{"list":"other","total":51,"rows":[{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"1802.01548","title":"Regularized Evolution for Image Classifier Architecture Search","created":"2018-02-05","cited_by_count":909},{"id":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"1805.09501","title":"AutoAugment: Learning Augmentation Policies from Data","created":"2018-05-24","cited_by_count":730},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"1712.00559","title":"Progressive Neural Architecture Search","created":"2017-12-02","cited_by_count":487},{"id":"1812.03443","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","created":"2018-12-09","cited_by_count":485},{"id":"2001.00326","title":"NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search","created":"2020-01-02","cited_by_count":416},{"id":"1904.00420","title":"Single Path One-Shot Neural Architecture Search with Uniform Sampling","created":"2019-03-31","cited_by_count":414},{"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":"1906.11829","title":"Selection via Proxy: Efficient Data Selection for Deep Learning","created":"2019-06-26","cited_by_count":339},{"id":"1803.00942","title":"Not All Samples Are Created Equal: Deep Learning with Importance Sampling","created":"2018-03-02","cited_by_count":328},{"id":"1812.09926","title":"SNAS: Stochastic Neural Architecture Search","created":"2018-12-24","cited_by_count":289},{"id":"1611.02167","title":"Designing Neural Network Architectures using Reinforcement Learning","created":"2016-11-07","cited_by_count":279},{"id":"1910.04465","title":"Searching for A Robust Neural Architecture in Four GPU Hours","created":"2019-10-10","cited_by_count":260},{"id":"1902.07638","title":"Random Search and Reproducibility for Neural Architecture Search","created":"2019-02-20","cited_by_count":254},{"id":"1605.07648","title":"FractalNet: Ultra-Deep Neural Networks without Residuals","created":"2016-05-24","cited_by_count":216},{"id":"2102.11535","title":"Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective","created":"2021-02-23","cited_by_count":169},{"id":"1309.2388","title":"Minimizing Finite Sums with the Stochastic Average Gradient","created":"2013-09-10","cited_by_count":164},{"id":"1704.07433","title":"Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samples","created":"2017-04-24","cited_by_count":147},{"id":"1310.5715","title":"Stochastic Gradient Descent, Weighted Sampling, and the Randomized Kaczmarz algorithm","created":"2013-10-21","cited_by_count":133},{"id":"1911.12126","title":"Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search","created":"2019-11-27","cited_by_count":131},{"id":"1907.01845","title":"FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search","created":"2019-07-03","cited_by_count":130},{"id":"1902.08142","title":"Evaluating the Search Phase of Neural Architecture Search","created":"2019-02-21","cited_by_count":120},{"id":"1910.00762","title":"Accelerating Deep Learning by Focusing on the Biggest Losers","created":"2019-10-02","cited_by_count":94},{"id":"2108.04392","title":"Rethinking Architecture Selection in Differentiable NAS","created":"2021-08-10","cited_by_count":92},{"id":"1401.2753","title":"Stochastic Optimization with Importance Sampling","created":"2014-01-13","cited_by_count":91},{"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":"2009.01027","title":"DARTS-: Robustly Stepping out of Performance Collapse Without Indicators","created":"2020-09-02","cited_by_count":81},{"id":"1511.06481","title":"Variance Reduction in SGD by Distributed Importance Sampling","created":"2015-11-20","cited_by_count":79},{"id":"2001.10422","title":"NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture Search","created":"2020-01-28","cited_by_count":64},{"id":"2008.03064","title":"Evaluating Efficient Performance Estimators of Neural Architectures","created":"2020-08-07","cited_by_count":55},{"id":"2006.06863","title":"Few-shot Neural Architecture Search","created":"2020-06-11","cited_by_count":50},{"id":"1706.00043","title":"Biased Importance Sampling for Deep Neural Network Training","created":"2017-05-31","cited_by_count":31},{"id":"2203.15207","title":"Generalizing Few-Shot NAS with Gradient Matching","created":"2022-03-29","cited_by_count":25},{"id":"2106.06442","title":"K-shot NAS: Learnable Weight-Sharing for NAS with K-shot Supernets","created":"2021-06-11","cited_by_count":22},{"id":"2108.12821","title":"Analyzing and Mitigating Interference in Neural Architecture Search","created":"2021-08-29","cited_by_count":20},{"id":"2110.04743","title":"ZARTS: On Zero-order Optimization for Neural Architecture Search","created":"2021-10-10","cited_by_count":18},{"id":"2203.08887","title":"On Redundancy and Diversity in Cell-based Neural Architecture Search","created":"2022-03-16","cited_by_count":18},{"id":"1905.03381","title":"AutoAssist: A Framework to Accelerate Training of Deep Neural Networks","created":"2019-05-08","cited_by_count":14},{"id":"2003.12563","title":"DA-NAS: Data Adapted Pruning for Efficient Neural Architecture Search","created":"2020-03-27","cited_by_count":14},{"id":"2001.05887","title":"MixPath: A Unified Approach for One-shot Neural Architecture Search","created":"2020-01-16","cited_by_count":7},{"id":"1603.05544","title":"Accelerating Deep Neural Network Training with Inconsistent Stochastic Gradient Descent","created":"2016-03-17","cited_by_count":6},{"id":"2111.13204","title":"BaLeNAS: Differentiable Architecture Search via the Bayesian Learning Rule","created":"2021-11-25","cited_by_count":5},{"id":"2207.07868","title":"CLOSE: Curriculum Learning On the Sharing Extent Towards Better One-shot NAS","created":"2022-07-16","cited_by_count":5}],"next_cursor":null}