He et al. (2018) have called into question the utility of pre-training by showing that training from scratch can often yield similar performance to pre-training. We show that although pre-training may not improve performance on traditional classification metrics, it improves model robustness and uncertainty estimates. …
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,982 papers · 148 categories
Trend · papers per month
48 results for “improve training”
Paper improves adversarial training using a learned optimizer.
problem Improving robustness of deep learning models against adversarial attacks.
method Empirically identified PGD attack's limitations and used a learning-to-learn framework to train an adaptive inner optimizer.
result The proposed framework consistently improves model robustness over traditional adversarial training methods.
CAT improves robustness of neural networks by customizing perturbation levels.
problem Poor generalization of adversarial training on clean and perturbed data.
method CAT adapts perturbation level and label for each sample.
result CAT achieves better clean and robust accuracy than previous methods.
TuneUp improves GNN training by focusing on hard-to-learn nodes.
problem Sub-optimal training of GNNs on all nodes equally.
method Two-stage training: base GNN + tail node improvement.
result Significant improvement in tail node prediction performance.
New sampling method improves model training speed and robustness.
problem Improving model training speed and robustness.
method Periodic sampling of model weights for gradient optimization methods.
result Better, faster, and more robust convergence with minimal computation time.
MLPerf benchmarks ML training to drive performance improvements.
problem Unique challenges in ML training benchmarks.
method Developed MLPerf to overcome ML training's specific challenges.
result Quantitatively evaluated MLPerf's effectiveness.
Self-training outperforms pre-training on COCO object detection and segmentation datasets.
problem The effectiveness of pre-training in improving object detection and segmentation models is limited.
method Investigated self-training as an alternative method to utilize additional data.
result Self-training consistently improves model performance across various dataset sizes and data augmentation levels.
FIRE PBT improves neural network training by focusing on long-term performance.
problem Greedy decision mechanisms in PBT lead to poor long-term performance.
method FIRE PBT uses a fitness metric to encourage long-term performance over short-term improvements.
result FIRE PBT outperforms PBT on ImageNet and matches hand-tuned learning rates.
Adaptive networks improve model robustness through conditional normalization.
problem Limited robustness of adversarial-trained networks due to network capacity and training samples.
method Proposes a conditional normalization module to adapt networks during adversarial training.
result Adaptive networks outperform both clean validation accuracy and robustness compared to non-adaptive counterparts.
We improve private training accuracy with learning rate schedules and matrix factorizations.
problem Private training with learning rate schedules and correlated noise.
method General upper and lower bounds for learning rate schedules, memory-efficient constructions, and schedule-aware factorizations.
result Schedule-aware factorizations improve accuracy in private training.
Improved GAN training stability through clipping and reweighting.
problem Inconsistent GAN training leading to inferior performance.
method Proposes a variational GAN framework with probability ratio clipping and sample reweighting.
result Significantly improved performance across various GAN tasks.
Improves neural network performance by enriching training dataset.
problem Achieving worst-case performance guarantees in neural networks.
method Adapting training dataset during training to reduce worst-case violations.
result Improved worst-case performance guarantees in neural networks.
Training on mixed distributions improves test performance even when components are unrelated.
problem Improving test performance with mismatched training and test distributions.
method Analyzing mixture distributions with different training and test proportions.
result Distribution shift can be beneficial, improving test performance even when components are unrelated.
Improved neural network robustness with instance-specific perturbation margins.
problem Adversarial training fails to generalize well to unperturbed test set.
method Instance adaptive adversarial training with sample-specific perturbation margins.
result Test accuracy improves with a marginal drop in robustness.
Pruning improves model generalization in over-parameterized models, contradicting traditional theories.
problem Pruning's effect on generalization in over-parameterized models.
method Empirical study on standard pruning algorithms and additional regularization effects.
result Pruning leads to better training and regularization, improving generalization.
Retraining with predicted labels improves model accuracy in noisy settings.
problem Improving model accuracy with noisy or corrupted labels.
method Retraining with predicted hard labels in a linearly separable binary classification setting.
result Retraining with predicted labels can increase model accuracy, as proven theoretically.
Generative models improve adversarial robustness by adding synthetic data.
problem Improving robustness in machine learning models trained on limited data.
method Using synthetic data generated from a large dataset to augment the original training set.
result Generative models can significantly reduce the robust-accuracy gap compared to models trained with additional real data.
New method improves adversarial robustness without extra training steps.
problem Improving robustness of deep learning models against adversarial attacks.
method Guided Complement Entropy (GCE) training paradigm.
result GCE achieves better adversarial robustness with improved performance.
SPAT improves adversarial robustness by preserving semantics in adversarial training.
problem Adversarial examples often have different semantics than original data, introducing unintended biases.
method Semantics-preserving adversarial training (SPAT) that encourages pixel perturbation shared among all classes.
result SPAT improves adversarial robustness and achieves state-of-the-art results in CIFAR-10 and CIFAR-100.
Fine-tuning with pre-training data improves performance.
problem Limited training data for tasks.
method Theoretical analysis of excess risk bound and selection of pre-training data subset.
result Improvement in generalization performance with pre-training data.
New method improves adversarial training efficiency and robustness.
problem High computational costs and lack of stability in adversarial training.
method Backward smoothing for randomized smoothing of random initialization.
result Our method achieves similar model robustness as state-of-the-art methods but with significantly less training time.
Federated learning is a distributed form of machine learning where both the training data and model training are decentralized. In this paper, we use federated learning in a commercial, global-scale setting to train, evaluate and deploy a model to improve virtual keyboard search suggestion quality without direct access…
Improved GAN training speed and quality with FastGAN.
problem Slower convergence and less expressive models in GAN training.
method Adversarial training with FastGAN algorithm.
result Better generation quality with less training time.
Post-training corrections boost time-series forecasting accuracy.
problem Improving forecasting accuracy of large models after training.
method Sequential application of carefully selected corrections to predictions.
result Up to 30% improvement in forecasting accuracy with minimal overhead.
Improved pre-trained embeddings through effective entropy maximization.
problem Developing high-quality pre-trained embeddings for future tasks.
method E2MC criterion defined in terms of low-dimensional constraints.
result Significant improvement in downstream performance.
New strategy improves GNN pre-training for graph datasets.
problem Effective pre-training for graph neural networks on graph datasets.
method Expressive pre-training of GNNs at both node and graph levels.
result Significant improvement in generalization across downstream tasks.
Meta-learning improves DNN generalization on standard supervised learning.
problem Improving deep neural networks' generalization without adding more parameters.
method MLTP simulates meta-training by considering a batch of samples as a task, optimizing for both current and new tasks.
result MLTP consistently improves DNN generalization across various sizes and datasets.
AGMMNs improve learning of copula models by adaptively selecting kernels.
problem Learning dependence structures in copula models.
method Adaptive bandwidth selection for MMD in GMMNs, increasing kernels based on validation loss.
result AGMMNs significantly improve training performance over GMMNs and parametric models.
Improved image classifier performance with faster training using adaptive learning rates.
problem Lower accuracy and training time in small datasets.
method Dynamic learning rate tuning for different model architectures.
result Two-fold to ten-fold speedup in accuracy over state-of-the-art methods.
Improves sample quality of generative models using energy-based methods.
problem Low sample quality in generative models.
method Constructs an energy function on latent space, trains an energy-based model, and generates improved samples.
result Significant improvement in sample quality with minimal computational overhead.
We simplify diffusion models by defining a design space and improving FID scores.
problem Complexity in diffusion-based generative models.
method Defined a design space, improved sampling and training processes, and pre-conditioned score networks.
result Improved FID scores of 1.79 for CIFAR-10 and 1.97 for unconditional settings.
Cost-effective method improves and re-purposes pre-trained GANs by fine-tuning class-embeddings.
problem Fine-tuning BigGANs from scratch is impractical due to instability and high computational cost.
method Fine-tuning only the class-embedding layer of pre-trained GANs.
result Significantly improved realism and diversity of samples, re-purposed for new tasks, and de-biased or improved diversity.
Ensemble models improve prediction calibration for mismatched distributions.
problem Calibration issues in deep neural networks with mismatched train and test distributions.
method Simple data augmentation and mixing techniques for ensemble models.
result Improves calibration and accuracy on CIFAR10 and CIFAR100 benchmarks.
Improves model performance with unlabeled test data.
problem Improving model robustness to distribution shifts.
method Self-supervised learning using a single unlabeled test sample.
result Improves performance on diverse image classification benchmarks.
Adversarial training improves robustness against common corruptions.
problem Improving robustness of models against common corruptions.
method Adversarial training with perturbation and learned perceptual similarity.
result Our approach leads to state-of-the-art performance on common corruptions.
LOGAN optimizes GAN training by improving adversarial dynamics.
problem Training GANs is challenging due to delicate adversarial dynamics and potential divergence.
method Integrates natural gradient-based latent optimisation into CS-GAN.
result Significant improvement in GAN training performance, achieving state-of-the-art results.
Joint training improves model accuracy by selectively using privileged information.
problem Two-stage training can lead to model failure with noisy privileged information.
method Joint training of two models to use privileged information selectively.
result Joint training outperforms two-stage baselines on synthetic and real-world tasks.
Improved disentanglement of data factors using recursive training.
problem Current unsupervised disentanglement methods are inconsistent and fail to achieve levels of disentanglement seen in supervised approaches.
method Introduced PBT for VAEs, used UDR for heuristic scoring, and developed recursive rPU-VAE approach.
result Recursive training leads to robust disentanglement of data factors across multiple datasets.
Nonlinear conjugate gradient (NLCG) based optimizers have shown superior loss convergence properties compared to gradient descent based optimizers for traditional optimization problems. However, in Deep Neural Network (DNN) training, the dominant optimization algorithm of choice is still Stochastic Gradient Descent (SG…
SMART training improves mask-predict translations.
problem Closing the performance gap between semi-autoregressive and autoregressive models.
method SMART training method for conditional masked language models.
result SMART-trained models produce higher-quality translations.
New method improves ensemble quality by exploring the pre-train basin more effectively.
problem Limited diversity in ensembles trained from a single pre-trained checkpoint.
method Proposed StarSSE modification of Snapshot Ensembles for transfer learning.
result Stronger ensembles and uniform model soups achieved.
Paper proposes a classifier to improve medical image classification with limited data.
problem Limited training data leads to overfitting in medical image classification.
method Uses reinforcement learning to update classifier parameters with generalization feedback from a subset of training data.
result Improves classification performance and demonstrates generalized learning.
Mixed-size training improves CNN accuracy and speed.
problem Training CNNs on fixed image sizes limits their adaptability to various image sizes.
method Mixed-size training: training on multiple image sizes at once.
result Models trained with mixed-size images achieve higher accuracy and faster inference.
Improved sample complexity for training diffusion models.
problem How many samples are needed to train an accurate diffusion model?
method Analyzing the sample complexity of training diffusion models using neural networks.
result Exponential improvement in the dependence on Wasserstein error and depth, along with improved dependencies on other parameters.
End-to-end method improves neural network calibration during training.
problem Improving neural network calibration for regression problems.
method Quantile Recalibration Training integrates post-hoc calibration into model training.
result Improved predictive accuracy and calibration in a large-scale experiment.
In this paper we introduce Curriculum GANs, a curriculum learning strategy for training Generative Adversarial Networks that increases the strength of the discriminator over the course of training, thereby making the learning task progressively more difficult for the generator. We demonstrate that this strategy is key …
Improved online AED models with multi-stage training and multi-task learning.
problem Enhance performance of online attention-based encoder-decoder models.
method Three-stage training with character encoder, BPE encoder, and attention decoder; multi-task learning at character and BPE levels; transfer learning from bidirectional encoder.
result 35% and 10% relative improvement over baselines for smaller and bigger models, respectively.
This paper improves volatility forecasting using dynamic subset selection in genetic programming.
problem Improving accuracy of implied volatility forecasting.
method Dynamic training-subset selection methods applied to genetic programming.
result Dynamic subset selection improves predictive accuracy of genetic programming models.