{"total":16,"rows":[{"id":"2203.02714","title":"Towards Efficient and Scalable Sharpness-Aware Minimization","created":"2022-03-05","cited_by_count":129,"area":null},{"id":"2102.06356","title":"A Large Batch Optimizer Reality Check: Traditional, Generic Optimizers Suffice Across Batch Sizes","created":"2021-02-12","cited_by_count":20,"area":null},{"id":"2105.14500","title":"Tesseract: Parallelize the Tensor Parallelism Efficiently","created":"2021-05-30","cited_by_count":19,"area":null},{"id":"2106.00221","title":"Concurrent Adversarial Learning for Large-Batch Training","created":"2021-06-01","cited_by_count":11,"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":"2202.08679","title":"Where Is My Training Bottleneck? Hidden Trade-Offs in Deep Learning Preprocessing Pipelines","created":"2022-02-17","cited_by_count":10,"area":null},{"id":"2112.15131","title":"Resource-Efficient Deep Learning: A Survey on Model-, Arithmetic-, and Implementation-Level Techniques","created":"2021-12-30","cited_by_count":9,"area":null},{"id":"2106.03640","title":"Making EfficientNet More Efficient: Exploring Batch-Independent Normalization, Group Convolutions and Reduced Resolution Training","created":"2021-06-07","cited_by_count":6,"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":"2212.03965","title":"CODEBench: A Neural Architecture and Hardware Accelerator Co-Design Framework","created":"2022-12-07","cited_by_count":5,"area":null},{"id":"2210.11078","title":"Large-batch Optimization for Dense Visual Predictions","created":"2022-10-20","cited_by_count":4,"area":null},{"id":"2312.06126","title":"Spreeze: High-Throughput Parallel Reinforcement Learning Framework","created":"2023-12-11","cited_by_count":2,"area":null},{"id":"2602.11852","title":"Prototype Transformer: Towards Language Model Architectures Interpretable by Design","created":"2026-02-12","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":"2208.02808","title":"Leveraging the HW/SW Optimizations and Ecosystems that Drive the AI Revolution","created":"2022-08-04","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}],"next_cursor":null}