{"total":145,"rows":[{"id":"2201.02177","title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","created":"2022-01-06","cited_by_count":629,"area":null},{"id":"2302.06675","title":"Symbolic Discovery of Optimization Algorithms","created":"2023-02-13","cited_by_count":434,"area":null},{"id":"2202.08906","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","created":"2022-02-17","cited_by_count":399,"area":"moe"},{"id":"2404.09591","title":"3D Gaussian Splatting as Markov Chain Monte Carlo","created":"2024-04-15","cited_by_count":217,"area":null},{"id":"2303.03329","title":"End-to-End Speech Recognition: A Survey","created":"2023-03-03","cited_by_count":129,"area":null},{"id":"2402.01109","title":"Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack","created":"2024-02-02","cited_by_count":115,"area":"alignment"},{"id":"2102.11972","title":"Do Transformer Modifications Transfer Across Implementations and Applications?","created":"2021-02-23","cited_by_count":87,"area":null},{"id":"2112.03459","title":"A Novel Convergence Analysis for Algorithms of the Adam Family","created":"2021-12-07","cited_by_count":50,"area":null},{"id":"2107.01614","title":"Survey: Leakage and Privacy at Inference Time","created":"2021-07-04","cited_by_count":44,"area":null},{"id":"2306.13812","title":"Maintaining Plasticity in Deep Continual Learning","created":"2023-06-23","cited_by_count":43,"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":"2104.15092","title":"Faster Meta Update Strategy for Noise-Robust Deep Learning","created":"2021-04-30","cited_by_count":38,"area":null},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2106.07830","title":"On the Convergence and Calibration of Deep Learning with Differential Privacy","created":"2021-06-15","cited_by_count":36,"area":null},{"id":"2105.10304","title":"Exploring Misclassifications of Robust Neural Networks to Enhance Adversarial Attacks","created":"2021-05-21","cited_by_count":33,"area":null},{"id":"2410.11582","title":"On-the-fly Modulation for Balanced Multimodal Learning","created":"2024-10-15","cited_by_count":32,"area":null},{"id":"2110.15456","title":"FAST: DNN Training Under Variable Precision Block Floating Point with Stochastic Rounding","created":"2021-10-28","cited_by_count":31,"area":null},{"id":"2103.17182","title":"Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization","created":"2021-03-31","cited_by_count":28,"area":null},{"id":"2309.16314","title":"A Primer on Bayesian Neural Networks: Review and Debates","created":"2023-09-28","cited_by_count":27,"area":null},{"id":"2106.02588","title":"Stochastic gradient descent with noise of machine learning type. Part II: Continuous time analysis","created":"2021-06-04","cited_by_count":25,"area":null},{"id":"2406.10952","title":"Avoiding Copyright Infringement via Large Language Model Unlearning","created":"2024-06-16","cited_by_count":24,"area":"safety"},{"id":"2212.03050","title":"Uniform-in-time propagation of chaos for mean field Langevin dynamics","created":"2022-12-06","cited_by_count":23,"area":null},{"id":"2410.14972","title":"MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning","created":"2024-10-19","cited_by_count":23,"area":"moe"},{"id":"2206.00024","title":"Online PAC-Bayes Learning","created":"2022-05-31","cited_by_count":22,"area":null},{"id":"2510.06826","title":"Mid-Training of Large Language Models: A Survey","created":"2025-10-08","cited_by_count":21,"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":"2101.09868","title":"CPT: Efficient Deep Neural Network Training via Cyclic Precision","created":"2021-01-25","cited_by_count":19,"area":null},{"id":"2111.06862","title":"Silicon Photonic Architecture for Training Deep Neural Networks with Direct Feedback Alignment","created":"2021-11-12","cited_by_count":17,"area":null},{"id":"2202.00308","title":"PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation","created":"2022-02-01","cited_by_count":17,"area":null},{"id":"2507.12224","title":"Optimizers Qualitatively Alter Solutions And We Should Leverage This","created":"2025-07-16","cited_by_count":17,"area":null},{"id":"2204.13751","title":"BEINIT: Avoiding Barren Plateaus in Variational Quantum Algorithms","created":"2022-04-28","cited_by_count":16,"area":null},{"id":"2102.02976","title":"Generalization Bounds for Noisy Iterative Algorithms Using Properties of Additive Noise Channels","created":"2021-02-05","cited_by_count":15,"area":null},{"id":"2104.14840","title":"Unified Convergence Analysis for Adaptive Optimization with Moving Average Estimator","created":"2021-04-30","cited_by_count":13,"area":null},{"id":"2204.06760","title":"HCFL: A High Compression Approach for Communication-Efficient Federated Learning in Very Large Scale IoT Networks","created":"2022-04-14","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":"2204.03230","title":"What You See is What You Get: Principled Deep Learning via Distributional Generalization","created":"2022-04-07","cited_by_count":11,"area":null},{"id":"2104.04874","title":"SGD Implicitly Regularizes Generalization Error","created":"2021-04-10","cited_by_count":10,"area":null},{"id":"2210.04349","title":"Nonlinear Sufficient Dimension Reduction with a Stochastic Neural Network","created":"2022-10-09","cited_by_count":10,"area":null},{"id":"2404.03176","title":"Information-Theoretic Generalization Bounds for Deep Neural Networks","created":"2024-04-04","cited_by_count":10,"area":null},{"id":"2201.05319","title":"A Kernel-Expanded Stochastic Neural Network","created":"2022-01-14","cited_by_count":9,"area":null},{"id":"2202.13808","title":"DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN Training","created":"2022-02-28","cited_by_count":9,"area":null},{"id":"2205.11361","title":"Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent","created":"2022-05-23","cited_by_count":9,"area":null},{"id":"2306.03630","title":"Mutual Information Regularization for Weakly-supervised RGB-D Salient Object Detection","created":"2023-06-06","cited_by_count":9,"area":null},{"id":"2209.12466","title":"Learned Force Fields Are Ready For Ground State Catalyst Discovery","created":"2022-09-26","cited_by_count":8,"area":null},{"id":"2407.15351","title":"LLMExplainer: Large Language Model based Bayesian Inference for Graph Explanation Generation","created":"2024-07-22","cited_by_count":8,"area":null},{"id":"2102.04450","title":"Noise Optimization for Artificial Neural Networks","created":"2021-02-06","cited_by_count":7,"area":null},{"id":"2106.03091","title":"Regularization in ResNet with Stochastic Depth","created":"2021-06-06","cited_by_count":7,"area":null},{"id":"2310.18626","title":"Benchmark Generation Framework with Customizable Distortions for Image Classifier Robustness","created":"2023-10-28","cited_by_count":7,"area":null},{"id":"2409.07626","title":"Generalization Error Bound for Quantum Machine Learning in NISQ Era -- A Survey","created":"2024-09-11","cited_by_count":7,"area":null},{"id":"2410.12707","title":"FusionLLM: A Decentralized LLM Training System on Geo-distributed GPUs with Adaptive Compression","created":"2024-10-16","cited_by_count":7,"area":null},{"id":"2410.19921","title":"Method for noise-induced regularization in quantum neural networks","created":"2024-10-25","cited_by_count":7,"area":null},{"id":"2602.15322","title":"On Surprising Effectiveness of Masking Updates in Adaptive Optimizers","created":"2026-02-17","cited_by_count":7,"area":null},{"id":"2206.01944","title":"Robust Meta-learning with Sampling Noise and Label Noise via Eigen-Reptile","created":"2022-06-04","cited_by_count":6,"area":null},{"id":"2305.19243","title":"Improving Generalization of Complex Models under Unbounded Loss Using PAC-Bayes Bounds","created":"2023-05-30","cited_by_count":6,"area":null},{"id":"2103.13894","title":"Boosting Binary Masks for Multi-Domain Learning through Affine Transformations","created":"2021-03-25","cited_by_count":5,"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":"2302.03281","title":"Utility-based Perturbed Gradient Descent: An Optimizer for Continual Learning","created":"2023-02-07","cited_by_count":5,"area":null},{"id":"2302.12304","title":"Uncertainty Injection: A Deep Learning Method for Robust Optimization","created":"2023-02-23","cited_by_count":5,"area":null},{"id":"2108.06771","title":"NPBDREG: Uncertainty Assessment in Diffeomorphic Brain MRI Registration using a Non-parametric Bayesian Deep-Learning Based Approach","created":"2021-08-15","cited_by_count":4,"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":"2306.10598","title":"DropCompute: simple and more robust distributed synchronous training via compute variance reduction","created":"2023-06-18","cited_by_count":4,"area":null},{"id":"2306.17630","title":"Navigating Noise: A Study of How Noise Influences Generalisation and Calibration of Neural Networks","created":"2023-06-30","cited_by_count":4,"area":null},{"id":"2403.02690","title":"Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learning","created":"2024-03-05","cited_by_count":4,"area":null},{"id":"2404.04550","title":"NPB-REC: A Non-parametric Bayesian Deep-learning Approach for Undersampled MRI Reconstruction with Uncertainty Estimation","created":"2024-04-06","cited_by_count":4,"area":null},{"id":"2412.17107","title":"Grams: Gradient Descent with Adaptive Momentum Scaling","created":"2024-12-22","cited_by_count":4,"area":null},{"id":"2503.13236","title":"Gradient Extrapolation for Debiased Representation Learning","created":"2025-03-17","cited_by_count":4,"area":null},{"id":"2510.25117","title":"A Survey on Unlearning in Large Language Models","created":"2025-10-29","cited_by_count":4,"area":"safety"},{"id":"2103.05461","title":"Analytically Tractable Inference in Deep Neural Networks","created":"2021-03-09","cited_by_count":3,"area":null},{"id":"2209.14520","title":"Label driven Knowledge Distillation for Federated Learning with non-IID Data","created":"2022-09-29","cited_by_count":3,"area":"distill"},{"id":"2312.07932","title":"A Novel Image Classification Framework Based on Variational Quantum Algorithms","created":"2023-12-13","cited_by_count":3,"area":null},{"id":"2407.13703","title":"Energy-Efficient Channel Decoding for Wireless Federated Learning: Convergence Analysis and Adaptive Design","created":"2024-06-26","cited_by_count":3,"area":null},{"id":"2501.14122","title":"Reinforcement Learning Platform for Adversarial Black-box Attacks with Custom Distortion Filters","created":"2025-01-23","cited_by_count":3,"area":"deeprl"},{"id":"2102.00511","title":"Fine-tuning Handwriting Recognition systems with Temporal Dropout","created":"2021-01-31","cited_by_count":2,"area":null},{"id":"2107.03759","title":"Analytically Tractable Hidden-States Inference in Bayesian Neural Networks","created":"2021-07-08","cited_by_count":2,"area":null},{"id":"2110.14092","title":"BioGrad: Biologically Plausible Gradient-Based Learning for Spiking Neural Networks","created":"2021-10-27","cited_by_count":2,"area":null},{"id":"2201.01871","title":"Direct multi-modal inversion of geophysical logs using deep learning","created":"2021-11-29","cited_by_count":2,"area":null},{"id":"2202.09052","title":"Tackling benign nonconvexity with smoothing and stochastic gradients","created":"2022-02-18","cited_by_count":2,"area":null},{"id":"2212.12018","title":"Langevin algorithms for Markovian Neural Networks and Deep Stochastic control","created":"2022-12-22","cited_by_count":2,"area":null},{"id":"2304.12681","title":"Differential Privacy via Distributionally Robust Optimization","created":"2023-04-25","cited_by_count":2,"area":null},{"id":"2309.06921","title":"Investigating the Impact of Action Representations in Policy Gradient Algorithms","created":"2023-09-13","cited_by_count":2,"area":null},{"id":"2309.13731","title":"Arabic Sentiment Analysis with Noisy Deep Explainable Model","created":"2023-09-24","cited_by_count":2,"area":null},{"id":"2402.11857","title":"Communication-Efficient Distributed Learning with Local Immediate Error Compensation","created":"2024-02-19","cited_by_count":2,"area":null},{"id":"2404.03992","title":"Rolling the dice for better deep learning performance: A study of randomness techniques in deep neural networks","created":"2024-04-05","cited_by_count":2,"area":null},{"id":"2409.07606","title":"The Role of Deep Learning Regularizations on Actors in Offline RL","created":"2024-09-11","cited_by_count":2,"area":"offlinerl"},{"id":"2503.16183","title":"Variance-Aware Noisy Training: Hardening DNNs against Unstable Analog Computations","created":"2025-03-20","cited_by_count":2,"area":null},{"id":"2506.18588","title":"Optimization-Induced Dynamics of Lipschitz Continuity in Neural Networks","created":"2025-06-23","cited_by_count":2,"area":null},{"id":"2508.21353","title":"Adaptive Heavy-Tailed Stochastic Gradient Descent","created":"2025-08-29","cited_by_count":2,"area":null},{"id":"2509.17789","title":"From Restoration to Reconstruction: Rethinking 3D Gaussian Splatting for Underwater Scenes","created":"2025-09-22","cited_by_count":2,"area":null},{"id":"2602.05600","title":"On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2107.14597","title":"Text Classification and Clustering with Annealing Soft Nearest Neighbor Loss","created":"2021-07-23","cited_by_count":1,"area":null},{"id":"2205.15617","title":"Optimizing Intermediate Representations of Generative Models for Phase Retrieval","created":"2022-05-31","cited_by_count":1,"area":null},{"id":"2208.11873","title":"Learning Rate Perturbation: A Generic Plugin of Learning Rate Schedule towards Flatter Local Minima","created":"2022-08-25","cited_by_count":1,"area":null},{"id":"2210.15764","title":"Noise Injection Node Regularization for Robust Learning","created":"2022-10-27","cited_by_count":1,"area":null},{"id":"2212.14718","title":"Langevin algorithms for very deep Neural Networks with application to image classification","created":"2022-12-27","cited_by_count":1,"area":null},{"id":"2302.04977","title":"Mithridates: Auditing and Boosting Backdoor Resistance of Machine Learning Pipelines","created":"2023-02-09","cited_by_count":1,"area":null},{"id":"2303.04744","title":"Federated Privacy-preserving Collaborative Filtering for On-Device Next App Prediction","created":"2023-02-05","cited_by_count":1,"area":null},{"id":"2306.05652","title":"Privacy Aware Question-Answering System for Online Mental Health Risk Assessment","created":"2023-06-09","cited_by_count":1,"area":null},{"id":"2311.05790","title":"The Paradox of Noise: An Empirical Study of Noise-Infusion Mechanisms to Improve Generalization, Stability, and Privacy in Federated Learning","created":"2023-11-09","cited_by_count":1,"area":null},{"id":"2311.18508","title":"DifAugGAN: A Practical Diffusion-style Data Augmentation for GAN-based Single Image Super-resolution","created":"2023-11-30","cited_by_count":1,"area":null}],"next_cursor":"100"}