{"total":90,"rows":[{"id":"2104.09841","title":"SelfReg: Self-supervised Contrastive Regularization for Domain Generalization","created":"2021-04-20","cited_by_count":189,"area":null},{"id":"2206.06232","title":"Towards Understanding Sharpness-Aware Minimization","created":"2022-06-13","cited_by_count":146,"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":"2111.01549","title":"Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima","created":"2021-10-30","cited_by_count":118,"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":"2206.07085","title":"Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction","created":"2022-06-14","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":"2202.00661","title":"When Do Flat Minima Optimizers Work?","created":"2022-02-01","cited_by_count":78,"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":"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":"2304.14647","title":"An Adaptive Policy to Employ Sharpness-Aware Minimization","created":"2023-04-28","cited_by_count":43,"area":null},{"id":"2203.10144","title":"Closing the Generalization Gap of Cross-silo Federated Medical Image Segmentation","created":"2022-03-18","cited_by_count":42,"area":null},{"id":"2307.06440","title":"No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models","created":"2023-07-12","cited_by_count":41,"area":null},{"id":"2105.14573","title":"Embedding Principle of Loss Landscape of Deep Neural Networks","created":"2021-05-30","cited_by_count":38,"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":"2405.16002","title":"Does SGD really happen in tiny subspaces?","created":"2024-05-25","cited_by_count":36,"area":null},{"id":"2210.17216","title":"Symmetries, flat minima, and the conserved quantities of gradient flow","created":"2022-10-31","cited_by_count":35,"area":null},{"id":"2404.00986","title":"Make Continual Learning Stronger via C-Flat","created":"2024-04-01","cited_by_count":35,"area":null},{"id":"2107.11228","title":"Taxonomizing local versus global structure in neural network loss landscapes","created":"2021-07-23","cited_by_count":34,"area":null},{"id":"2203.10036","title":"On the Generalization Mystery in Deep Learning","created":"2022-03-18","cited_by_count":25,"area":null},{"id":"2111.15527","title":"Embedding Principle: a hierarchical structure of loss landscape of deep neural networks","created":"2021-11-30","cited_by_count":22,"area":null},{"id":"2301.02312","title":"Training trajectories, mini-batch losses and the curious role of the learning rate","created":"2023-01-05","cited_by_count":21,"area":null},{"id":"2303.00565","title":"AdaSAM: Boosting Sharpness-Aware Minimization with Adaptive Learning Rate and Momentum for Training Deep Neural Networks","created":"2023-03-01","cited_by_count":21,"area":null},{"id":"2211.13723","title":"Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective","created":"2022-11-24","cited_by_count":15,"area":null},{"id":"2310.11428","title":"Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression","created":"2023-10-17","cited_by_count":14,"area":null},{"id":"2305.15659","title":"How to escape sharp minima with random perturbations","created":"2023-05-25","cited_by_count":13,"area":null},{"id":"2505.02809","title":"Towards Quantifying the Hessian Structure of Neural Networks","created":"2025-05-05","cited_by_count":13,"area":null},{"id":"2102.10094","title":"Formal Language Theory Meets Modern NLP","created":"2021-02-19","cited_by_count":9,"area":null},{"id":"2208.07951","title":"On the generalization of learning algorithms that do not converge","created":"2022-08-16","cited_by_count":9,"area":null},{"id":"2209.02525","title":"Generalisation under gradient descent via deterministic PAC-Bayes","created":"2022-09-06","cited_by_count":9,"area":null},{"id":"2302.10181","title":"Exploring the Effect of Multi-step Ascent in Sharpness-Aware Minimization","created":"2023-01-27","cited_by_count":9,"area":null},{"id":"2404.06391","title":"Exploring Neural Network Landscapes: Star-Shaped and Geodesic Connectivity","created":"2024-04-09","cited_by_count":9,"area":null},{"id":"2501.01045","title":"ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think","created":"2025-01-02","cited_by_count":9,"area":null},{"id":"2302.11085","title":"Learning to Generalize Provably in Learning to Optimize","created":"2023-02-22","cited_by_count":8,"area":null},{"id":"2104.03525","title":"A Neural Pre-Conditioning Active Learning Algorithm to Reduce Label Complexity","created":"2021-04-08","cited_by_count":7,"area":null},{"id":"2205.13283","title":"Embedding Principle in Depth for the Loss Landscape Analysis of Deep Neural Networks","created":"2022-05-26","cited_by_count":7,"area":null},{"id":"2305.04573","title":"HiFi: High-Information Attention Heads Hold for Parameter-Efficient Model Adaptation","created":"2023-05-08","cited_by_count":7,"area":null},{"id":"2307.08436","title":"DOT: A Distillation-Oriented Trainer","created":"2023-07-17","cited_by_count":7,"area":"distill"},{"id":"2106.11514","title":"Rethinking Adam: A Twofold Exponential Moving Average Approach","created":"2021-06-22","cited_by_count":6,"area":null},{"id":"2107.05804","title":"AlterSGD: Finding Flat Minima for Continual Learning by Alternative Training","created":"2021-07-13","cited_by_count":6,"area":null},{"id":"2302.12091","title":"Random Teachers are Good Teachers","created":"2023-02-23","cited_by_count":6,"area":"distill"},{"id":"2402.11262","title":"Mirror Gradient: Towards Robust Multimodal Recommender Systems via Exploring Flat Local Minima","created":"2024-02-17","cited_by_count":6,"area":null},{"id":"2503.17138","title":"Structure Is Not Enough: Leveraging Behavior for Neural Network Weight Reconstruction","created":"2025-03-21","cited_by_count":6,"area":null},{"id":"2506.05454","title":"Zeroth-Order Optimization Finds Flat Minima","created":"2025-06-05","cited_by_count":6,"area":"deeprl"},{"id":"2103.11154","title":"Low Dimensional Landscape Hypothesis is True: DNNs can be Trained in Tiny Subspaces","created":"2021-03-20","cited_by_count":5,"area":null},{"id":"2106.04186","title":"What training reveals about neural network complexity","created":"2021-06-08","cited_by_count":5,"area":null},{"id":"2111.04004","title":"Exponential escape efficiency of SGD from sharp minima in non-stationary regime","created":"2021-11-07","cited_by_count":5,"area":null},{"id":"2206.04762","title":"Data-Efficient Double-Win Lottery Tickets from Robust Pre-training","created":"2022-06-09","cited_by_count":5,"area":null},{"id":"2306.07104","title":"Unveiling the Hessian's Connection to the Decision Boundary","created":"2023-06-12","cited_by_count":5,"area":null},{"id":"2406.02234","title":"On the Limitations of Fractal Dimension as a Measure of Generalization","created":"2024-06-04","cited_by_count":5,"area":null},{"id":"2411.06710","title":"Model Fusion through Bayesian Optimization in Language Model Fine-Tuning","created":"2024-11-11","cited_by_count":5,"area":null},{"id":"2101.02524","title":"A spin-glass model for the loss surfaces of generative adversarial networks","created":"2021-01-07","cited_by_count":4,"area":null},{"id":"2309.16369","title":"Bringing the Discussion of Minima Sharpness to the Audio Domain: a Filter-Normalised Evaluation for Acoustic Scene Classification","created":"2023-09-28","cited_by_count":4,"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":"2305.08611","title":"GeNAS: Neural Architecture Search with Better Generalization","created":"2023-05-15","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":"2204.12466","title":"Meta-free few-shot learning via representation learning with weight averaging","created":"2022-04-26","cited_by_count":2,"area":null},{"id":"2304.11519","title":"Hierarchical Weight Averaging for Deep Neural Networks","created":"2023-04-23","cited_by_count":2,"area":null},{"id":"2410.11330","title":"Evolutionary Retrofitting","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2102.11210","title":"Non-Convex Optimization with Spectral Radius Regularization","created":"2021-02-22","cited_by_count":1,"area":null},{"id":"2107.05328","title":"Structured Directional Pruning via Perturbation Orthogonal Projection","created":"2021-07-12","cited_by_count":1,"area":null},{"id":"2112.11619","title":"A Convergent ADMM Framework for Efficient Neural Network Training","created":"2021-12-22","cited_by_count":1,"area":null},{"id":"2204.01365","title":"Deep learning, stochastic gradient descent and diffusion maps","created":"2022-04-04","cited_by_count":1,"area":null},{"id":"2303.02357","title":"DiTTO: A Feature Representation Imitation Approach for Improving Cross-Lingual Transfer","created":"2023-03-04","cited_by_count":1,"area":null},{"id":"2405.12489","title":"Exploring and Exploiting the Asymmetric Valley of Deep Neural Networks","created":"2024-05-21","cited_by_count":1,"area":null},{"id":"2405.12493","title":"Visualizing, Rethinking, and Mining the Loss Landscape of Deep Neural Networks","created":"2024-05-21","cited_by_count":1,"area":null},{"id":"2412.02153","title":"Revisiting the Initial Steps in Adaptive Gradient Descent Optimization","created":"2024-12-03","cited_by_count":1,"area":null},{"id":"2501.06603","title":"Preconditioned Sharpness-Aware Minimization: Unifying Analysis and a Novel Learning Algorithm","created":"2025-01-11","cited_by_count":1,"area":null},{"id":"2502.06192","title":"Right Time to Learn:Promoting Generalization via Bio-inspired Spacing Effect in Knowledge Distillation","created":"2025-02-10","cited_by_count":1,"area":"distill"},{"id":"2505.18107","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2508.18860","title":"C-Flat++: Towards a More Efficient and Powerful Framework for Continual Learning","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2511.04514","title":"Linear Mode Connectivity under Data Shifts for Deep Ensembles of Image Classifiers","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2604.11064","title":"A Faster Path to Continual Learning","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2107.01525","title":"AdaL: Adaptive Gradient Transformation Contributes to Convergences and Generalizations","created":"2021-07-04","cited_by_count":0,"area":null},{"id":"2204.01705","title":"Learning to Accelerate by the Methods of Step-size Planning","created":"2022-04-01","cited_by_count":0,"area":null},{"id":"2207.12505","title":"On the benefits of non-linear weight updates","created":"2022-07-25","cited_by_count":0,"area":null},{"id":"2211.16209","title":"The Vanishing Decision Boundary Complexity and the Strong First Component","created":"2022-11-25","cited_by_count":0,"area":null},{"id":"2302.09376","title":"Why is parameter averaging beneficial in SGD? An objective smoothing perspective","created":"2023-02-18","cited_by_count":0,"area":null},{"id":"2305.15997","title":"SING: A Plug-and-Play DNN Learning Technique","created":"2023-05-25","cited_by_count":0,"area":null},{"id":"2402.03021","title":"Data-induced multiscale losses and efficient multirate gradient descent schemes","created":"2024-02-05","cited_by_count":0,"area":null},{"id":"2403.00798","title":"Helen: Optimizing CTR Prediction Models with Frequency-wise Hessian Eigenvalue Regularization","created":"2024-02-23","cited_by_count":0,"area":null},{"id":"2504.02272","title":"Generative Classifier for Domain Generalization","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2510.02174","title":"Flatness-Aware Stochastic Gradient Langevin Dynamics","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2510.08968","title":"Learning Regularizers: Learning Optimizers that can Regularize","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2601.07636","title":"Beyond Sharpness: A Flatness Decomposition Framework for Efficient Continual Learning","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2601.19947","title":"NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2606.25004","title":"Certification of Machine Learning Models via Directional Sharpness","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2608.26587","title":"Surgical Alignment in Knowledge Graph Training for Clinical Diagnosis with Large Language Models","created":"2026-08-27","cited_by_count":0,"area":"lr"}],"next_cursor":null}