{"total":78,"rows":[{"id":"2102.06171","title":"High-Performance Large-Scale Image Recognition Without Normalization","created":"2021-02-11","cited_by_count":360,"area":null},{"id":"2204.13650","title":"Unlocking High-Accuracy Differentially Private Image Classification through Scale","created":"2022-04-28","cited_by_count":224,"area":null},{"id":"2101.12176","title":"On the Origin of Implicit Regularization in Stochastic Gradient Descent","created":"2021-01-28","cited_by_count":184,"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":"2101.08692","title":"Characterizing signal propagation to close the performance gap in unnormalized ResNets","created":"2021-01-21","cited_by_count":88,"area":null},{"id":"2211.13609","title":"PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization","created":"2022-11-24","cited_by_count":76,"area":null},{"id":"2102.12470","title":"On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs)","created":"2021-02-24","cited_by_count":73,"area":null},{"id":"2310.04415","title":"Why Do We Need Weight Decay in Modern Deep Learning?","created":"2023-10-06","cited_by_count":72,"area":null},{"id":"2109.14119","title":"Stochastic Training is Not Necessary for Generalization","created":"2021-09-29","cited_by_count":63,"area":null},{"id":"2210.03403","title":"TAN Without a Burn: Scaling Laws of DP-SGD","created":"2022-10-07","cited_by_count":52,"area":null},{"id":"2107.01614","title":"Survey: Leakage and Privacy at Inference Time","created":"2021-07-04","cited_by_count":44,"area":null},{"id":"2202.02831","title":"Anticorrelated Noise Injection for Improved Generalization","created":"2022-02-06","cited_by_count":42,"area":null},{"id":"2205.02973","title":"Large Scale Transfer Learning for Differentially Private Image Classification","created":"2022-05-06","cited_by_count":41,"area":null},{"id":"2303.02749","title":"Revisiting the Noise Model of Stochastic Gradient Descent","created":"2023-03-05","cited_by_count":36,"area":null},{"id":"2105.13343","title":"Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error","created":"2021-05-27","cited_by_count":33,"area":null},{"id":"2509.14786","title":"Pre-training under infinite compute","created":"2025-09-18","cited_by_count":29,"area":null},{"id":"2206.07252","title":"Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions","created":"2022-06-15","cited_by_count":23,"area":null},{"id":"2301.08203","title":"An SDE for Modeling SAM: Theory and Insights","created":"2023-01-19","cited_by_count":22,"area":null},{"id":"2410.23922","title":"Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training","created":"2024-10-31","cited_by_count":22,"area":null},{"id":"2401.07187","title":"A Survey on Statistical Theory of Deep Learning: Approximation, Training Dynamics, and Generative Models","created":"2024-01-14","cited_by_count":20,"area":null},{"id":"2307.15196","title":"The Marginal Value of Momentum for Small Learning Rate SGD","created":"2023-07-27","cited_by_count":18,"area":null},{"id":"2205.00756","title":"VICE: Variational Interpretable Concept Embeddings","created":"2022-05-02","cited_by_count":15,"area":null},{"id":"2306.02913","title":"Decentralized SGD and Average-direction SAM are Asymptotically Equivalent","created":"2023-06-05","cited_by_count":15,"area":null},{"id":"2105.01281","title":"Citadel: Protecting Data Privacy and Model Confidentiality for Collaborative Learning with SGX","created":"2021-05-04","cited_by_count":14,"area":null},{"id":"2210.12583","title":"Active Learning of Discrete-Time Dynamics for Uncertainty-Aware Model Predictive Control","created":"2022-10-23","cited_by_count":13,"area":null},{"id":"2410.04642","title":"The Optimization Landscape of SGD Across the Feature Learning Strength","created":"2024-10-06","cited_by_count":13,"area":null},{"id":"2206.10011","title":"When Does Re-initialization Work?","created":"2022-06-20","cited_by_count":12,"area":null},{"id":"2212.10520","title":"Privacy-Preserving Domain Adaptation of Semantic Parsers","created":"2022-12-20","cited_by_count":12,"area":null},{"id":"2309.10688","title":"On the different regimes of Stochastic Gradient Descent","created":"2023-09-19","cited_by_count":12,"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":"2306.08590","title":"Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning","created":"2023-06-14","cited_by_count":10,"area":null},{"id":"2603.15958","title":"Deriving Hyperparameter Scaling Laws via Modern Optimization Theory","created":"2026-03-16","cited_by_count":10,"area":null},{"id":"2203.03304","title":"Regularising for invariance to data augmentation improves supervised learning","created":"2022-03-07","cited_by_count":9,"area":null},{"id":"2301.13703","title":"Dissecting the Effects of SGD Noise in Distinct Regimes of Deep Learning","created":"2023-01-31","cited_by_count":9,"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":"2410.05838","title":"Time Transfer: On Optimal Learning Rate and Batch Size In The Infinite Data Limit","created":"2024-10-08","cited_by_count":9,"area":null},{"id":"2411.19671","title":"On the Performance Analysis of Momentum Method: A Frequency Domain Perspective","created":"2024-11-29","cited_by_count":8,"area":null},{"id":"2303.17940","title":"Per-Example Gradient Regularization Improves Learning Signals from Noisy Data","created":"2023-03-31","cited_by_count":7,"area":null},{"id":"2307.02520","title":"Conditional independence testing under misspecified inductive biases","created":"2023-07-05","cited_by_count":7,"area":null},{"id":"2311.05589","title":"A Coefficient Makes SVRG Effective","created":"2023-11-09","cited_by_count":7,"area":null},{"id":"2404.12293","title":"Singular-limit analysis of gradient descent with noise injection","created":"2024-04-18","cited_by_count":7,"area":null},{"id":"2109.07752","title":"Deep Visual Navigation under Partial Observability","created":"2021-09-16","cited_by_count":6,"area":null},{"id":"2207.04922","title":"On uniform-in-time diffusion approximation for stochastic gradient descent","created":"2022-07-11","cited_by_count":6,"area":null},{"id":"2207.09682","title":"Quantized Training of Gradient Boosting Decision Trees","created":"2022-07-20","cited_by_count":6,"area":null},{"id":"2209.09162","title":"On the Theoretical Properties of Noise Correlation in Stochastic Optimization","created":"2022-09-19","cited_by_count":5,"area":null},{"id":"2310.14423","title":"A Quadratic Synchronization Rule for Distributed Deep Learning","created":"2023-10-22","cited_by_count":5,"area":null},{"id":"2207.09304","title":"A sharp uniform-in-time error estimate for Stochastic Gradient Langevin Dynamics","created":"2022-07-19","cited_by_count":4,"area":null},{"id":"2505.23489","title":"SGD as Free Energy Minimization: A Thermodynamic View on Neural Network Training","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2506.00181","title":"On the Interaction of Batch Noise, Adaptivity, and Compression, under $(L_0,L_1)$-Smoothness: An SDE Approach","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2510.26997","title":"Gradient Descent as Loss Landscape Navigation: a Normative Framework for Deriving Learning Rules","created":"2025-10-30","cited_by_count":4,"area":null},{"id":"2112.09741","title":"Envisioning Future Deep Learning Theories: Some Basic Concepts and Characteristics","created":"2021-12-17","cited_by_count":3,"area":null},{"id":"2303.06314","title":"Stabilizing and Improving Federated Learning with Non-IID Data and Client Dropout","created":"2023-03-11","cited_by_count":3,"area":null},{"id":"2404.10386","title":"I/O in Machine Learning Applications on HPC Systems: A 360-degree Survey","created":"2024-04-16","cited_by_count":3,"area":null},{"id":"2407.03641","title":"Learning Scalable Model Soup on a Single GPU: An Efficient Subspace Training Strategy","created":"2024-07-04","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":"2402.08344","title":"Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training","created":"2024-02-13","cited_by_count":2,"area":null},{"id":"2408.14677","title":"Can Optimization Trajectories Explain Multi-Task Transfer?","created":"2024-08-26","cited_by_count":2,"area":null},{"id":"2506.12903","title":"Variational Learning Finds Flatter Solutions at the Edge of Stability","created":"2025-06-15","cited_by_count":2,"area":null},{"id":"2510.04686","title":"How does the optimizer implicitly bias the model merging loss landscape?","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2603.14451","title":"How to find expressible and trainable parameterized quantum circuits?","created":"2026-03-15","cited_by_count":2,"area":null},{"id":"2606.00571","title":"On the Difficulty of Learning a Meta-network for Training Data Selection","created":"2026-05-30","cited_by_count":2,"area":null},{"id":"2409.18905","title":"Probabilistic Analysis of Least Squares, Orthogonal Projection, and QR Factorization Algorithms Subject to Gaussian Noise","created":"2024-09-27","cited_by_count":1,"area":null},{"id":"2512.06297","title":"Entropic Confinement and Mode Connectivity in Overparameterized Neural Networks","created":"2025-12-06","cited_by_count":1,"area":null},{"id":"2609.11716","title":"Why Does Post-Training Quantization Work?","created":"2026-09-10","cited_by_count":1,"area":null},{"id":"2111.12495","title":"Altering Backward Pass Gradients improves Convergence","created":"2021-11-24","cited_by_count":0,"area":null},{"id":"2205.08231","title":"Hyper-Learning for Gradient-Based Batch Size Adaptation","created":"2022-05-17","cited_by_count":0,"area":null},{"id":"2212.05603","title":"Error-aware Quantization through Noise Tempering","created":"2022-12-11","cited_by_count":0,"area":null},{"id":"2305.18864","title":"Stochastic Gradient Langevin Dynamics Based on Quantization with Increasing Resolution","created":"2023-05-30","cited_by_count":0,"area":null},{"id":"2405.01067","title":"AB-Training: A Communication-Efficient Approach for Distributed Low-Rank Learning","created":"2024-05-02","cited_by_count":0,"area":null},{"id":"2409.07326","title":"ART: Artifact Removal Transformer for Reconstructing Noise-Free Multichannel Electroencephalographic Signals","created":"2024-09-11","cited_by_count":0,"area":null},{"id":"2601.05034","title":"How to Set the Batch Size for Large-Scale Pre-training?","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2603.00127","title":"Segmenting Low-Contrast XCTs of Concrete: An Unsupervised Approach","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2605.06835","title":"On Privacy in Data-Space Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metrics","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.06412","title":"Nonreversible Gauge Fields in Fokker--Planck Dynamics: Supersymmetric Hamiltonians and Learned Finite Forces","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.12054","title":"Simplicity Suffices for Parameter Noise Injection in Stochastic Gradient Descent","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.27171","title":"Stochastic Gradient Optimization with Model-Assisted Sampling","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2609.32479","title":"Fast and Precise Learned Charged-Particle Trajectory Regression at the Large Hadron Collider","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.15965","title":"Scaling Repeated-Data Pretraining: Batch Size, Regularization, and GPU-Time Tradeoffs","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}