{"total":30,"rows":[{"id":"2106.09352","title":"Large Scale Private Learning via Low-rank Reparametrization","created":"2021-06-17","cited_by_count":88,"area":null},{"id":"2505.02222","title":"Practical Efficiency of Muon for Pretraining","created":"2025-05-04","cited_by_count":80,"area":null},{"id":"2312.00333","title":"Green Edge AI: A Contemporary Survey","created":"2023-12-01","cited_by_count":25,"area":null},{"id":"2405.14578","title":"Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling","created":"2024-05-23","cited_by_count":22,"area":null},{"id":"2108.10434","title":"Adaptive shot allocation for fast convergence in variational quantum algorithms","created":"2021-08-23","cited_by_count":12,"area":null},{"id":"2409.08770","title":"Increasing Both Batch Size and Learning Rate Accelerates Stochastic Gradient Descent","created":"2024-09-13","cited_by_count":11,"area":null},{"id":"2402.11215","title":"AdAdaGrad: Adaptive Batch Size Schemes for Adaptive Gradient Methods","created":"2024-02-17","cited_by_count":8,"area":null},{"id":"2102.06604","title":"Cockpit: A Practical Debugging Tool for the Training of Deep Neural Networks","created":"2021-02-12","cited_by_count":7,"area":null},{"id":"2111.07952","title":"Stochastic Gradient Line Bayesian Optimization for Efficient Noise-Robust Optimization of Parameterized Quantum Circuits","created":"2021-11-15","cited_by_count":7,"area":null},{"id":"2411.00999","title":"Normalization Layer Per-Example Gradients are Sufficient to Predict Gradient Noise Scale in Transformers","created":"2024-11-01","cited_by_count":7,"area":null},{"id":"2304.12950","title":"Shot Optimization in Quantum Machine Learning Architectures to Accelerate Training","created":"2023-04-21","cited_by_count":5,"area":null},{"id":"2406.13936","title":"Communication-Efficient Adaptive Batch Size Strategies for Distributed Local Gradient Methods","created":"2024-06-20","cited_by_count":4,"area":null},{"id":"2412.21124","title":"Adaptive Batch Size Schedules for Distributed Training of Language Models with Data and Model Parallelism","created":"2024-12-30","cited_by_count":4,"area":null},{"id":"2312.01898","title":"Unlocking optimal batch size schedules using continuous-time control and perturbation theory","created":"2023-12-04","cited_by_count":3,"area":null},{"id":"2507.07907","title":"A statistical physics framework for optimal learning","created":"2025-07-10","cited_by_count":3,"area":null},{"id":"2110.07029","title":"Adaptive Elastic Training for Sparse Deep Learning on Heterogeneous Multi-GPU Servers","created":"2021-10-13","cited_by_count":2,"area":null},{"id":"2311.08745","title":"Using Stochastic Gradient Descent to Smooth Nonconvex Functions: Analysis of Implicit Graduated Optimization","created":"2023-11-15","cited_by_count":2,"area":null},{"id":"2501.08883","title":"Increasing Batch Size Improves Convergence of Stochastic Gradient Descent with Momentum","created":"2025-01-15","cited_by_count":2,"area":null},{"id":"2407.15525","title":"Multiple Importance Sampling for Stochastic Gradient Estimation","created":"2024-07-22","cited_by_count":1,"area":null},{"id":"2409.09984","title":"Convergence of Sharpness-Aware Minimization Algorithms using Increasing Batch Size and Decaying Learning Rate","created":"2024-09-16","cited_by_count":1,"area":null},{"id":"2505.08198","title":"SIM-Shapley: A Stable and Computationally Efficient Approach to Shapley Value Approximation","created":"2025-05-13","cited_by_count":1,"area":null},{"id":"2508.03105","title":"Accelerating SGDM via Learning Rate and Batch Size Schedules: A Lyapunov-Based Analysis","created":"2025-08-05","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":"2111.07058","title":"Bolstering Stochastic Gradient Descent with Model Building","created":"2021-11-13","cited_by_count":0,"area":null},{"id":"2112.00174","title":"Adaptive Optimization with Examplewise Gradients","created":"2021-11-30","cited_by_count":0,"area":null},{"id":"2208.00815","title":"Dynamic Batch Adaptation","created":"2022-08-01","cited_by_count":0,"area":null},{"id":"2503.00815","title":"Evaluation of adaptive sampling methods in scenario generation for virtual safety impact assessment of pre-crash safety systems","created":"2025-03-02","cited_by_count":0,"area":null},{"id":"2509.16173","title":"DIVEBATCH: Accelerating Model Training Through Gradient-Diversity Aware Batch Size Adaptation","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2606.09734","title":"Adaptive directional gradients for parameterised quantum circuits","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2610.02355","title":"Why Does Adaptive Batching Help LLM Pretraining? A Perspective from Unbounded Variance","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}