{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"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":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"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":"1812.11118","title":"Reconciling modern machine learning practice and the bias-variance trade-off","created":"2018-12-28","cited_by_count":927},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"1904.09237","title":"On the Convergence of Adam and Beyond","created":"2019-04-19","cited_by_count":841},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"id":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"1606.04474","title":"Learning to learn by gradient descent by gradient descent","created":"2016-06-14","cited_by_count":620},{"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":"1708.03888","title":"Large Batch Training of Convolutional Networks","created":"2017-08-13","cited_by_count":535},{"id":"1903.08560","title":"Surprises in High-Dimensional Ridgeless Least Squares Interpolation","created":"2019-03-19","cited_by_count":513},{"id":"1703.04933","title":"Sharp Minima Can Generalize For Deep Nets","created":"2017-03-15","cited_by_count":466},{"id":"1609.07061","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","created":"2016-09-22","cited_by_count":426},{"id":"2106.04399","title":"Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation","created":"2021-06-08","cited_by_count":392},{"id":"1904.05801","title":"Bridging Theory and Algorithm for Domain Adaptation","created":"2019-04-11","cited_by_count":332},{"id":"2104.08894","title":"The Intrinsic Dimension of Images and Its Impact on Learning","created":"2021-04-18","cited_by_count":315},{"id":"1703.02930","title":"Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networks","created":"2017-03-08","cited_by_count":311},{"id":"1905.12784","title":"Intrinsic dimension of data representations in deep neural networks","created":"2019-05-29","cited_by_count":282},{"id":"2011.15091","title":"Inductive Biases for Deep Learning of Higher-Level Cognition","created":"2020-11-30","cited_by_count":275},{"id":"1705.08292","title":"The Marginal Value of Adaptive Gradient Methods in Machine Learning","created":"2017-05-23","cited_by_count":250},{"id":"1612.01064","title":"Trained Ternary Quantization","created":"2016-12-04","cited_by_count":208},{"id":"2004.09602","title":"Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation","created":"2020-04-20","cited_by_count":188},{"id":"1805.11046","title":"Scalable Methods for 8-bit Training of Neural Networks","created":"2018-05-25","cited_by_count":142},{"id":"1712.07628","title":"Improving Generalization Performance by Switching from Adam to SGD","created":"2017-12-20","cited_by_count":125},{"id":"2003.04475","title":"Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift","created":"2020-03-10","cited_by_count":125},{"id":"2107.00793","title":"The Causal-Neural Connection: Expressiveness, Learnability, and Inference","created":"2021-07-02","cited_by_count":98},{"id":"1802.04680","title":"Training and Inference with Integers in Deep Neural Networks","created":"2018-02-13","cited_by_count":86},{"id":"2211.13609","title":"PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization","created":"2022-11-24","cited_by_count":76},{"id":"1802.07044","title":"The Description Length of Deep Learning Models","created":"2018-02-20","cited_by_count":72},{"id":"2111.13171","title":"Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks","created":"2021-11-25","cited_by_count":70},{"id":"1911.00623","title":"On-Device Machine Learning: An Algorithms and Learning Theory Perspective","created":"2019-11-02","cited_by_count":63},{"id":"1509.07385","title":"Provable approximation properties for deep neural networks","created":"2015-09-24","cited_by_count":60},{"id":"1802.04474","title":"Deep Neural Networks Learn Non-Smooth Functions Effectively","created":"2018-02-13","cited_by_count":57},{"id":"2211.09760","title":"VeLO: Training Versatile Learned Optimizers by Scaling Up","created":"2022-11-17","cited_by_count":57},{"id":"2106.11344","title":"f-Domain-Adversarial Learning: Theory and Algorithms","created":"2021-06-21","cited_by_count":47},{"id":"1504.07676","title":"Explaining the Success of AdaBoost and Random Forests as Interpolating Classifiers","created":"2015-04-28","cited_by_count":45},{"id":"1802.00930","title":"Mixed Precision Training of Convolutional Neural Networks using Integer Operations","created":"2018-02-03","cited_by_count":45},{"id":"2209.13083","title":"Why neural networks find simple solutions: the many regularizers of geometric complexity","created":"2022-09-27","cited_by_count":39},{"id":"2111.05275","title":"Towards a Unified Information-Theoretic Framework for Generalization","created":"2021-11-09","cited_by_count":30},{"id":"2111.05529","title":"Understanding the Generalization Benefit of Model Invariance from a Data Perspective","created":"2021-11-10","cited_by_count":22},{"id":"2009.13108","title":"NITI: Training Integer Neural Networks Using Integer-only Arithmetic","created":"2020-09-28","cited_by_count":20},{"id":"2011.02256","title":"Advantage of Deep Neural Networks for Estimating Functions with Singularity on Hypersurfaces","created":"2020-11-04","cited_by_count":17},{"id":"2206.09909","title":"Low-Precision Stochastic Gradient Langevin Dynamics","created":"2022-06-20","cited_by_count":12},{"id":"2207.08822","title":"Is Integer Arithmetic Enough for Deep Learning Training?","created":"2022-07-18","cited_by_count":12},{"id":"1811.00658","title":"Non-monotone Behavior of the Heavy Ball Method","created":"2018-11-01","cited_by_count":8},{"id":"2301.01651","title":"On the Convergence of Stochastic Gradient Descent in Low-precision Number Formats","created":"2023-01-04","cited_by_count":4},{"id":"2211.04655","title":"Perturbed Iterate SGD for Lipschitz Continuous Loss Functions with Numerical Error and Adaptive Step Sizes","created":"2022-11-09","cited_by_count":1}],"next_cursor":null}