{"list":"other","total":56,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1901.08573","title":"Theoretically Principled Trade-off between Robustness and Accuracy","created":"2019-01-24","cited_by_count":1517},{"id":"1609.04747","title":"An overview of gradient descent optimization algorithms","created":"2016-09-15","cited_by_count":1033},{"id":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567},{"id":"2102.00554","title":"Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks","created":"2021-01-31","cited_by_count":527},{"id":"1911.11134","title":"Rigging the Lottery: Making All Tickets Winners","created":"2019-11-25","cited_by_count":495},{"id":"1801.00553","title":"Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey","created":"2018-01-02","cited_by_count":460},{"id":"1407.0202","title":"SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives","created":"2014-07-01","cited_by_count":402},{"id":"1707.04780","title":"Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science","created":"2017-07-15","cited_by_count":328},{"id":"1905.10018","title":"Momentum-Based Variance Reduction in Non-Convex SGD","created":"2019-05-24","cited_by_count":306},{"id":"1807.01695","title":"SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path Integrated Differential Estimator","created":"2018-07-04","cited_by_count":287},{"id":"1703.00102","title":"SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient","created":"2017-03-01","cited_by_count":220},{"id":"1907.04840","title":"Sparse Networks from Scratch: Faster Training without Losing Performance","created":"2019-07-10","cited_by_count":213},{"id":"1902.05967","title":"Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization","created":"2019-02-15","cited_by_count":189},{"id":"1603.06160","title":"Stochastic Variance Reduction for Nonconvex Optimization","created":"2016-03-19","cited_by_count":145},{"id":"1711.05136","title":"Deep Rewiring: Training very sparse deep networks","created":"2017-11-14","cited_by_count":139},{"id":"2102.02887","title":"Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training","created":"2021-02-04","cited_by_count":110},{"id":"2102.08124","title":"Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks","created":"2021-02-16","cited_by_count":103},{"id":"1903.12561","title":"Adversarial Robustness vs Model Compression, or Both?","created":"2019-03-29","cited_by_count":98},{"id":"1905.11261","title":"A Unified Theory of SGD: Variance Reduction, Sampling, Quantization and Coordinate Descent","created":"2019-05-27","cited_by_count":84},{"id":"2010.00892","title":"Variance-Reduced Methods for Machine Learning","created":"2020-10-02","cited_by_count":79},{"id":"2106.03517","title":"Top-KAST: Top-K Always Sparse Training","created":"2021-06-07","cited_by_count":79},{"id":"1403.4699","title":"A Proximal Stochastic Gradient Method with Progressive Variance Reduction","created":"2014-03-19","cited_by_count":78},{"id":"2010.03533","title":"Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win","created":"2020-10-07","cited_by_count":77},{"id":"2112.00029","title":"Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models","created":"2021-11-30","cited_by_count":76},{"id":"1603.05643","title":"Variance Reduction for Faster Non-Convex Optimization","created":"2016-03-17","cited_by_count":72},{"id":"2212.06152","title":"Accelerating Dataset Distillation via Model Augmentation","created":"2022-12-12","cited_by_count":62},{"id":"2206.10369","title":"The State of Sparse Training in Deep Reinforcement Learning","created":"2022-06-17","cited_by_count":61},{"id":"1906.03728","title":"The Generalization-Stability Tradeoff In Neural Network Pruning","created":"2019-06-09","cited_by_count":54},{"id":"2110.00296","title":"Powerpropagation: A sparsity inducing weight reparameterisation","created":"2021-10-01","cited_by_count":49},{"id":"2105.01571","title":"Effective Sparsification of Neural Networks with Global Sparsity Constraint","created":"2021-05-03","cited_by_count":45},{"id":"1907.01003","title":"Accurate, reliable and fast robustness evaluation","created":"2019-07-01","cited_by_count":43},{"id":"2011.03083","title":"A Tunable Robust Pruning Framework Through Dynamic Network Rewiring of DNNs","created":"2020-11-03","cited_by_count":37},{"id":"2108.05574","title":"Implicit Sparse Regularization: The Impact of Depth and Early Stopping","created":"2021-08-12","cited_by_count":30},{"id":"2111.05685","title":"Efficient Neural Network Training via Forward and Backward Propagation Sparsification","created":"2021-11-10","cited_by_count":30},{"id":"2110.10030","title":"Accelerating Framework of Transformer by Hardware Design and Model Compression Co-Optimization","created":"2021-10-19","cited_by_count":27},{"id":"1706.05439","title":"Control Variates for Stochastic Gradient MCMC","created":"2017-06-16","cited_by_count":25},{"id":"2112.11027","title":"More is Less: Inducing Sparsity via Overparameterization","created":"2021-12-21","cited_by_count":24},{"id":"1802.05431","title":"On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo","created":"2018-02-15","cited_by_count":19},{"id":"2207.08629","title":"Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks","created":"2022-07-18","cited_by_count":18},{"id":"2211.16667","title":"Dynamic Sparse Training via Balancing the Exploration-Exploitation Trade-off","created":"2022-11-30","cited_by_count":15},{"id":"2206.00395","title":"Optimization with Access to Auxiliary Information","created":"2022-06-01","cited_by_count":13},{"id":"2010.01084","title":"Accelerating Convergence of Replica Exchange Stochastic Gradient MCMC via Variance Reduction","created":"2020-10-02","cited_by_count":10},{"id":"1802.09932","title":"VR-SGD: A Simple Stochastic Variance Reduction Method for Machine Learning","created":"2018-02-26","cited_by_count":7},{"id":"1905.13074","title":"Robust Sparse Regularization: Simultaneously Optimizing Neural Network Robustness and Compactness","created":"2019-05-30","cited_by_count":7},{"id":"2201.10360","title":"Resource-efficient Deep Neural Networks for Automotive Radar Interference Mitigation","created":"2022-01-25","cited_by_count":6},{"id":"2001.09623","title":"Variance Reduction with Sparse Gradients","created":"2020-01-27","cited_by_count":5},{"id":"2103.15767","title":"[Reproducibility Report] Rigging the Lottery: Making All Tickets Winners","created":"2021-03-29","cited_by_count":4},{"id":"1709.01180","title":"A Convergence Analysis for A Class of Practical Variance-Reduction Stochastic Gradient MCMC","created":"2017-09-04","cited_by_count":3}],"next_cursor":null}