{"total":54,"rows":[{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315,"area":null},{"id":"2108.06098","title":"FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learning","created":"2021-08-13","cited_by_count":141,"area":null},{"id":"2312.06550","title":"LLM360: Towards Fully Transparent Open-Source LLMs","created":"2023-12-11","cited_by_count":104,"area":null},{"id":"2112.12371","title":"DENSE: Data-Free One-Shot Federated Learning","created":"2021-12-23","cited_by_count":100,"area":null},{"id":"2105.03361","title":"What Kinds of Functions do Deep Neural Networks Learn? Insights from Variational Spline Theory","created":"2021-05-07","cited_by_count":60,"area":null},{"id":"2205.13571","title":"Low-rank lottery tickets: finding efficient low-rank neural networks via matrix differential equations","created":"2022-05-26","cited_by_count":43,"area":null},{"id":"2110.10302","title":"Layer-wise Adaptive Model Aggregation for Scalable Federated Learning","created":"2021-10-19","cited_by_count":36,"area":null},{"id":"2111.14655","title":"FedHM: Efficient Federated Learning for Heterogeneous Models via Low-rank Factorization","created":"2021-11-29","cited_by_count":31,"area":null},{"id":"2408.11804","title":"Approaching Deep Learning through the Spectral Dynamics of Weights","created":"2024-08-21","cited_by_count":31,"area":null},{"id":"2206.01299","title":"Fine-tuning Language Models over Slow Networks using Activation Compression with Guarantees","created":"2022-06-02","cited_by_count":30,"area":null},{"id":"2209.13569","title":"Exploring Low Rank Training of Deep Neural Networks","created":"2022-09-27","cited_by_count":30,"area":null},{"id":"2305.02538","title":"Cuttlefish: Low-Rank Model Training without All the Tuning","created":"2023-05-04","cited_by_count":25,"area":null},{"id":"2301.09554","title":"Deep Learning Meets Sparse Regularization: A Signal Processing Perspective","created":"2023-01-23","cited_by_count":21,"area":null},{"id":"2305.16534","title":"Variation Spaces for Multi-Output Neural Networks: Insights on Multi-Task Learning and Network Compression","created":"2023-05-25","cited_by_count":18,"area":null},{"id":"2106.08895","title":"Masked Training of Neural Networks with Partial Gradients","created":"2021-06-16","cited_by_count":16,"area":null},{"id":"2301.09830","title":"Optimus-CC: Efficient Large NLP Model Training with 3D Parallelism Aware Communication Compression","created":"2023-01-24","cited_by_count":15,"area":null},{"id":"2403.06664","title":"Smart-Infinity: Fast Large Language Model Training using Near-Storage Processing on a Real System","created":"2024-03-11","cited_by_count":15,"area":null},{"id":"2110.03450","title":"Efficient and Private Federated Learning with Partially Trainable Networks","created":"2021-10-06","cited_by_count":13,"area":null},{"id":"2302.07937","title":"The Expressive Power of Tuning Only the Normalization Layers","created":"2023-02-15","cited_by_count":13,"area":null},{"id":"2306.01485","title":"Robust low-rank training via approximate orthonormal constraints","created":"2023-06-02","cited_by_count":13,"area":null},{"id":"2301.02654","title":"Does compressing activations help model parallel training?","created":"2023-01-06","cited_by_count":12,"area":null},{"id":"2305.19059","title":"Geometry-aware training of factorized layers in tensor Tucker format","created":"2023-05-30","cited_by_count":12,"area":null},{"id":"2506.01260","title":"Subspace Networks: Scaling Decentralized Training with Communication-Efficient Model Parallelism","created":"2025-06-02","cited_by_count":12,"area":null},{"id":"2112.02668","title":"On the Convergence of Shallow Neural Network Training with Randomly Masked Neurons","created":"2021-12-05","cited_by_count":11,"area":null},{"id":"2401.10341","title":"ELRT: Efficient Low-Rank Training for Compact Convolutional Neural Networks","created":"2024-01-18","cited_by_count":11,"area":null},{"id":"2402.03991","title":"Provable Emergence of Deep Neural Collapse and Low-Rank Bias in $L^2$-Regularized Nonlinear Networks","created":"2024-02-06","cited_by_count":11,"area":null},{"id":"2305.12201","title":"GraVAC: Adaptive Compression for Communication-Efficient Distributed DL Training","created":"2023-05-20","cited_by_count":10,"area":null},{"id":"2306.11250","title":"InRank: Incremental Low-Rank Learning","created":"2023-06-20","cited_by_count":10,"area":null},{"id":"2308.14929","title":"Maestro: Uncovering Low-Rank Structures via Trainable Decomposition","created":"2023-08-28","cited_by_count":8,"area":null},{"id":"2406.17887","title":"Federated Dynamical Low-Rank Training with Global Loss Convergence Guarantees","created":"2024-06-25","cited_by_count":7,"area":null},{"id":"2505.08022","title":"Dynamical Low-Rank Compression of Neural Networks with Robustness under Adversarial Attacks","created":"2025-05-12","cited_by_count":6,"area":null},{"id":"2602.12429","title":"Stabilizing Native Low-Rank LLM Pretraining","created":"2026-02-12","cited_by_count":6,"area":null},{"id":"2410.18720","title":"GeoLoRA: Geometric integration for parameter efficient fine-tuning","created":"2024-10-24","cited_by_count":5,"area":null},{"id":"2506.17475","title":"A geometric framework for momentum-based optimizers for low-rank training","created":"2025-06-20","cited_by_count":5,"area":null},{"id":"2406.03768","title":"Enhancing In-Context Learning Performance with just SVD-Based Weight Pruning: A Theoretical Perspective","created":"2024-06-06","cited_by_count":4,"area":null},{"id":"2202.00834","title":"Nonlinear Initialization Methods for Low-Rank Neural Networks","created":"2022-02-02","cited_by_count":3,"area":null},{"id":"2210.03069","title":"PathProx: A Proximal Gradient Algorithm for Weight Decay Regularized Deep Neural Networks","created":"2022-10-06","cited_by_count":2,"area":null},{"id":"2406.06564","title":"SwitchLoRA: Switched Low-Rank Adaptation Can Learn Full-Rank Information","created":"2024-06-03","cited_by_count":2,"area":null},{"id":"2410.17661","title":"PETAH: Parameter Efficient Task Adaptation for Hybrid Transformers in a resource-limited Context","created":"2024-10-23","cited_by_count":2,"area":null},{"id":"2602.02680","title":"FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2502.07739","title":"HRP: High-Rank Preheating for Superior LoRA Initialization","created":"2025-02-11","cited_by_count":1,"area":null},{"id":"2507.03828","title":"IMPACT: Importance-Aware Activation Space Reconstruction","created":"2025-07-04","cited_by_count":1,"area":null},{"id":"2507.09428","title":"On Information Geometry and Iterative Optimization in Model Compression: Operator Factorization","created":"2025-07-12","cited_by_count":1,"area":null},{"id":"2602.18248","title":"Neural-HSS: Hierarchical Semi-Separable Neural PDE Solver","created":"2026-02-20","cited_by_count":1,"area":null},{"id":"2606.05484","title":"Learned Subspace Compression for Communication-Efficient Pipeline Parallelism","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2403.10232","title":"Matrix Completion via Nonsmooth Regularization of Fully Connected Neural Networks","created":"2024-03-15","cited_by_count":0,"area":null},{"id":"2405.01067","title":"AB-Training: A Communication-Efficient Approach for Distributed Low-Rank Learning","created":"2024-05-02","cited_by_count":0,"area":null},{"id":"2406.08904","title":"AdaPTwin: Low-Cost Adaptive Compression of Product Twins in Transformers","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2506.00486","title":"It Takes a Good Model to Train a Good Model: Generalized Gaussian Priors for Optimized LLMs","created":"2025-05-31","cited_by_count":0,"area":null},{"id":"2602.14397","title":"LRD-MPC: Efficient MPC Inference through Low-rank Decomposition","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2604.11947","title":"ResBM: Residual Bottleneck Models for Low-Bandwidth Pipeline Parallelism","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2606.16384","title":"Mixtures of Subspaces for Bandwidth Efficient Context Parallel Training","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2609.14339","title":"Communication-Efficient LLM Adaptation over Decentralized GPU Meshes","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.21039","title":"Stiefel-AdamW: Geometry-Aware AdamW for Linear Factorization Blocks","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}