{"total":1248,"rows":[{"id":"2302.00487","title":"A Comprehensive Survey of Continual Learning: Theory, Method and Application","created":"2023-01-31","cited_by_count":872,"area":null},{"id":"2201.02177","title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","created":"2022-01-06","cited_by_count":629,"area":null},{"id":"2203.02053","title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning","created":"2022-03-03","cited_by_count":561,"area":null},{"id":"2102.08604","title":"SWAD: Domain Generalization by Seeking Flat Minima","created":"2021-02-17","cited_by_count":434,"area":null},{"id":"2302.06675","title":"Symbolic Discovery of Optimization Algorithms","created":"2023-02-13","cited_by_count":434,"area":null},{"id":"2103.00065","title":"Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability","created":"2021-02-26","cited_by_count":427,"area":null},{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367,"area":null},{"id":"2105.03404","title":"ResMLP: Feedforward networks for image classification with data-efficient training","created":"2021-05-07","cited_by_count":339,"area":null},{"id":"2202.06709","title":"How Do Vision Transformers Work?","created":"2022-02-14","cited_by_count":307,"area":null},{"id":"2102.11600","title":"ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks","created":"2021-02-23","cited_by_count":293,"area":null},{"id":"2110.06296","title":"The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks","created":"2021-10-12","cited_by_count":291,"area":null},{"id":"2106.01548","title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","created":"2021-06-03","cited_by_count":260,"area":null},{"id":"2309.14509","title":"DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models","created":"2023-09-25","cited_by_count":245,"area":null},{"id":"2206.07137","title":"Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt","created":"2022-06-14","cited_by_count":236,"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":"2203.05740","title":"QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization","created":"2022-03-11","cited_by_count":180,"area":null},{"id":"2203.08065","title":"Surrogate Gap Minimization Improves Sharpness-Aware Training","created":"2022-03-15","cited_by_count":172,"area":null},{"id":"2209.15594","title":"Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability","created":"2022-09-30","cited_by_count":155,"area":null},{"id":"2303.00654","title":"How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy","created":"2023-03-01","cited_by_count":153,"area":null},{"id":"2109.05687","title":"Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning","created":"2021-09-13","cited_by_count":146,"area":null},{"id":"2206.06232","title":"Towards Understanding Sharpness-Aware Minimization","created":"2022-06-13","cited_by_count":146,"area":null},{"id":"2206.02618","title":"Generalized Federated Learning via Sharpness Aware Minimization","created":"2022-06-06","cited_by_count":144,"area":null},{"id":"2211.11004","title":"Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation","created":"2022-11-20","cited_by_count":142,"area":null},{"id":"2106.09647","title":"Deep Learning Through the Lens of Example Difficulty","created":"2021-06-17","cited_by_count":141,"area":null},{"id":"2110.03141","title":"Efficient Sharpness-aware Minimization for Improved Training of Neural Networks","created":"2021-10-07","cited_by_count":137,"area":null},{"id":"2112.09153","title":"An Empirical Investigation of the Role of Pre-training in Lifelong Learning","created":"2021-12-16","cited_by_count":134,"area":null},{"id":"2203.02714","title":"Towards Efficient and Scalable Sharpness-Aware Minimization","created":"2022-03-05","cited_by_count":129,"area":null},{"id":"2205.09745","title":"Understanding Gradient Descent on Edge of Stability in Deep Learning","created":"2022-05-19","cited_by_count":128,"area":null},{"id":"2210.01790","title":"Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals","created":"2022-10-04","cited_by_count":126,"area":null},{"id":"2202.03599","title":"Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning","created":"2022-02-08","cited_by_count":122,"area":null},{"id":"2106.06530","title":"Label Noise SGD Provably Prefers Flat Global Minimizers","created":"2021-06-11","cited_by_count":121,"area":null},{"id":"2211.08403","title":"REPAIR: REnormalizing Permuted Activations for Interpolation Repair","created":"2022-11-15","cited_by_count":120,"area":null},{"id":"2111.14213","title":"Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning","created":"2021-11-28","cited_by_count":114,"area":null},{"id":"2201.12604","title":"Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System","created":"2022-01-29","cited_by_count":112,"area":null},{"id":"2106.09524","title":"Implicit Bias of SGD for Diagonal Linear Networks: a Provable Benefit of Stochasticity","created":"2021-06-17","cited_by_count":110,"area":null},{"id":"2110.08529","title":"Sharpness-Aware Minimization Improves Language Model Generalization","created":"2021-10-16","cited_by_count":108,"area":null},{"id":"2110.06914","title":"What Happens after SGD Reaches Zero Loss? --A Mathematical Framework","created":"2021-10-13","cited_by_count":107,"area":null},{"id":"2104.04975","title":"Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning","created":"2021-04-11","cited_by_count":106,"area":null},{"id":"2303.10353","title":"Sharpness-Aware Gradient Matching for Domain Generalization","created":"2023-03-18","cited_by_count":102,"area":null},{"id":"2111.10603","title":"Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning","created":"2021-11-20","cited_by_count":101,"area":null},{"id":"2107.04562","title":"The Bayesian Learning Rule","created":"2021-07-09","cited_by_count":99,"area":null},{"id":"2406.04836","title":"Revisiting Catastrophic Forgetting in Large Language Model Tuning","created":"2024-06-07","cited_by_count":99,"area":null},{"id":"2203.11834","title":"Improving Generalization in Federated Learning by Seeking Flat Minima","created":"2022-03-22","cited_by_count":98,"area":null},{"id":"2205.14083","title":"Sharpness-Aware Training for Free","created":"2022-05-27","cited_by_count":95,"area":null},{"id":"2210.09221","title":"Vision Transformers provably learn spatial structure","created":"2022-10-13","cited_by_count":93,"area":null},{"id":"2302.07011","title":"A Modern Look at the Relationship between Sharpness and Generalization","created":"2023-02-14","cited_by_count":92,"area":null},{"id":"2403.19522","title":"Model Stock: All we need is just a few fine-tuned models","created":"2024-03-28","cited_by_count":92,"area":null},{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91,"area":null},{"id":"2111.04877","title":"Papaya: Practical, Private, and Scalable Federated Learning","created":"2021-11-08","cited_by_count":90,"area":null},{"id":"2203.13450","title":"A Comparative Survey of Deep Active Learning","created":"2022-03-25","cited_by_count":89,"area":null},{"id":"2206.07085","title":"Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction","created":"2022-06-14","cited_by_count":86,"area":null},{"id":"2208.12591","title":"On the Implicit Bias in Deep-Learning Algorithms","created":"2022-08-26","cited_by_count":86,"area":null},{"id":"2206.08213","title":"A Closer Look at Smoothness in Domain Adversarial Training","created":"2022-06-16","cited_by_count":85,"area":null},{"id":"2102.00931","title":"Information-Theoretic Generalization Bounds for Stochastic Gradient Descent","created":"2021-02-01","cited_by_count":84,"area":null},{"id":"2110.15777","title":"GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and Heterophily","created":"2021-10-29","cited_by_count":84,"area":null},{"id":"2206.04920","title":"Fisher SAM: Information Geometry and Sharpness Aware Minimisation","created":"2022-06-10","cited_by_count":84,"area":null},{"id":"2210.14199","title":"Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models","created":"2022-10-25","cited_by_count":84,"area":null},{"id":"2102.12108","title":"The Promises and Pitfalls of Deep Kernel Learning","created":"2021-02-24","cited_by_count":81,"area":null},{"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":"2202.00661","title":"When Do Flat Minima Optimizers Work?","created":"2022-02-01","cited_by_count":78,"area":null},{"id":"2104.07446","title":"Rehearsal revealed: The limits and merits of revisiting samples in continual learning","created":"2021-04-15","cited_by_count":76,"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":"2102.13042","title":"Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling","created":"2021-02-25","cited_by_count":75,"area":null},{"id":"2106.07820","title":"On Large-Cohort Training for Federated Learning","created":"2021-06-15","cited_by_count":74,"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":"2405.17730","title":"MMPareto: Boosting Multimodal Learning with Innocent Unimodal Assistance","created":"2024-05-28","cited_by_count":73,"area":null},{"id":"2309.10818","title":"SlimPajama-DC: Understanding Data Combinations for LLM Training","created":"2023-09-19","cited_by_count":72,"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":"2411.18704","title":"Exponential Moving Average of Weights in Deep Learning: Dynamics and Benefits","created":"2024-11-27","cited_by_count":71,"area":null},{"id":"2210.05177","title":"Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach","created":"2022-10-11","cited_by_count":70,"area":null},{"id":"2210.01725","title":"MEDFAIR: Benchmarking Fairness for Medical Imaging","created":"2022-10-04","cited_by_count":68,"area":null},{"id":"2210.05337","title":"SGD with Large Step Sizes Learns Sparse Features","created":"2022-10-11","cited_by_count":68,"area":null},{"id":"2201.04122","title":"In Defense of the Unitary Scalarization for Deep Multi-Task Learning","created":"2022-01-11","cited_by_count":67,"area":null},{"id":"2103.05127","title":"Model Complexity of Deep Learning: A Survey","created":"2021-03-08","cited_by_count":65,"area":null},{"id":"2211.05729","title":"How Does Sharpness-Aware Minimization Minimize Sharpness?","created":"2022-11-10","cited_by_count":65,"area":null},{"id":"2104.05522","title":"Neural basis expansion analysis with exogenous variables: Forecasting electricity prices with NBEATSx","created":"2021-04-12","cited_by_count":64,"area":null},{"id":"2112.10775","title":"HarmoFL: Harmonizing Local and Global Drifts in Federated Learning on Heterogeneous Medical Images","created":"2021-12-20","cited_by_count":64,"area":null},{"id":"2207.02628","title":"The alignment property of SGD noise and how it helps select flat minima: A stability analysis","created":"2022-07-06","cited_by_count":64,"area":null},{"id":"2105.13462","title":"On Linear Stability of SGD and Input-Smoothness of Neural Networks","created":"2021-05-27","cited_by_count":63,"area":null},{"id":"2109.14119","title":"Stochastic Training is Not Necessary for Generalization","created":"2021-09-29","cited_by_count":63,"area":null},{"id":"2306.02602","title":"ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstruction","created":"2023-06-05","cited_by_count":63,"area":null},{"id":"2103.03936","title":"Pufferfish: Communication-efficient Models At No Extra Cost","created":"2021-03-05","cited_by_count":61,"area":null},{"id":"2106.10891","title":"Open-set Label Noise Can Improve Robustness Against Inherent Label Noise","created":"2021-06-21","cited_by_count":59,"area":null},{"id":"2206.03996","title":"Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning","created":"2022-06-08","cited_by_count":58,"area":null},{"id":"2301.11300","title":"ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradients","created":"2023-01-26","cited_by_count":58,"area":null},{"id":"2302.10911","title":"Revisiting Weighted Aggregation in Federated Learning with Neural Networks","created":"2023-02-14","cited_by_count":58,"area":null},{"id":"2104.04448","title":"Relating Adversarially Robust Generalization to Flat Minima","created":"2021-04-09","cited_by_count":57,"area":null},{"id":"2206.10654","title":"On the Maximum Hessian Eigenvalue and Generalization","created":"2022-06-21","cited_by_count":57,"area":null},{"id":"2303.03108","title":"Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization","created":"2023-03-03","cited_by_count":57,"area":null},{"id":"2205.12411","title":"Linear Connectivity Reveals Generalization Strategies","created":"2022-05-24","cited_by_count":56,"area":null},{"id":"2503.02113","title":"Deep Learning is Not So Mysterious or Different","created":"2025-03-03","cited_by_count":56,"area":null},{"id":"2403.12350","title":"Friendly Sharpness-Aware Minimization","created":"2024-03-19","cited_by_count":53,"area":null},{"id":"2106.16225","title":"Analytic Insights into Structure and Rank of Neural Network Hessian Maps","created":"2021-06-30","cited_by_count":52,"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":"2306.10209","title":"ZeRO++: Extremely Efficient Collective Communication for Giant Model Training","created":"2023-06-16","cited_by_count":52,"area":null},{"id":"2210.01513","title":"The Dynamics of Sharpness-Aware Minimization: Bouncing Across Ravines and Drifting Towards Wide Minima","created":"2022-10-04","cited_by_count":51,"area":null},{"id":"2105.02716","title":"Noether's Learning Dynamics: Role of Symmetry Breaking in Neural Networks","created":"2021-05-06","cited_by_count":50,"area":null},{"id":"2102.04828","title":"Consensus Control for Decentralized Deep Learning","created":"2021-02-09","cited_by_count":49,"area":null},{"id":"2203.13834","title":"A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration","created":"2022-03-25","cited_by_count":49,"area":null},{"id":"2406.18533","title":"On Scaling Up 3D Gaussian Splatting Training","created":"2024-06-26","cited_by_count":49,"area":null}],"next_cursor":"100"}