{"list":"other","total":66,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1712.05877","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","created":"2017-12-15","cited_by_count":1593},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"1511.00363","title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","created":"2015-11-02","cited_by_count":592},{"id":"1606.06160","title":"DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients","created":"2016-06-20","cited_by_count":569},{"id":"2106.08295","title":"A White Paper on Neural Network Quantization","created":"2021-06-15","cited_by_count":472},{"id":"1802.05668","title":"Model compression via distillation and quantization","created":"2018-02-15","cited_by_count":289},{"id":"1807.10029","title":"LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks","created":"2018-07-26","cited_by_count":274},{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263},{"id":"1808.00278","title":"Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm","created":"2018-08-01","cited_by_count":235},{"id":"1612.01064","title":"Trained Ternary Quantization","created":"2016-12-04","cited_by_count":208},{"id":"1605.04711","title":"Ternary Weight Networks","created":"2016-05-16","cited_by_count":204},{"id":"1902.06822","title":"Low-bit Quantization of Neural Networks for Efficient Inference","created":"2019-02-18","cited_by_count":193},{"id":"2004.03333","title":"Binary Neural Networks: A Survey","created":"2020-03-31","cited_by_count":190},{"id":"2004.09576","title":"LSQ+: Improving low-bit quantization through learnable offsets and better initialization","created":"2020-04-20","cited_by_count":189},{"id":"2003.03488","title":"ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions","created":"2020-03-07","cited_by_count":184},{"id":"1812.08011","title":"Training Deep Neural Networks with 8-bit Floating Point Numbers","created":"2018-12-19","cited_by_count":164},{"id":"1909.13144","title":"Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networks","created":"2019-09-28","cited_by_count":148},{"id":"1805.11046","title":"Scalable Methods for 8-bit Training of Neural Networks","created":"2018-05-25","cited_by_count":142},{"id":"1611.05128","title":"Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning","created":"2016-11-16","cited_by_count":134},{"id":"1804.07795","title":"Stochastic subgradient method converges on tame functions","created":"2018-04-20","cited_by_count":124},{"id":"1402.0030","title":"Neural Variational Inference and Learning in Belief Networks","created":"2014-01-31","cited_by_count":117},{"id":"2003.11535","title":"Training Binary Neural Networks with Real-to-Binary Convolutions","created":"2020-03-25","cited_by_count":112},{"id":"1711.05852","title":"Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy","created":"2017-11-15","cited_by_count":101},{"id":"2107.04562","title":"The Bayesian Learning Rule","created":"2021-07-09","cited_by_count":99},{"id":"2009.13055","title":"Rotated Binary Neural Network","created":"2020-09-28","cited_by_count":77},{"id":"1706.02379","title":"Training Quantized Nets: A Deeper Understanding","created":"2017-06-07","cited_by_count":75},{"id":"1808.04752","title":"A Survey on Methods and Theories of Quantized Neural Networks","created":"2018-08-13","cited_by_count":75},{"id":"1712.01048","title":"Adaptive Quantization for Deep Neural Network","created":"2017-12-04","cited_by_count":67},{"id":"1707.09870","title":"Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMM","created":"2017-07-24","cited_by_count":61},{"id":"1904.02823","title":"Regularizing Activation Distribution for Training Binarized Deep Networks","created":"2019-04-04","cited_by_count":61},{"id":"1810.00861","title":"ProxQuant: Quantized Neural Networks via Proximal Operators","created":"2018-10-01","cited_by_count":59},{"id":"1709.01134","title":"WRPN: Wide Reduced-Precision Networks","created":"2017-09-04","cited_by_count":51},{"id":"2010.14298","title":"A Statistical Framework for Low-bitwidth Training of Deep Neural Networks","created":"2020-10-27","cited_by_count":51},{"id":"2208.08084","title":"AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets","created":"2022-08-17","cited_by_count":38},{"id":"1511.05176","title":"MuProp: Unbiased Backpropagation for Stochastic Neural Networks","created":"2015-11-16","cited_by_count":37},{"id":"2001.05936","title":"MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy?","created":"2020-01-16","cited_by_count":32},{"id":"1802.08635","title":"Loss-aware Weight Quantization of Deep Networks","created":"2018-02-23","cited_by_count":31},{"id":"1601.06071","title":"Bitwise Neural Networks","created":"2016-01-22","cited_by_count":29},{"id":"2112.10769","title":"Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats","created":"2021-12-19","cited_by_count":26},{"id":"1807.00301","title":"SYQ: Learning Symmetric Quantization For Efficient Deep Neural Networks","created":"2018-07-01","cited_by_count":24},{"id":"1802.02733","title":"From Hashing to CNNs: Training BinaryWeight Networks via Hashing","created":"2018-02-08","cited_by_count":23},{"id":"2002.10778","title":"Training Binary Neural Networks using the Bayesian Learning Rule","created":"2020-02-25","cited_by_count":23},{"id":"1705.07199","title":"The High-Dimensional Geometry of Binary Neural Networks","created":"2017-05-19","cited_by_count":22},{"id":"1711.00215","title":"Minimum Energy Quantized Neural Networks","created":"2017-11-01","cited_by_count":21},{"id":"1809.03368","title":"Probabilistic Binary Neural Networks","created":"2018-09-10","cited_by_count":21},{"id":"2106.02295","title":"Differentiable Dynamic Quantization with Mixed Precision and Adaptive Resolution","created":"2021-06-04","cited_by_count":20},{"id":"1807.06964","title":"Bridging the Accuracy Gap for 2-bit Quantized Neural Networks (QNN)","created":"2018-07-17","cited_by_count":19},{"id":"1910.08237","title":"Mirror Descent View for Neural Network Quantization","created":"2019-10-18","cited_by_count":16},{"id":"1812.11732","title":"Per-Tensor Fixed-Point Quantization of the Back-Propagation Algorithm","created":"2018-12-31","cited_by_count":15},{"id":"2006.06880","title":"Reintroducing Straight-Through Estimators as Principled Methods for Stochastic Binary Networks","created":"2020-06-11","cited_by_count":15},{"id":"1406.2989","title":"Techniques for Learning Binary Stochastic Feedforward Neural Networks","created":"2014-06-11","cited_by_count":14},{"id":"2107.08225","title":"On Constraints in First-Order Optimization: A View from Non-Smooth Dynamical Systems","created":"2021-07-17","cited_by_count":13},{"id":"2004.04729","title":"Dithered backprop: A sparse and quantized backpropagation algorithm for more efficient deep neural network training","created":"2020-04-09","cited_by_count":11},{"id":"2112.02880","title":"AdaSTE: An Adaptive Straight-Through Estimator to Train Binary Neural Networks","created":"2021-12-06","cited_by_count":11},{"id":"1802.08530","title":"Training wide residual networks for deployment using a single bit for each weight","created":"2018-02-23","cited_by_count":10},{"id":"1707.04319","title":"Model compression as constrained optimization, with application to neural nets. Part II: quantization","created":"2017-07-13","cited_by_count":8},{"id":"2105.04246","title":"In-Hindsight Quantization Range Estimation for Quantized Training","created":"2021-05-10","cited_by_count":7},{"id":"1812.04353","title":"Proximal Mean-field for Neural Network Quantization","created":"2018-12-11","cited_by_count":6},{"id":"2110.03549","title":"Bias-Variance Tradeoffs in Single-Sample Binary Gradient Estimators","created":"2021-10-07","cited_by_count":4},{"id":"2011.14824","title":"A Review of Recent Advances of Binary Neural Networks for Edge Computing","created":"2020-11-24","cited_by_count":3}],"next_cursor":null}