1701.06548","title":"Regularizing Neural Networks by Penalizing Confident Output Distributions","created":"2017-01-23","cited_by_count":464},{"id":"2102.08604","title":"SWAD: Domain Generalization by Seeking Flat Minima","created":"2021-02-17","cited_by_count":434},{"id":"1611.01838","title":"Entropy-SGD: Biasing Gradient Descent Into Wide Valleys","created":"2016-11-06","cited_by_count":359},{"id":"1704.00109","title":"Snapshot Ensembles: Train 1, get M for free","created":"2017-04-01","cited_by_count":350},{"id":"1710.10571","title":"Certifying Some Distributional Robustness with Principled Adversarial Training","created":"2017-10-29","cited_by_count":337},{"id":"2102.11600","title":"ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks","created":"2021-02-23","cited_by_count":293},{"id":"1505.05116","title":"Data-driven Distributionally Robust Optimization Using the Wasserstein Metric: Performance Guarantees and Tractable Reformulations","created":"2015-05-19","cited_by_count":291},{"id":"1711.04623","title":"Three Factors Influencing Minima in SGD","created":"2017-11-13","cited_by_count":273},{"id":"2106.01548","title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","created":"2021-06-03","cited_by_count":260},{"id":"2002.06470","title":"Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning","created":"2020-02-15","cited_by_count":210},{"id":"1604.02199","title":"Distributionally Robust Stochastic Optimization with Wasserstein Distance","created":"2016-04-08","cited_by_count":185},{"id":"1610.03425","title":"Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach","created":"2016-10-11","cited_by_count":183},{"id":"2203.08065","title":"Surrogate Gap Minimization Improves Sharpness-Aware Training","created":"2022-03-15","cited_by_count":172},{"id":"1908.08729","title":"Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learning","created":"2019-08-23","cited_by_count":170},{"id":"2206.06232","title":"Towards Understanding Sharpness-Aware Minimization","created":"2022-06-13","cited_by_count":146},{"id":"2206.02618","title":"Generalized Federated Learning via Sharpness Aware Minimization","created":"2022-06-06","cited_by_count":144},{"id":"2203.02714","title":"Towards Efficient and Scalable Sharpness-Aware Minimization","created":"2022-03-05","cited_by_count":129},{"id":"1509.09259","title":"Distributionally Robust Logistic Regression","created":"2015-09-30","cited_by_count":126},{"id":"2010.08001","title":"Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness","created":"2020-10-15","cited_by_count":121},{"id":"2110.08529","title":"Sharpness-Aware Minimization Improves Language Model Generalization","created":"2021-10-16","cited_by_count":108},{"id":"2205.14083","title":"Sharpness-Aware Training for Free","created":"2022-05-27","cited_by_count":95},{"id":"2001.00939","title":"Relative Flatness and Generalization","created":"2020-01-03","cited_by_count":88},{"id":"2206.04920","title":"Fisher SAM: Information Geometry and Sharpness Aware Minimisation","created":"2022-06-10","cited_by_count":84},{"id":"2202.00661","title":"When Do Flat Minima Optimizers Work?","created":"2022-02-01","cited_by_count":78},{"id":"2002.12915","title":"The Implicit and Explicit Regularization Effects of Dropout","created":"2020-02-28","cited_by_count":71},{"id":"1507.00677","title":"Distributional Smoothing with Virtual Adversarial Training","created":"2015-07-02","cited_by_count":61},{"id":"2206.03996","title":"Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning","created":"2022-06-08","cited_by_count":58},{"id":"1910.05929","title":"Emergent properties of the local geometry of neural loss landscapes","created":"2019-10-14","cited_by_count":46},{"id":"2106.14568","title":"Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity","created":"2021-06-28","cited_by_count":44},{"id":"2210.01620","title":"SAM as an Optimal Relaxation of Bayes","created":"2022-10-04","cited_by_count":41},{"id":"2202.13437","title":"A Unified Wasserstein Distributional Robustness Framework for Adversarial Training","created":"2022-02-27","cited_by_count":36},{"id":"1812.09808","title":"Wasserstein Distributionally Robust Stochastic Control: A Data-Driven Approach","created":"2018-12-24","cited_by_count":29},{"id":"1712.06050","title":"Wasserstein Distributionally Robust Optimization and Variation Regularization","created":"2017-12-17","cited_by_count":25},{"id":"2206.01934","title":"Stochastic Multiple Target Sampling Gradient Descent","created":"2022-06-04","cited_by_count":14},{"id":"1702.08848","title":"Semi-supervised Learning based on Distributionally Robust Optimization","created":"2017-02-28","cited_by_count":12},{"id":"2203.00553","title":"Global-Local Regularization Via Distributional Robustness","created":"2022-03-01","cited_by_count":11}],"next_cursor":null}