{"total":170,"rows":[{"id":"2312.12148","title":"Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment","created":"2023-12-19","cited_by_count":230,"area":null},{"id":"2308.06767","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","created":"2023-08-13","cited_by_count":202,"area":null},{"id":"2312.04564","title":"EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingS","created":"2023-12-07","cited_by_count":196,"area":null},{"id":"2102.04010","title":"Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch","created":"2021-02-08","cited_by_count":179,"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":"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,"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":"2210.04284","title":"SparseAdapter: An Easy Approach for Improving the Parameter-Efficiency of Adapters","created":"2022-10-09","cited_by_count":83,"area":null},{"id":"2106.02890","title":"Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?","created":"2021-06-05","cited_by_count":75,"area":null},{"id":"2206.10369","title":"The State of Sparse Training in Deep Reinforcement Learning","created":"2022-06-17","cited_by_count":61,"area":null},{"id":"2210.04092","title":"Advancing Model Pruning via Bi-level Optimization","created":"2022-10-08","cited_by_count":56,"area":null},{"id":"2110.14678","title":"Meta-Learning Sparse Implicit Neural Representations","created":"2021-10-27","cited_by_count":48,"area":null},{"id":"2106.03225","title":"Efficient Lottery Ticket Finding: Less Data is More","created":"2021-06-06","cited_by_count":44,"area":null},{"id":"2103.06460","title":"Recent Advances on Neural Network Pruning at Initialization","created":"2021-03-11","cited_by_count":41,"area":null},{"id":"2203.04466","title":"The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks","created":"2022-03-09","cited_by_count":41,"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":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2104.05641","title":"Generalization bounds via distillation","created":"2021-04-12","cited_by_count":34,"area":null},{"id":"2202.08132","title":"Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients","created":"2022-02-16","cited_by_count":34,"area":null},{"id":"2202.12002","title":"Rare Gems: Finding Lottery Tickets at Initialization","created":"2022-02-24","cited_by_count":34,"area":null},{"id":"2303.03428","title":"Towards provably efficient quantum algorithms for large-scale machine-learning models","created":"2023-03-06","cited_by_count":32,"area":null},{"id":"2210.13738","title":"Pruning's Effect on Generalization Through the Lens of Training and Regularization","created":"2022-10-25","cited_by_count":31,"area":null},{"id":"2406.16797","title":"Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs","created":"2024-06-24","cited_by_count":31,"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":"2401.12200","title":"APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference","created":"2024-01-22","cited_by_count":29,"area":null},{"id":"2107.05802","title":"How many degrees of freedom do we need to train deep networks: a loss landscape perspective","created":"2021-07-13","cited_by_count":28,"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":"2206.08684","title":"Sparse Double Descent: Where Network Pruning Aggravates Overfitting","created":"2022-06-17","cited_by_count":26,"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":"2404.04612","title":"Spectral Graph Pruning Against Over-Squashing and Over-Smoothing","created":"2024-04-06","cited_by_count":24,"area":null},{"id":"2103.16547","title":"The Elastic Lottery Ticket Hypothesis","created":"2021-03-30","cited_by_count":23,"area":null},{"id":"2210.03858","title":"AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models","created":"2022-10-08","cited_by_count":23,"area":null},{"id":"2102.01670","title":"Keep the Gradients Flowing: Using Gradient Flow to Study Sparse Network Optimization","created":"2021-02-02","cited_by_count":22,"area":null},{"id":"2102.11068","title":"Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?","created":"2021-02-19","cited_by_count":22,"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":"2206.10451","title":"Winning the Lottery Ahead of Time: Efficient Early Network Pruning","created":"2022-06-21","cited_by_count":21,"area":null},{"id":"2208.14057","title":"Symmetric Pruning in Quantum Neural Networks","created":"2022-08-30","cited_by_count":21,"area":null},{"id":"2102.07804","title":"Scaling Up Exact Neural Network Compression by ReLU Stability","created":"2021-02-15","cited_by_count":19,"area":null},{"id":"2108.04214","title":"Neural Network Repair with Reachability Analysis","created":"2021-08-09","cited_by_count":19,"area":null},{"id":"2110.14856","title":"An Operator Theoretic View on Pruning Deep Neural Networks","created":"2021-10-28","cited_by_count":18,"area":null},{"id":"2111.00162","title":"You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownership","created":"2021-10-30","cited_by_count":18,"area":null},{"id":"2402.04744","title":"Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers","created":"2024-02-07","cited_by_count":18,"area":null},{"id":"2306.12230","title":"Fantastic Weights and How to Find Them: Where to Prune in Dynamic Sparse Training","created":"2023-06-21","cited_by_count":17,"area":null},{"id":"2312.14229","title":"Real-time Neural Network Inference on Extremely Weak Devices: Agile Offloading with Explainable AI","created":"2023-12-21","cited_by_count":17,"area":null},{"id":"2203.07808","title":"Interspace Pruning: Using Adaptive Filter Representations to Improve Training of Sparse CNNs","created":"2022-03-15","cited_by_count":16,"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":"2301.05219","title":"Why is the State of Neural Network Pruning so Confusing? On the Fairness, Comparison Setup, and Trainability in Network Pruning","created":"2023-01-12","cited_by_count":16,"area":null},{"id":"2405.15743","title":"Sparse maximal update parameterization: A holistic approach to sparse training dynamics","created":"2024-05-24","cited_by_count":16,"area":null},{"id":"2407.02068","title":"LPViT: Low-Power Semi-structured Pruning for Vision Transformers","created":"2024-07-02","cited_by_count":16,"area":null},{"id":"2205.11819","title":"Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free","created":"2022-05-24","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":"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":"2207.09455","title":"To update or not to update? Neurons at equilibrium in deep models","created":"2022-07-19","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":"2108.06277","title":"Towards Structured Dynamic Sparse Pre-Training of BERT","created":"2021-08-13","cited_by_count":12,"area":null},{"id":"2110.14583","title":"Deep learning via message passing algorithms based on belief propagation","created":"2021-10-27","cited_by_count":12,"area":null},{"id":"2205.08099","title":"Dimensionality Reduced Training by Pruning and Freezing Parts of a Deep Neural Network, a Survey","created":"2022-05-17","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":"2206.04743","title":"Strong Memory Lower Bounds for Learning Natural Models","created":"2022-06-09","cited_by_count":11,"area":null},{"id":"2209.07617","title":"Training Recipe for N:M Structured Sparsity with Decaying Pruning Mask","created":"2022-09-15","cited_by_count":11,"area":null},{"id":"2310.01225","title":"A path-norm toolkit for modern networks: consequences, promises and challenges","created":"2023-10-02","cited_by_count":10,"area":null},{"id":"2402.01242","title":"Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness","created":"2024-02-02","cited_by_count":10,"area":null},{"id":"2402.17210","title":"Purified and Unified Steganographic Network","created":"2024-02-27","cited_by_count":10,"area":null},{"id":"2406.01820","title":"Finding Lottery Tickets in Vision Models via Data-driven Spectral Foresight Pruning","created":"2024-06-03","cited_by_count":10,"area":null},{"id":"2102.07655","title":"Dense for the Price of Sparse: Improved Performance of Sparsely Initialized Networks via a Subspace Offset","created":"2021-02-12","cited_by_count":9,"area":null},{"id":"2108.00065","title":"Model Preserving Compression for Neural Networks","created":"2021-07-30","cited_by_count":9,"area":null},{"id":"2112.03406","title":"Equal Bits: Enforcing Equally Distributed Binary Network Weights","created":"2021-12-02","cited_by_count":9,"area":null},{"id":"2203.14328","title":"On the Neural Tangent Kernel Analysis of Randomly Pruned Neural Networks","created":"2022-03-27","cited_by_count":9,"area":null},{"id":"2212.01076","title":"Are Straight-Through gradients and Soft-Thresholding all you need for Sparse Training?","created":"2022-12-02","cited_by_count":9,"area":null},{"id":"2306.05857","title":"How Sparse Can We Prune A Deep Network: A Fundamental Limit Perspective","created":"2023-06-09","cited_by_count":9,"area":null},{"id":"2110.03210","title":"Universality of Winning Tickets: A Renormalization Group Perspective","created":"2021-10-07","cited_by_count":8,"area":null},{"id":"2208.12816","title":"Complexity-Driven CNN Compression for Resource-constrained Edge AI","created":"2022-08-26","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":"2309.06973","title":"DNNShifter: An Efficient DNN Pruning System for Edge Computing","created":"2023-09-13","cited_by_count":8,"area":null},{"id":"2402.01089","title":"No Free Prune: Information-Theoretic Barriers to Pruning at Initialization","created":"2024-02-02","cited_by_count":8,"area":null},{"id":"2412.11768","title":"No More Adam: Learning Rate Scaling at Initialization is All You Need","created":"2024-12-16","cited_by_count":8,"area":null},{"id":"2203.02549","title":"Structured Pruning is All You Need for Pruning CNNs at Initialization","created":"2022-03-04","cited_by_count":7,"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":"2307.04552","title":"SparseVSR: Lightweight and Noise Robust Visual Speech Recognition","created":"2023-07-10","cited_by_count":7,"area":null},{"id":"2310.04680","title":"The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning","created":"2023-10-07","cited_by_count":7,"area":null},{"id":"2403.02914","title":"DynST: Dynamic Sparse Training for Resource-Constrained Spatio-Temporal Forecasting","created":"2024-03-05","cited_by_count":7,"area":null},{"id":"2404.05579","title":"DRoP: Distributionally Robust Data Pruning","created":"2024-04-08","cited_by_count":7,"area":null},{"id":"2405.17420","title":"Survival of the Fittest Representation: A Case Study with Modular Addition","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2412.00143","title":"Is Oracle Pruning the True Oracle?","created":"2024-11-28","cited_by_count":7,"area":null},{"id":"2606.22019","title":"Channel Location Constrains the Auditability of Subliminal Learning","created":"2026-06-20","cited_by_count":7,"area":null},{"id":"2407.01320","title":"Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning","created":"2024-07-01","cited_by_count":6,"area":null},{"id":"2504.12801","title":"Sign-In to the Lottery: Reparameterizing Sparse Training From Scratch","created":"2025-04-17","cited_by_count":6,"area":null},{"id":"2106.04767","title":"Ex uno plures: Splitting One Model into an Ensemble of Subnetworks","created":"2021-06-09","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":"2301.11936","title":"Quantum Ridgelet Transform: Winning Lottery Ticket of Neural Networks with Quantum Computation","created":"2023-01-27","cited_by_count":5,"area":null},{"id":"2310.11611","title":"In defense of parameter sharing for model-compression","created":"2023-10-17","cited_by_count":5,"area":null},{"id":"2108.00259","title":"How much pre-training is enough to discover a good subnetwork?","created":"2021-07-31","cited_by_count":4,"area":null},{"id":"2212.08311","title":"Can We Find Strong Lottery Tickets in Generative Models?","created":"2022-12-16","cited_by_count":4,"area":null},{"id":"2308.13816","title":"Homological Convolutional Neural Networks","created":"2023-08-26","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":"2202.00834","title":"Nonlinear Initialization Methods for Low-Rank Neural Networks","created":"2022-02-02","cited_by_count":3,"area":null}],"next_cursor":"100"}