Research graph
References from Instance-Dependent Early Stopping for Adaptive Data Pruning. Local targets link to admitted publications; unresolved targets remain external evidence.
10.1007/3-540-49430-8_3
10.1007/3-540-49430-8_3 · External reference
Early stopping and non-parametric regression: An optimal data-dependent stopping rule
2014 · External reference
Overfitting in neural nets: Backpropagation, conjugate gradient, and early stopping
2000 · External reference
Early stopping against label noise without validation data
2024 · External reference
Generalization and parameter estimation in feedforward nets: Some experiments
1990 · External reference
10.1145/3446776
10.1145/3446776 · External reference
10.1073/pnas.1903070116
10.1073/pnas.1903070116 · External reference
10.1088/1742-5468/ac3a74
10.1088/1742-5468/ac3a74 · External reference
10.1111/j.2517-6161.1996.tb02080.x
10.1111/j.2517-6161.1996.tb02080.x · External reference
10.2307/1267351
10.2307/1267351 · External reference
Unresolved reference
2016 · External reference
Deep learning scaling is predictable, empirically
2017 · External reference
Scaling laws for neural language models
2020 · External reference
Language models are few-shot learners
2020 · External reference
10.52202/068431-1419
10.52202/068431-1419 · External reference
LoftQ: LoRA-fine-tuning-aware quantization for large language models
2024 · External reference
CasCast: Skillful high-resolution precipitation nowcasting via cascaded modelling
2024 · External reference
Overfitting in adversarially robust deep learning
2020 · External reference
Rethinking bias-variance trade-off for generalization of neural networks
2020 · External reference
An investigation of why overparameterization exacerbates spurious correlations
2020 · External reference
A closer look at memorization in deep networks
2017 · External reference
Benign overfitting in classification: Provably counter label noise with larger models
2023 · External reference
Online batch selection for faster training of neural networks
2015 · External reference
Accelerating deep learning by focusing on the biggest losers
2019 · External reference
InfoBatch: Lossless training speed up by unbiased dynamic data pruning
2024 · External reference
On the power of curriculum learning in training deep networks
2019 · External reference
Optimizing data usage via differentiable rewards
2020 · External reference
On calibration of modern neural networks
2017 · External reference
Enhancing the reliability of out-of-distribution image detection in neural networks
2018 · External reference
MentorNet: Learning data-driven curriculum for very deep neural networks on corrupted labels
2018 · External reference
10.1109/cvpr.2019.00949
10.1109/cvpr.2019.00949 · External reference
Learning imbalanced datasets with label-distribution-aware margin loss
2019 · External reference
Do we need zero training loss after achieving zero training error?
2020 · External reference
Sharpness minimization algorithms do not only minimize sharpness to achieve better generalization
2024 · External reference
On the over-memorization during natural, robust and catastrophic overfitting
2024 · External reference
Layer-aware analysis of catastrophic overfitting: Revealing the pseudo-robust shortcut dependency
2024 · External reference
10.52202/075280-2968
10.52202/075280-2968 · External reference
10.5555/2969033.2969154
10.5555/2969033.2969154 · External reference
Sharpness-aware minimization for efficiently improving generalization
2021 · External reference
10.18653/v1/2021.findings-acl.449
10.18653/v1/2021.findings-acl.449 · External reference
10.18653/v1/d19-5406
10.18653/v1/d19-5406 · External reference
10.1093/jamia/ocae122
10.1093/jamia/ocae122 · External reference
10.1016/j.csl.2019.06.009
10.1016/j.csl.2019.06.009 · External reference
The Llama 3 herd of models
2024 · External reference
Qwen3 technical report
2025 · External reference
Instance-dependent early stopping
2025 · External reference
Variance reduction in SGD by distributed importance sampling
2015 · External reference
Biased importance sampling for deep neural network training
2017 · External reference
Not all samples are created equal: Deep learning with importance sampling
2018 · External reference
Active bias: Training more accurate neural networks by emphasizing high variance samples
2017 · External reference
10.18653/v1/2021.naacl-main.207
10.18653/v1/2021.naacl-main.207 · External reference
Uniform convergence of rank-weighted learning
2020 · External reference
Selection via proxy: Efficient data selection for deep learning
2020 · External reference
Deep learning on a data diet: Finding important examples early in training
2021 · External reference
10.1609/aaai.v35i9.16988
10.1609/aaai.v35i9.16988 · External reference
Coverage-centric coreset selection for high pruning rates
2023 · External reference
D2 pruning: Message passing for balancing diversity and difficulty in data pruning
2024 · External reference
Data pruning by information maximization
2025 · External reference
Coresets for scalable Bayesian logistic regression
2016 · External reference
10.1109/focs.2018.00082
10.1109/focs.2018.00082 · External reference
10.1109/focs54457.2022.00051
10.1109/focs54457.2022.00051 · External reference
Moderate coreset: A universal method of data selection for real-world data-efficient deep learning
2022 · External reference
Refined coreset selection: Towards minimal coreset size under model performance constraints
2024 · External reference
Lightweight dataset pruning without full training via example difficulty and prediction uncertainty
2025 · External reference
10.1109/cvpr52733.2024.02477
10.1109/cvpr52733.2024.02477 · External reference
Accelerating deep learning with dynamic data pruning
2021 · External reference
Prioritized training on points that are learnable, worth learning, and not yet learnt
2022 · External reference
10.1109/cvprw63382.2024.00767
10.1109/cvprw63382.2024.00767 · External reference
KAKURENBO: Adaptively hiding samples in deep neural network training
2023 · External reference
Importance sampling for minibatches
2018 · External reference
Diversified batch selection for training acceleration
2024 · External reference
10.1109/iccv51701.2025.00037
10.1109/iccv51701.2025.00037 · External reference
10.18653/v1/2026.acl-long.158
10.18653/v1/2026.acl-long.158 · External reference
Grad-match: Gradient matching based data subset selection for efficient deep model training
2021 · External reference
Prioritized experience replay
2016 · External reference
Minimal effort back propagation for convolutional neural networks
2017 · External reference
10.1145/1553374.1553380
10.1145/1553374.1553380 · External reference
When do curricula work?
2021 · External reference
Curriculum learning by dynamic instance hardness
2020 · External reference
10.1109/tpami.2024.3401036
10.1109/tpami.2024.3401036 · External reference
10.26599/cai.2024.9390002
10.26599/cai.2024.9390002 · External reference
Self-paced learning for latent variable models
2010 · External reference
Curriculum learning by transfer learning: Theory and experiments with deep networks
2018 · External reference
Data parameters: A new family of parameters for learning a differentiable curriculum
2019 · External reference
Active learning literature survey
2007 · External reference
Deep Bayesian active learning with image data
2017 · External reference
Active learning for convolutional neural networks: A core-set approach
2018 · External reference
10.1109/cvpr.2019.00018
10.1109/cvpr.2019.00018 · External reference
Deep batch active learning by diverse, uncertain gradient lower bounds
2020 · External reference
Stochastic modified equations and adaptive stochastic gradient algorithms
2017 · External reference
Harnessing out-of-distribution examples via augmenting content and style
2023 · External reference
Winning prize comes from losing tickets: Improve invariant learning by exploring variant parameters for out-of-distribution generalization
2024 · External reference
Towards realistic model selection for semi-supervised learning
2023 · External reference
Improving non-transferable representation learning by harnessing content and style
2024 · External reference
Unresolved reference
2013 · External reference
Gradient descent on neural networks typically occurs at the edge of stability
2021 · External reference
10.1162/neco.1997.9.1.1
10.1162/neco.1997.9.1.1 · External reference
Towards understanding sharpness-aware minimization
2022 · External reference
10.1109/cvpr52729.2023.01552
10.1109/cvpr52729.2023.01552 · External reference
Sharp minima can generalize for deep nets
2017 · External reference
Normalized flat minima: Exploring scale invariant definition of flat minima for neural networks using PAC-Bayesian analysis
2020 · External reference
On large-batch training for deep learning: Generalization gap and sharp minima
2017 · External reference
Exploring generalization in deep learning
2017 · External reference
Learning multiple layers of features from tiny images
2009 · External reference
10.1109/cvpr.2009.5206848
10.1109/cvpr.2009.5206848 · External reference
10.1109/cvpr.2016.90
10.1109/cvpr.2016.90 · External reference
Very deep convolutional networks for large-scale image recognition
2015 · External reference
An image is worth 16x16 words: Transformers for image recognition at scale
2021 · External reference
10.1109/iccv48922.2021.00986
10.1109/iccv48922.2021.00986 · External reference
Caltech 101
2022 · External reference
When less is more: Investigating data pruning for pretraining LLMs at scale
2023 · External reference
Repeated random sampling for minimizing the time-to-accuracy of learning
2024 · External reference
Decoupled weight decay regularization
2019 · External reference
FlashAttention-2: Faster attention with better parallelism and work partitioning
2024 · External reference
ROUGE: A package for automatic evaluation of summaries
2004 · External reference
Faster R-CNN: Towards real-time object detection with region proposal networks
2015 · External reference
The PASCAL visual object classes challenge 2007 (VOC2007) results
2007 · External reference
Rethinking atrous convolution for semantic image segmentation
2017 · External reference
The PASCAL visual object classes challenge 2012 (VOC2012) Results
2012 · External reference
Large-scale celebfaces attributes (celeba) dataset
2018 · External reference
Fairlearn: A toolkit for assessing and improving fairness in AI
2020 · External reference
Robust early-learning: Hindering the memorization of noisy labels
2020 · External reference
10.1109/iccv51070.2023.01473
10.1109/iccv51070.2023.01473 · External reference
Learning with symmetric label noise: The importance of being unhinged
2015 · External reference
Part-dependent label noise: Towards instance-dependent label noise
2020 · External reference
An empirical study of example forgetting during deep neural network learning
2019 · External reference
