{"list":"other","total":64,"rows":[{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"1608.03665","title":"Learning Structured Sparsity in Deep Neural Networks","created":"2016-08-12","cited_by_count":541},{"id":"1608.04636","title":"Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-\\L{}ojasiewicz Condition","created":"2016-08-16","cited_by_count":539},{"id":"1911.11134","title":"Rigging the Lottery: Making All Tickets Winners","created":"2019-11-25","cited_by_count":495},{"id":"2006.05467","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","created":"2020-06-09","cited_by_count":479},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"1705.09280","title":"Implicit Regularization in Matrix Factorization","created":"2017-05-25","cited_by_count":322},{"id":"2002.09277","title":"Kernel and Rich Regimes in Overparametrized Models","created":"2020-02-20","cited_by_count":306},{"id":"2002.04486","title":"Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss","created":"2020-02-11","cited_by_count":268},{"id":"1802.08246","title":"Characterizing Implicit Bias in Terms of Optimization Geometry","created":"2018-02-22","cited_by_count":266},{"id":"2111.00364","title":"Sustainable AI: Environmental Implications, Challenges and Opportunities","created":"2021-10-30","cited_by_count":242},{"id":"2003.02389","title":"Comparing Rewinding and Fine-tuning in Neural Network Pruning","created":"2020-03-05","cited_by_count":240},{"id":"1907.04840","title":"Sparse Networks from Scratch: Faster Training without Losing Performance","created":"2019-07-10","cited_by_count":213},{"id":"2002.00585","title":"Proving the Lottery Ticket Hypothesis: Pruning is All You Need","created":"2020-02-03","cited_by_count":201},{"id":"2311.16863","title":"Power Hungry Processing: Watts Driving the Cost of AI Deployment?","created":"2023-11-28","cited_by_count":191},{"id":"2009.08576","title":"Pruning Neural Networks at Initialization: Why are We Missing the Mark?","created":"2020-09-18","cited_by_count":182},{"id":"1909.11957","title":"Drawing Early-Bird Tickets: Towards More Efficient Training of Deep Networks","created":"2019-09-26","cited_by_count":160},{"id":"2002.03231","title":"Soft Threshold Weight Reparameterization for Learnable Sparsity","created":"2020-02-08","cited_by_count":151},{"id":"2106.09524","title":"Implicit Bias of SGD for Diagonal Linear Networks: a Provable Benefit of Stochasticity","created":"2021-06-17","cited_by_count":110},{"id":"1912.04427","title":"Winning the Lottery with Continuous Sparsification","created":"2019-12-10","cited_by_count":100},{"id":"2202.02643","title":"The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training","created":"2022-02-05","cited_by_count":85},{"id":"2006.07990","title":"Optimal Lottery Tickets via SubsetSum: Logarithmic Over-Parameterization is Sufficient","created":"2020-06-14","cited_by_count":81},{"id":"1909.05122","title":"Implicit Regularization for Optimal Sparse Recovery","created":"2019-09-11","cited_by_count":80},{"id":"1705.10412","title":"Gradient Descent Can Take Exponential Time to Escape Saddle Points","created":"2017-05-29","cited_by_count":74},{"id":"2006.12156","title":"Logarithmic Pruning is All You Need","created":"2020-06-22","cited_by_count":71},{"id":"1904.01517","title":"Convergence rates for the stochastic gradient descent method for non-convex objective functions","created":"2019-04-02","cited_by_count":66},{"id":"2109.10317","title":"Introduction to Neural Network Verification","created":"2021-09-21","cited_by_count":63},{"id":"2106.12379","title":"AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks","created":"2021-06-23","cited_by_count":59},{"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":"2105.01650","title":"Stochastic gradient descent with noise of machine learning type. Part I: Discrete time analysis","created":"2021-05-04","cited_by_count":39},{"id":"2207.04036","title":"Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent","created":"2022-07-08","cited_by_count":39},{"id":"2210.03044","title":"Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask?","created":"2022-10-06","cited_by_count":38},{"id":"2305.02299","title":"Dynamic Sparse Training with Structured Sparsity","created":"2023-05-03","cited_by_count":38},{"id":"2202.12002","title":"Rare Gems: Finding Lottery Tickets at Initialization","created":"2022-02-24","cited_by_count":34},{"id":"2210.13738","title":"Pruning's Effect on Generalization Through the Lens of Training and Regularization","created":"2022-10-25","cited_by_count":31},{"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":"2111.11146","title":"On the Existence of Universal Lottery Tickets","created":"2021-11-22","cited_by_count":30},{"id":"2102.09385","title":"Convergence of stochastic gradient descent schemes for Lojasiewicz-landscapes","created":"2021-02-16","cited_by_count":28},{"id":"1811.10331","title":"Hessian Riemannian gradient flows in convex programming","created":"2018-11-26","cited_by_count":26},{"id":"2210.02412","title":"Why Random Pruning Is All We Need to Start Sparse","created":"2022-10-05","cited_by_count":26},{"id":"1903.09367","title":"High-Dimensional Linear Regression via Implicit Regularization","created":"2019-03-22","cited_by_count":25},{"id":"2208.04425","title":"Controlled Sparsity via Constrained Optimization or: How I Learned to Stop Tuning Penalties and Love Constraints","created":"2022-08-08","cited_by_count":25},{"id":"2309.16932","title":"Symmetry Induces Structure and Constraint of Learning","created":"2023-09-29","cited_by_count":25},{"id":"2403.04861","title":"A Survey of Lottery Ticket Hypothesis","created":"2024-03-07","cited_by_count":24},{"id":"2205.02321","title":"Most Activation Functions Can Win the Lottery Without Excessive Depth","created":"2022-05-04","cited_by_count":21},{"id":"2206.04270","title":"A General Framework For Proving The Equivariant Strong Lottery Ticket Hypothesis","created":"2022-06-09","cited_by_count":19},{"id":"2403.08699","title":"Implicit Regularization of Gradient Flow on One-Layer Softmax Attention","created":"2024-03-13","cited_by_count":19},{"id":"2010.11354","title":"PHEW: Constructing Sparse Networks that Learn Fast and Generalize Well without Training Data","created":"2020-10-22","cited_by_count":17},{"id":"2205.02343","title":"Convolutional and Residual Networks Provably Contain Lottery Tickets","created":"2022-05-04","cited_by_count":16},{"id":"2402.19262","title":"Masks, Signs, And Learning Rate Rewinding","created":"2024-02-29","cited_by_count":15},{"id":"2111.11153","title":"Plant 'n' Seek: Can You Find the Winning Ticket?","created":"2021-11-22","cited_by_count":13},{"id":"1912.09802","title":"Taxonomy and Evaluation of Structured Compression of Convolutional Neural Networks","created":"2019-12-20","cited_by_count":12},{"id":"2106.06955","title":"Towards Understanding Iterative Magnitude Pruning: Why Lottery Tickets Win","created":"2021-06-13","cited_by_count":11},{"id":"2308.02060","title":"Accurate Neural Network Pruning Requires Rethinking Sparse Optimization","created":"2023-08-03","cited_by_count":10},{"id":"2301.12540","title":"Implicit Regularization for Group Sparsity","created":"2023-01-29","cited_by_count":8},{"id":"2009.08574","title":"Linear Convergence of Generalized Mirror Descent with Time-Dependent Mirrors","created":"2020-09-18","cited_by_count":5}],"next_cursor":null}