{"total":59,"rows":[{"id":"2103.00123","title":"GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training","created":"2021-02-27","cited_by_count":274,"area":null},{"id":"2203.02714","title":"Towards Efficient and Scalable Sharpness-Aware Minimization","created":"2022-03-05","cited_by_count":129,"area":null},{"id":"2106.11342","title":"Dive into Deep Learning","created":"2021-06-21","cited_by_count":111,"area":null},{"id":"2109.14119","title":"Stochastic Training is Not Necessary for Generalization","created":"2021-09-29","cited_by_count":63,"area":null},{"id":"2305.17212","title":"Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks","created":"2023-05-26","cited_by_count":53,"area":null},{"id":"2306.12517","title":"FFCV: Accelerating Training by Removing Data Bottlenecks","created":"2023-06-21","cited_by_count":49,"area":null},{"id":"2405.13698","title":"How to set AdamW's weight decay as you scale model and dataset size","created":"2024-05-22","cited_by_count":43,"area":null},{"id":"2202.07896","title":"Aryl: An Elastic Cluster Scheduler for Deep Learning","created":"2022-02-16","cited_by_count":27,"area":null},{"id":"2304.03589","title":"On Efficient Training of Large-Scale Deep Learning Models: A Literature Review","created":"2023-04-07","cited_by_count":26,"area":null},{"id":"2104.11125","title":"ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training","created":"2021-04-21","cited_by_count":22,"area":null},{"id":"2110.14807","title":"L2ight: Enabling On-Chip Learning for Optical Neural Networks via Efficient in-situ Subspace Optimization","created":"2021-10-27","cited_by_count":21,"area":null},{"id":"2103.07013","title":"Large Batch Simulation for Deep Reinforcement Learning","created":"2021-03-12","cited_by_count":19,"area":null},{"id":"2105.14500","title":"Tesseract: Parallelize the Tensor Parallelism Efficiently","created":"2021-05-30","cited_by_count":19,"area":null},{"id":"2107.00961","title":"ResIST: Layer-Wise Decomposition of ResNets for Distributed Training","created":"2021-07-02","cited_by_count":18,"area":null},{"id":"2110.04478","title":"Themis: A Network Bandwidth-Aware Collective Scheduling Policy for Distributed Training of DL Models","created":"2021-10-09","cited_by_count":16,"area":null},{"id":"2202.11921","title":"Auto-scaling Vision Transformers without Training","created":"2022-02-24","cited_by_count":15,"area":null},{"id":"2104.03042","title":"On-device Federated Learning with Flower","created":"2021-04-07","cited_by_count":13,"area":null},{"id":"2106.00221","title":"Concurrent Adversarial Learning for Large-Batch Training","created":"2021-06-01","cited_by_count":11,"area":null},{"id":"2401.02643","title":"Training and Serving System of Foundation Models: A Comprehensive Survey","created":"2024-01-05","cited_by_count":11,"area":null},{"id":"2102.06025","title":"Large-Scale Training System for 100-Million Classification at Alibaba","created":"2021-02-09","cited_by_count":10,"area":null},{"id":"2102.07511","title":"GradPIM: A Practical Processing-in-DRAM Architecture for Gradient Descent","created":"2021-02-15","cited_by_count":10,"area":null},{"id":"2111.00856","title":"Large-Scale Deep Learning Optimizations: A Comprehensive Survey","created":"2021-11-01","cited_by_count":10,"area":null},{"id":"2307.15034","title":"Guaranteed Approximation Bounds for Mixed-Precision Neural Operators","created":"2023-07-27","cited_by_count":9,"area":null},{"id":"2401.16645","title":"Speeding up and reducing memory usage for scientific machine learning via mixed precision","created":"2024-01-30","cited_by_count":8,"area":null},{"id":"2206.15143","title":"Scalable K-FAC Training for Deep Neural Networks with Distributed Preconditioning","created":"2022-06-30","cited_by_count":7,"area":null},{"id":"2306.08881","title":"Evaluation and Optimization of Gradient Compression for Distributed Deep Learning","created":"2023-06-15","cited_by_count":7,"area":null},{"id":"2301.00230","title":"Disjoint Masking with Joint Distillation for Efficient Masked Image Modeling","created":"2022-12-31","cited_by_count":6,"area":null},{"id":"2407.01378","title":"Beyond Throughput and Compression Ratios: Towards High End-to-end Utility of Gradient Compression","created":"2024-07-01","cited_by_count":6,"area":null},{"id":"2107.06533","title":"Accelerating Distributed K-FAC with Smart Parallelism of Computing and Communication Tasks","created":"2021-07-14","cited_by_count":5,"area":null},{"id":"2204.06787","title":"Sign Bit is Enough: A Learning Synchronization Framework for Multi-hop All-reduce with Ultimate Compression","created":"2022-04-14","cited_by_count":5,"area":null},{"id":"2309.14053","title":"Revisiting LARS for Large Batch Training Generalization of Neural Networks","created":"2023-09-25","cited_by_count":5,"area":null},{"id":"2101.11748","title":"Rethinking Floating Point Overheads for Mixed Precision DNN Accelerators","created":"2021-01-27","cited_by_count":4,"area":null},{"id":"2110.10548","title":"Synthesizing Optimal Parallelism Placement and Reduction Strategies on Hierarchical Systems for Deep Learning","created":"2021-10-20","cited_by_count":4,"area":null},{"id":"2210.11078","title":"Large-batch Optimization for Dense Visual Predictions","created":"2022-10-20","cited_by_count":4,"area":null},{"id":"2110.15362","title":"BitTrain: Sparse Bitmap Compression for Memory-Efficient Training on the Edge","created":"2021-10-29","cited_by_count":3,"area":null},{"id":"2302.12445","title":"DeAR: Accelerating Distributed Deep Learning with Fine-Grained All-Reduce Pipelining","created":"2023-02-24","cited_by_count":3,"area":null},{"id":"2510.27153","title":"Exploring Landscapes for Better Minima along Valleys","created":"2025-10-31","cited_by_count":3,"area":null},{"id":"2104.09075","title":"An Oracle for Guiding Large-Scale Model/Hybrid Parallel Training of Convolutional Neural Networks","created":"2021-04-19","cited_by_count":2,"area":null},{"id":"2109.06440","title":"Complexity-aware Adaptive Training and Inference for Edge-Cloud Distributed AI Systems","created":"2021-09-14","cited_by_count":2,"area":null},{"id":"2110.11199","title":"Asynchronous Decentralized Distributed Training of Acoustic Models","created":"2021-10-21","cited_by_count":2,"area":null},{"id":"2206.03661","title":"One Hyper-Initializer for All Network Architectures in Medical Image Analysis","created":"2022-06-08","cited_by_count":2,"area":null},{"id":"2211.08544","title":"Exploiting the Partly Scratch-off Lottery Ticket for Quantization-Aware Training","created":"2022-11-12","cited_by_count":2,"area":null},{"id":"2509.07252","title":"GCond: Gradient Conflict Resolution via Accumulation-based Stabilization for Large-Scale Multi-Task Learning","created":"2025-09-08","cited_by_count":2,"area":null},{"id":"2103.15940","title":"Representation range needs for 16-bit neural network training","created":"2021-03-29","cited_by_count":1,"area":null},{"id":"2105.08120","title":"Itsy Bitsy SpiderNet: Fully Connected Residual Network for Fraud Detection","created":"2021-05-17","cited_by_count":1,"area":null},{"id":"2110.09132","title":"EmbRace: Accelerating Sparse Communication for Distributed Training of NLP Neural Networks","created":"2021-10-18","cited_by_count":1,"area":null},{"id":"2205.07260","title":"Guidelines for the Regularization of Gammas in Batch Normalization for Deep Residual Networks","created":"2022-05-15","cited_by_count":1,"area":null},{"id":"2207.11912","title":"Dive into Big Model Training","created":"2022-07-25","cited_by_count":1,"area":null},{"id":"2208.06825","title":"Teacher Guided Training: An Efficient Framework for Knowledge Transfer","created":"2022-08-14","cited_by_count":1,"area":null},{"id":"2301.06193","title":"RedBit: An End-to-End Flexible Framework for Evaluating the Accuracy of Quantized CNNs","created":"2023-01-15","cited_by_count":1,"area":null},{"id":"2508.03760","title":"FlashCommunication V2: Bit Splitting and Spike Reserving for Any Bit Communication","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2308.15164","title":"ABS-SGD: A Delayed Synchronous Stochastic Gradient Descent Algorithm with Adaptive Batch Size for Heterogeneous GPU Clusters","created":"2023-08-29","cited_by_count":0,"area":null},{"id":"2401.02736","title":"On the numerical reliability of nonsmooth autodiff: a MaxPool case study","created":"2024-01-05","cited_by_count":0,"area":null},{"id":"2407.19721","title":"Rina: Enhancing Ring-AllReduce with In-network Aggregation in Distributed Model Training","created":"2024-07-29","cited_by_count":0,"area":null},{"id":"2503.05324","title":"Routing for Large ML Models","created":"2025-03-07","cited_by_count":0,"area":null},{"id":"2503.15758","title":"ATTENTION2D: Communication Efficient Distributed Self-Attention Mechanism","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2509.10537","title":"On Using Large-Batches in Federated Learning","created":"2025-09-05","cited_by_count":0,"area":null},{"id":"2510.23498","title":"Mixed Precision Training of Neural ODEs","created":"2025-10-27","cited_by_count":0,"area":null},{"id":"2605.00539","title":"AGoQ: Activation and Gradient Quantization for Memory-Efficient Distributed Training of LLMs","created":"2026-05-01","cited_by_count":0,"area":null}],"next_cursor":null}