{"total":25,"rows":[{"id":"2208.06102","title":"Zeus: Understanding and Optimizing GPU Energy Consumption of DNN Training","created":"2022-08-12","cited_by_count":79,"area":null},{"id":"2106.07820","title":"On Large-Cohort Training for Federated Learning","created":"2021-06-15","cited_by_count":74,"area":null},{"id":"2410.21676","title":"How Does Critical Batch Size Scale in Pre-training?","created":"2024-10-29","cited_by_count":73,"area":null},{"id":"2109.14119","title":"Stochastic Training is Not Necessary for Generalization","created":"2021-09-29","cited_by_count":63,"area":null},{"id":"2505.13738","title":"Power Lines: Scaling Laws for Weight Decay and Batch Size in LLM Pre-training","created":"2025-05-19","cited_by_count":43,"area":null},{"id":"2310.03882","title":"Small batch deep reinforcement learning","created":"2023-10-05","cited_by_count":36,"area":null},{"id":"2110.00641","title":"Batch size-invariance for policy optimization","created":"2021-10-01","cited_by_count":35,"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":"2312.06902","title":"Reducing Energy Bloat in Large Model Training","created":"2023-12-12","cited_by_count":22,"area":null},{"id":"2107.07572","title":"Globally Convergent Multilevel Training of Deep Residual Networks","created":"2021-07-15","cited_by_count":11,"area":null},{"id":"2206.05985","title":"Modeling the Machine Learning Multiverse","created":"2022-06-13","cited_by_count":11,"area":null},{"id":"2106.02679","title":"Layered gradient accumulation and modular pipeline parallelism: fast and efficient training of large language models","created":"2021-06-04","cited_by_count":6,"area":null},{"id":"2402.18824","title":"Batch size invariant Adam","created":"2024-02-29","cited_by_count":5,"area":null},{"id":"2207.09078","title":"ILASR: Privacy-Preserving Incremental Learning for Automatic Speech Recognition at Production Scale","created":"2022-07-19","cited_by_count":4,"area":null},{"id":"2602.09492","title":"Beware of the Batch Size: Hyperparameter Bias in Evaluating LoRA","created":"2026-02-10","cited_by_count":4,"area":null},{"id":"2407.15738","title":"Parallel Split Learning with Global Sampling","created":"2024-07-22","cited_by_count":3,"area":null},{"id":"2108.09507","title":"Shift-Curvature, SGD, and Generalization","created":"2021-08-21","cited_by_count":2,"area":null},{"id":"2203.06638","title":"Scaling the Wild: Decentralizing Hogwild!-style Shared-memory SGD","created":"2022-03-13","cited_by_count":1,"area":null},{"id":"2607.27731","title":"Towards joint scaling laws with optimal batch size schedules","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2112.07110","title":"Non-Asymptotic Analysis of Online Multiplicative Stochastic Gradient Descent","created":"2021-12-14","cited_by_count":0,"area":null},{"id":"2209.06469","title":"Learning Deep Optimal Embeddings with Sinkhorn Divergences","created":"2022-09-14","cited_by_count":0,"area":null},{"id":"2507.21749","title":"Improving Neural Network Training using Dynamic Learning Rate Schedule for PINNs and Image Classification","created":"2025-07-29","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":"2603.18112","title":"Tula: Optimizing Time, Cost, and Generalization in Distributed Large-Batch Training","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2605.18609","title":"Perfect Parallelization in Mini-Batch SGD with Classical Momentum Acceleration","created":"2026-05-18","cited_by_count":0,"area":null}],"next_cursor":null}