{"total":18,"rows":[{"id":"2110.02861","title":"8-bit Optimizers via Block-wise Quantization","created":"2021-10-06","cited_by_count":403,"area":null},{"id":"2108.01624","title":"Large-Scale Differentially Private BERT","created":"2021-08-03","cited_by_count":118,"area":null},{"id":"2304.13960","title":"Noise Is Not the Main Factor Behind the Gap Between SGD and Adam on Transformers, but Sign Descent Might Be","created":"2023-04-27","cited_by_count":114,"area":null},{"id":"2211.09760","title":"VeLO: Training Versatile Learned Optimizers by Scaling Up","created":"2022-11-17","cited_by_count":57,"area":null},{"id":"2309.01507","title":"Memory Efficient Optimizers with 4-bit States","created":"2023-09-04","cited_by_count":54,"area":null},{"id":"2103.15060","title":"PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS","created":"2021-03-28","cited_by_count":52,"area":null},{"id":"2307.02047","title":"CAME: Confidence-guided Adaptive Memory Efficient Optimization","created":"2023-07-05","cited_by_count":36,"area":null},{"id":"2202.00980","title":"Robust Training of Neural Networks Using Scale Invariant Architectures","created":"2022-02-02","cited_by_count":29,"area":null},{"id":"2302.03764","title":"Sketchy: Memory-efficient Adaptive Regularization with Frequent Directions","created":"2023-02-07","cited_by_count":17,"area":null},{"id":"2106.06199","title":"LocoProp: Enhancing BackProp via Local Loss Optimization","created":"2021-06-11","cited_by_count":15,"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":"2310.11291","title":"An Automatic Learning Rate Schedule Algorithm for Achieving Faster Convergence and Steeper Descent","created":"2023-10-17","cited_by_count":9,"area":null},{"id":"2305.19982","title":"Adam Accumulation to Reduce Memory Footprints of both Activations and Gradients for Large-scale DNN Training","created":"2023-05-31","cited_by_count":5,"area":null},{"id":"2204.02360","title":"Scientometric Review of Artificial Intelligence for Operations & Maintenance of Wind Turbines: The Past, Present and Future","created":"2022-03-30","cited_by_count":4,"area":null},{"id":"2212.08321","title":"Investigation of Japanese PnG BERT language model in text-to-speech synthesis for pitch accent language","created":"2022-12-16","cited_by_count":2,"area":null},{"id":"2203.04464","title":"On the Evaluation of Answer-Agnostic Paragraph-level Multi-Question Generation","created":"2022-03-09","cited_by_count":1,"area":null},{"id":"2212.03720","title":"Pseudo-Riemannian Embedding Models for Multi-Relational Graph Representations","created":"2022-12-02","cited_by_count":0,"area":null},{"id":"2601.19739","title":"TokenSeek: Memory Efficient Fine Tuning via Instance-Aware Token Ditching","created":"2026-01-27","cited_by_count":0,"area":null}],"next_cursor":null}