{"total":100,"rows":[{"id":"2312.04564","title":"EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingS","created":"2023-12-07","cited_by_count":196,"area":null},{"id":"2102.06790","title":"A Unified Lottery Ticket Hypothesis for Graph Neural Networks","created":"2021-02-12","cited_by_count":118,"area":null},{"id":"2102.02887","title":"Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training","created":"2021-02-04","cited_by_count":110,"area":null},{"id":"2106.10404","title":"Sparse Training via Boosting Pruning Plasticity with Neuroregeneration","created":"2021-06-19","cited_by_count":84,"area":null},{"id":"2105.12002","title":"Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization","created":"2021-05-25","cited_by_count":56,"area":null},{"id":"2104.11832","title":"Playing Lottery Tickets with Vision and Language","created":"2021-04-23","cited_by_count":45,"area":null},{"id":"2301.10884","title":"Break It Down: Evidence for Structural Compositionality in Neural Networks","created":"2023-01-26","cited_by_count":44,"area":null},{"id":"2306.03805","title":"The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter","created":"2023-06-06","cited_by_count":42,"area":null},{"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,"area":null},{"id":"2202.12002","title":"Rare Gems: Finding Lottery Tickets at Initialization","created":"2022-02-24","cited_by_count":34,"area":null},{"id":"2106.00134","title":"GANs Can Play Lottery Tickets Too","created":"2021-05-31","cited_by_count":32,"area":null},{"id":"2111.05685","title":"Efficient Neural Network Training via Forward and Backward Propagation Sparsification","created":"2021-11-10","cited_by_count":30,"area":null},{"id":"2111.11146","title":"On the Existence of Universal Lottery Tickets","created":"2021-11-22","cited_by_count":30,"area":null},{"id":"2304.02840","title":"NTK-SAP: Improving neural network pruning by aligning training dynamics","created":"2023-04-06","cited_by_count":30,"area":null},{"id":"2110.14068","title":"Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks","created":"2021-10-26","cited_by_count":29,"area":null},{"id":"2303.02141","title":"Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!","created":"2023-03-03","cited_by_count":27,"area":null},{"id":"2206.12755","title":"Training Your Sparse Neural Network Better with Any Mask","created":"2022-06-26","cited_by_count":26,"area":null},{"id":"2210.02412","title":"Why Random Pruning Is All We Need to Start Sparse","created":"2022-10-05","cited_by_count":26,"area":null},{"id":"2103.00397","title":"Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective","created":"2021-02-28","cited_by_count":25,"area":null},{"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,"area":null},{"id":"2403.04861","title":"A Survey of Lottery Ticket Hypothesis","created":"2024-03-07","cited_by_count":24,"area":null},{"id":"2305.02190","title":"Rethinking Graph Lottery Tickets: Graph Sparsity Matters","created":"2023-05-03","cited_by_count":23,"area":null},{"id":"2205.02321","title":"Most Activation Functions Can Win the Lottery Without Excessive Depth","created":"2022-05-04","cited_by_count":21,"area":null},{"id":"2301.09254","title":"Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference","created":"2023-01-23","cited_by_count":20,"area":null},{"id":"2108.08532","title":"An Information Theory-inspired Strategy for Automatic Network Pruning","created":"2021-08-19","cited_by_count":17,"area":null},{"id":"2205.02343","title":"Convolutional and Residual Networks Provably Contain Lottery Tickets","created":"2022-05-04","cited_by_count":16,"area":null},{"id":"2401.15347","title":"A Comprehensive Survey of Compression Algorithms for Language Models","created":"2024-01-27","cited_by_count":15,"area":null},{"id":"2107.02306","title":"Connectivity Matters: Neural Network Pruning Through the Lens of Effective Sparsity","created":"2021-07-05","cited_by_count":14,"area":null},{"id":"2407.03779","title":"Sheaf Discovery with Joint Computation Graph Pruning and Flexible Granularity","created":"2024-07-04","cited_by_count":14,"area":null},{"id":"2408.09966","title":"Mask in the Mirror: Implicit Sparsification","created":"2024-08-19","cited_by_count":14,"area":null},{"id":"2502.02496","title":"Deep Weight Factorization: Sparse Learning Through the Lens of Artificial Symmetries","created":"2025-02-04","cited_by_count":14,"area":null},{"id":"2111.11153","title":"Plant 'n' Seek: Can You Find the Winning Ticket?","created":"2021-11-22","cited_by_count":13,"area":null},{"id":"2209.14624","title":"Is Complexity Required for Neural Network Pruning? A Case Study on Global Magnitude Pruning","created":"2022-09-29","cited_by_count":13,"area":null},{"id":"2406.15955","title":"Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects","created":"2024-06-22","cited_by_count":13,"area":null},{"id":"2501.13492","title":"Quantized Spike-driven Transformer","created":"2025-01-23","cited_by_count":13,"area":null},{"id":"2111.00843","title":"How I Learned to Stop Worrying and Love Retraining","created":"2021-11-01","cited_by_count":12,"area":null},{"id":"2302.13019","title":"A Unified Framework for Soft Threshold Pruning","created":"2023-02-25","cited_by_count":12,"area":null},{"id":"2305.11203","title":"PDP: Parameter-free Differentiable Pruning is All You Need","created":"2023-05-18","cited_by_count":12,"area":null},{"id":"2311.04354","title":"Uncovering Intermediate Variables in Transformers using Circuit Probing","created":"2023-11-07","cited_by_count":12,"area":null},{"id":"2105.03343","title":"Adapting by Pruning: A Case Study on BERT","created":"2021-05-07","cited_by_count":11,"area":null},{"id":"2106.06955","title":"Towards Understanding Iterative Magnitude Pruning: Why Lottery Tickets Win","created":"2021-06-13","cited_by_count":11,"area":null},{"id":"2410.01434","title":"Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models","created":"2024-10-02","cited_by_count":11,"area":null},{"id":"2104.08700","title":"Lottery Jackpots Exist in Pre-trained Models","created":"2021-04-18","cited_by_count":10,"area":null},{"id":"2307.08483","title":"Differentiable Transportation Pruning","created":"2023-07-17","cited_by_count":10,"area":null},{"id":"2308.02060","title":"Accurate Neural Network Pruning Requires Rethinking Sparse Optimization","created":"2023-08-03","cited_by_count":10,"area":null},{"id":"2205.07320","title":"Analyzing Lottery Ticket Hypothesis from PAC-Bayesian Theory Perspective","created":"2022-05-15","cited_by_count":9,"area":null},{"id":"2308.07163","title":"HyperSparse Neural Networks: Shifting Exploration to Exploitation through Adaptive Regularization","created":"2023-08-14","cited_by_count":9,"area":null},{"id":"2309.00244","title":"NeuroSurgeon: A Toolkit for Subnetwork Analysis","created":"2023-09-01","cited_by_count":9,"area":null},{"id":"2503.06901","title":"PRO-VPT: Distribution-Adaptive Visual Prompt Tuning via Prompt Relocation","created":"2025-03-10","cited_by_count":9,"area":null},{"id":"2205.14107","title":"Spartan: Differentiable Sparsity via Regularized Transportation","created":"2022-05-27","cited_by_count":8,"area":null},{"id":"2212.02770","title":"CSQ: Growing Mixed-Precision Quantization Scheme with Bi-level Continuous Sparsification","created":"2022-12-06","cited_by_count":8,"area":null},{"id":"2302.14670","title":"Balanced Training for Sparse GANs","created":"2023-02-28","cited_by_count":8,"area":null},{"id":"2204.02965","title":"LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification","created":"2022-04-06","cited_by_count":7,"area":null},{"id":"2402.02855","title":"Dynamic Sparse Learning: A Novel Paradigm for Efficient Recommendation","created":"2024-02-05","cited_by_count":7,"area":null},{"id":"2310.10899","title":"Instilling Inductive Biases with Subnetworks","created":"2023-10-17","cited_by_count":6,"area":null},{"id":"2407.18119","title":"Tracking linguistic information in transformer-based sentence embeddings through targeted sparsification","created":"2024-07-25","cited_by_count":6,"area":null},{"id":"2602.00693","title":"Topology and Geometry of the Learning Space of ReLU Networks: Connectivity and Singularities","created":"2026-01-31","cited_by_count":6,"area":null},{"id":"2101.03255","title":"Spending Your Winning Lottery Better After Drawing It","created":"2021-01-08","cited_by_count":5,"area":null},{"id":"2201.12826","title":"OptG: Optimizing Gradient-driven Criteria in Network Sparsity","created":"2022-01-30","cited_by_count":5,"area":null},{"id":"2504.15471","title":"Bigram Subnetworks: Mapping to Next Tokens in Transformer Language Models","created":"2025-04-21","cited_by_count":5,"area":null},{"id":"2110.11150","title":"Lottery Tickets with Nonzero Biases","created":"2021-10-21","cited_by_count":4,"area":null},{"id":"2307.08771","title":"UPSCALE: Unconstrained Channel Pruning","created":"2023-07-17","cited_by_count":4,"area":null},{"id":"2311.12526","title":"Neural Network Pruning by Gradient Descent","created":"2023-11-21","cited_by_count":4,"area":null},{"id":"2105.12920","title":"Search Spaces for Neural Model Training","created":"2021-05-27","cited_by_count":3,"area":null},{"id":"2110.00684","title":"Learning Compact Representations of Neural Networks using DiscriminAtive Masking (DAM)","created":"2021-10-01","cited_by_count":3,"area":null},{"id":"2202.09284","title":"Amenable Sparse Network Investigator","created":"2022-02-18","cited_by_count":3,"area":null},{"id":"2306.07030","title":"Resource Efficient Neural Networks Using Hessian Based Pruning","created":"2023-06-12","cited_by_count":3,"area":null},{"id":"2310.13183","title":"Breaking through Deterministic Barriers: Randomized Pruning Mask Generation and Selection","created":"2023-10-19","cited_by_count":3,"area":null},{"id":"2509.23898","title":"Differentiable Sparsity via $D$-Gating: Simple and Versatile Structured Penalization","created":"2025-09-28","cited_by_count":3,"area":null},{"id":"2110.11804","title":"Probabilistic fine-tuning of pruning masks and PAC-Bayes self-bounded learning","created":"2021-10-22","cited_by_count":2,"area":null},{"id":"2202.05226","title":"Deadwooding: Robust Global Pruning for Deep Neural Networks","created":"2022-02-10","cited_by_count":2,"area":null},{"id":"2304.06941","title":"AUTOSPARSE: Towards Automated Sparse Training of Deep Neural Networks","created":"2023-04-14","cited_by_count":2,"area":null},{"id":"2405.06038","title":"From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2507.22349","title":"MSQ: Memory-Efficient Bit Sparsification Quantization","created":"2025-07-30","cited_by_count":2,"area":null},{"id":"2601.05770","title":"Weights to Code: Extracting Interpretable Algorithms from the Discrete Transformer","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2103.15692","title":"Self-Constructing Neural Networks Through Random Mutation","created":"2021-03-29","cited_by_count":1,"area":null},{"id":"2203.13802","title":"Playing Lottery Tickets in Style Transfer Models","created":"2022-03-25","cited_by_count":1,"area":null},{"id":"2303.06815","title":"On Model Compression for Neural Networks: Framework, Algorithm, and Convergence Guarantee","created":"2023-03-13","cited_by_count":1,"area":null},{"id":"2307.04365","title":"One-Shot Pruning for Fast-adapting Pre-trained Models on Devices","created":"2023-07-10","cited_by_count":1,"area":null},{"id":"2403.04805","title":"Pruning neural network models for gene regulatory dynamics using data and domain knowledge","created":"2024-03-05","cited_by_count":1,"area":null},{"id":"2110.15829","title":"Holistic Deep Learning","created":"2021-10-29","cited_by_count":0,"area":null},{"id":"2206.08175","title":"Not All Lotteries Are Made Equal","created":"2022-06-16","cited_by_count":0,"area":null},{"id":"2209.06932","title":"Optimizing Connectivity through Network Gradients for Restricted Boltzmann Machines","created":"2022-09-14","cited_by_count":0,"area":null},{"id":"2301.11560","title":"Voting from Nearest Tasks: Meta-Vote Pruning of Pre-trained Models for Downstream Tasks","created":"2023-01-27","cited_by_count":0,"area":null},{"id":"2307.07389","title":"Learning Sparse Neural Networks with Identity Layers","created":"2023-07-14","cited_by_count":0,"area":null},{"id":"2312.03889","title":"A Masked Pruning Approach for Dimensionality Reduction in Communication-Efficient Federated Learning Systems","created":"2023-12-06","cited_by_count":0,"area":null},{"id":"2402.10339","title":"What to Do When Your Discrete Optimization Is the Size of a Neural Network?","created":"2024-02-15","cited_by_count":0,"area":null},{"id":"2402.17902","title":"SequentialAttention++ for Block Sparsification: Differentiable Pruning Meets Combinatorial Optimization","created":"2024-02-27","cited_by_count":0,"area":null},{"id":"2410.07046","title":"S2HPruner: Soft-to-Hard Distillation Bridges the Discretization Gap in Pruning","created":"2024-10-09","cited_by_count":0,"area":null},{"id":"2410.24187","title":"Chasing Better Deep Image Priors between Over- and Under-parameterization","created":"2024-10-31","cited_by_count":0,"area":null},{"id":"2501.11135","title":"Playing the Lottery With Concave Regularizers for Sparse Trainable Neural Networks","created":"2025-01-19","cited_by_count":0,"area":null},{"id":"2502.07189","title":"Exploring Vision Neural Network Pruning via Screening Methodology","created":"2025-02-11","cited_by_count":0,"area":null},{"id":"2504.05349","title":"Hyperflux: Pruning Reveals Importance","created":"2025-04-06","cited_by_count":0,"area":null},{"id":"2508.12891","title":"ONG: One-Shot NMF-based Gradient Masking for Efficient Model Sparsification","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2603.26595","title":"PQuantML: A Tool for End-to-End Hardware-aware Model Compression","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2605.17289","title":"LEAP: Learnable End-to-End Adaptive Pruning of Large Language Models","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2605.17704","title":"Toy Combinatorial Interpretability Models Reveal Lottery Tickets in Early Feature Space","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.25134","title":"Theoretical Analysis of Sparse Optimization with Reparameterization, Weight Decay, and Adaptive Learning Rate","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2606.18691","title":"Robust and Interpretable Adaptation of Equivariant Materials Foundation Models via Sparsity-promoting Fine-tuning","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2610.20588","title":"Your Transformer Is Secretly Elastic","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}