{"list":"other","total":62,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"1706.08947","title":"Exploring Generalization in Deep Learning","created":"2017-06-27","cited_by_count":600},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"id":"1806.08342","title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","created":"2018-06-21","cited_by_count":521},{"id":"2204.01697","title":"MaxViT: Multi-Axis Vision Transformer","created":"2022-04-04","cited_by_count":476},{"id":"1905.13655","title":"Implicit Regularization in Deep Matrix Factorization","created":"2019-05-31","cited_by_count":405},{"id":"1412.6614","title":"In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning","created":"2014-12-20","cited_by_count":342},{"id":"1705.09280","title":"Implicit Regularization in Matrix Factorization","created":"2017-05-25","cited_by_count":322},{"id":"1802.05296","title":"Stronger generalization bounds for deep nets via a compression approach","created":"2018-02-14","cited_by_count":307},{"id":"1405.3866","title":"Speeding up Convolutional Neural Networks with Low Rank Expansions","created":"2014-05-15","cited_by_count":284},{"id":"2102.04626","title":"Physics-informed neural networks with hard constraints for inverse design","created":"2021-02-09","cited_by_count":280},{"id":"2403.07378","title":"SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression","created":"2024-03-12","cited_by_count":243},{"id":"1412.6553","title":"Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition","created":"2014-12-19","cited_by_count":203},{"id":"2308.06767","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","created":"2023-08-13","cited_by_count":202},{"id":"2207.00112","title":"Language model compression with weighted low-rank factorization","created":"2022-06-30","cited_by_count":195},{"id":"2312.05821","title":"ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models","created":"2023-12-10","cited_by_count":169},{"id":"2012.09839","title":"Towards Resolving the Implicit Bias of Gradient Descent for Matrix Factorization: Greedy Low-Rank Learning","created":"2020-12-17","cited_by_count":150},{"id":"1407.1065","title":"Phase Retrieval via Wirtinger Flow: Theory and Algorithms","created":"2014-07-03","cited_by_count":125},{"id":"1904.13262","title":"Implicit Regularization of Discrete Gradient Dynamics in Linear Neural Networks","created":"2019-04-30","cited_by_count":124},{"id":"2005.06398","title":"Implicit Regularization in Deep Learning May Not Be Explainable by Norms","created":"2020-05-13","cited_by_count":119},{"id":"1506.03648","title":"Constrained Convolutional Neural Networks for Weakly Supervised Segmentation","created":"2015-06-11","cited_by_count":100},{"id":"2002.10553","title":"Neural Networks are Convex Regularizers: Exact Polynomial-time Convex Optimization Formulations for Two-layer Networks","created":"2020-02-24","cited_by_count":98},{"id":"1709.01953","title":"Implicit Regularization in Deep Learning","created":"2017-09-06","cited_by_count":90},{"id":"1607.00485","title":"Group Sparse Regularization for Deep Neural Networks","created":"2016-07-02","cited_by_count":89},{"id":"1411.8003","title":"Guaranteed Matrix Completion via Non-convex Factorization","created":"2014-11-28","cited_by_count":82},{"id":"1805.04628","title":"Constrained-CNN losses for weakly supervised segmentation","created":"2018-05-12","cited_by_count":62},{"id":"1810.00861","title":"ProxQuant: Quantized Neural Networks via Proximal Operators","created":"2018-10-01","cited_by_count":59},{"id":"2201.12760","title":"Implicit Regularization Towards Rank Minimization in ReLU Networks","created":"2022-01-30","cited_by_count":53},{"id":"1701.00794","title":"Constrained Deep Weak Supervision for Histopathology Image Segmentation","created":"2017-01-03","cited_by_count":51},{"id":"2206.06072","title":"Rank Diminishing in Deep Neural Networks","created":"2022-06-13","cited_by_count":47},{"id":"1606.04970","title":"The non-convex Burer-Monteiro approach works on smooth semidefinite programs","created":"2016-06-15","cited_by_count":46},{"id":"1706.02025","title":"Imposing Hard Constraints on Deep Networks: Promises and Limitations","created":"2017-06-07","cited_by_count":43},{"id":"1509.03917","title":"Dropping Convexity for Faster Semi-definite Optimization","created":"2015-09-14","cited_by_count":40},{"id":"2012.08749","title":"Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks","created":"2020-12-16","cited_by_count":40},{"id":"1609.03240","title":"Non-square matrix sensing without spurious local minima via the Burer-Monteiro approach","created":"2016-09-12","cited_by_count":38},{"id":"2012.13329","title":"Vector-output ReLU Neural Network Problems are Copositive Programs: Convex Analysis of Two Layer Networks and Polynomial-time Algorithms","created":"2020-12-24","cited_by_count":34},{"id":"2201.11968","title":"Training invariances and the low-rank phenomenon: beyond linear networks","created":"2022-01-28","cited_by_count":33},{"id":"1906.11357","title":"An Inexact Augmented Lagrangian Framework for Nonconvex Optimization with Nonlinear Constraints","created":"2019-06-26","cited_by_count":29},{"id":"1602.04915","title":"Gradient Descent Converges to Minimizers","created":"2016-02-16","cited_by_count":25},{"id":"2010.07243","title":"Deep Neural Network Training with Frank-Wolfe","created":"2020-10-14","cited_by_count":23},{"id":"1606.03168","title":"Finding Low-Rank Solutions via Non-Convex Matrix Factorization, Efficiently and Provably","created":"2016-06-10","cited_by_count":22},{"id":"1805.01532","title":"Lifted Neural Networks","created":"2018-05-03","cited_by_count":20},{"id":"1804.02008","title":"Deterministic guarantees for Burer-Monteiro factorizations of smooth semidefinite programs","created":"2018-04-05","cited_by_count":19},{"id":"2205.11921","title":"Compression-aware Training of Neural Networks using Frank-Wolfe","created":"2022-05-24","cited_by_count":16},{"id":"2101.02429","title":"Neural Spectrahedra and Semidefinite Lifts: Global Convex Optimization of Polynomial Activation Neural Networks in Fully Polynomial-Time","created":"2021-01-07","cited_by_count":14},{"id":"1906.05032","title":"Decoupling Gating from Linearity","created":"2019-06-12","cited_by_count":13},{"id":"1812.03046","title":"Rank optimality for the Burer-Monteiro factorization","created":"2018-12-07","cited_by_count":12},{"id":"2001.04264","title":"On implicit regularization: Morse functions and applications to matrix factorization","created":"2020-01-13","cited_by_count":11},{"id":"1904.07147","title":"On the Burer-Monteiro method for general semidefinite programs","created":"2019-04-15","cited_by_count":8},{"id":"2110.03274","title":"Three Operator Splitting with Subgradients, Stochastic Gradients, and Adaptive Learning Rates","created":"2021-10-07","cited_by_count":6},{"id":"2110.08105","title":"Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings","created":"2021-10-15","cited_by_count":5},{"id":"2204.14067","title":"Accelerating nuclear-norm regularized low-rank matrix optimization through Burer-Monteiro decomposition","created":"2022-04-29","cited_by_count":5},{"id":"2208.07469","title":"Semidefinite Programming versus Burer-Monteiro Factorization for Matrix Sensing","created":"2022-08-15","cited_by_count":5},{"id":"2410.22311","title":"Convex Formulations for Training Two-Layer ReLU Neural Networks","created":"2024-10-29","cited_by_count":4},{"id":"2210.03069","title":"PathProx: A Proximal Gradient Algorithm for Weight Decay Regularized Deep Neural Networks","created":"2022-10-06","cited_by_count":2}],"next_cursor":null}