{"list":"other","total":58,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"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":"1606.04838","title":"Optimization Methods for Large-Scale Machine Learning","created":"2016-06-15","cited_by_count":1150},{"id":"1812.11118","title":"Reconciling modern machine learning practice and the bias-variance trade-off","created":"2018-12-28","cited_by_count":927},{"id":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"1706.08947","title":"Exploring Generalization in Deep Learning","created":"2017-06-27","cited_by_count":600},{"id":"1901.08584","title":"Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks","created":"2019-01-24","cited_by_count":566},{"id":"1509.01240","title":"Train faster, generalize better: Stability of stochastic gradient descent","created":"2015-09-03","cited_by_count":552},{"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":"1703.04933","title":"Sharp Minima Can Generalize For Deep Nets","created":"2017-03-15","cited_by_count":466},{"id":"1611.01838","title":"Entropy-SGD: Biasing Gradient Descent Into Wide Valleys","created":"2016-11-06","cited_by_count":359},{"id":"1905.11881","title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","created":"2019-05-28","cited_by_count":341},{"id":"1707.09564","title":"A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks","created":"2017-07-29","cited_by_count":314},{"id":"1802.05296","title":"Stronger generalization bounds for deep nets via a compression approach","created":"2018-02-14","cited_by_count":307},{"id":"1705.07809","title":"Information-theoretic analysis of generalization capability of learning algorithms","created":"2017-05-22","cited_by_count":303},{"id":"1503.00036","title":"Norm-Based Capacity Control in Neural Networks","created":"2015-02-27","cited_by_count":299},{"id":"1912.07145","title":"PyHessian: Neural Networks Through the Lens of the Hessian","created":"2019-12-16","cited_by_count":292},{"id":"1711.04623","title":"Three Factors Influencing Minima in SGD","created":"2017-11-13","cited_by_count":273},{"id":"1708.02182","title":"Regularizing and Optimizing LSTM Language Models","created":"2017-08-07","cited_by_count":205},{"id":"2006.06914","title":"Stability of Stochastic Gradient Descent on Nonsmooth Convex Losses","created":"2020-06-12","cited_by_count":173},{"id":"2001.09122","title":"Reasoning About Generalization via Conditional Mutual Information","created":"2020-01-24","cited_by_count":147},{"id":"1805.12076","title":"Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks","created":"2018-05-30","cited_by_count":142},{"id":"1911.02151","title":"Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates","created":"2019-11-06","cited_by_count":119},{"id":"2006.08157","title":"Fine-Grained Analysis of Stability and Generalization for Stochastic Gradient Descent","created":"2020-06-15","cited_by_count":119},{"id":"1901.04609","title":"Tightening Mutual Information Based Bounds on Generalization Error","created":"2019-01-15","cited_by_count":117},{"id":"2002.11328","title":"Rethinking Bias-Variance Trade-off for Generalization of Neural Networks","created":"2020-02-26","cited_by_count":107},{"id":"1902.10710","title":"High probability generalization bounds for uniformly stable algorithms with nearly optimal rate","created":"2019-02-27","cited_by_count":98},{"id":"1511.05219","title":"How much does your data exploration overfit? Controlling bias via information usage","created":"2015-11-16","cited_by_count":95},{"id":"2004.12983","title":"Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithms","created":"2020-04-27","cited_by_count":89},{"id":"2102.00931","title":"Information-Theoretic Generalization Bounds for Stochastic Gradient Descent","created":"2021-02-01","cited_by_count":84},{"id":"1506.02629","title":"Generalization in Adaptive Data Analysis and Holdout Reuse","created":"2015-06-08","cited_by_count":83},{"id":"1801.04295","title":"Generalization Error Bounds for Noisy, Iterative Algorithms","created":"2018-01-12","cited_by_count":82},{"id":"1912.10985","title":"BackPACK: Packing more into backprop","created":"2019-12-23","cited_by_count":78},{"id":"2010.04925","title":"Regularizing Neural Networks via Adversarial Model Perturbation","created":"2020-10-10","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":"1806.03803","title":"Chaining Mutual Information and Tightening Generalization Bounds","created":"2018-06-11","cited_by_count":65},{"id":"2002.08709","title":"Do We Need Zero Training Loss After Achieving Zero Training Error?","created":"2020-02-20","cited_by_count":61},{"id":"1804.01619","title":"Stability and Convergence Trade-off of Iterative Optimization Algorithms","created":"2018-04-04","cited_by_count":53},{"id":"2007.07368","title":"Explicit Regularisation in Gaussian Noise Injections","created":"2020-07-14","cited_by_count":37},{"id":"2012.09922","title":"Individually Conditional Individual Mutual Information Bound on Generalization Error","created":"2020-12-17","cited_by_count":30},{"id":"1709.06617","title":"A PAC-Bayesian Analysis of Randomized Learning with Application to Stochastic Gradient Descent","created":"2017-09-19","cited_by_count":29},{"id":"2007.04532","title":"A Study of Gradient Variance in Deep Learning","created":"2020-07-09","cited_by_count":28},{"id":"2010.10994","title":"On Random Subset Generalization Error Bounds and the Stochastic Gradient Langevin Dynamics Algorithm","created":"2020-10-21","cited_by_count":28},{"id":"2011.06220","title":"Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgetting","created":"2020-11-12","cited_by_count":28},{"id":"2103.17182","title":"Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization","created":"2021-03-31","cited_by_count":28},{"id":"2102.07006","title":"Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections","created":"2021-02-13","cited_by_count":12},{"id":"1906.11148","title":"Chaining Meets Chain Rule: Multilevel Entropic Regularization and Training of Neural Nets","created":"2019-06-26","cited_by_count":6}],"next_cursor":null}