Stabilizes GAN training with limited data.
problem Overfitting in GANs with scarce data.
method Adaptive discriminator augmentation.
result Good results possible with few thousand images.
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.
169,051 papers · 148 categories
Trend · papers per month
48 results for “Limited Training Data”
Generative GAN improves classifier performance with limited training data.
problem Limited training data for black-box API attacks.
method Generative adversarial network (GAN) to generate synthetic training data.
result Improves classifier performance with synthetic data.
Unified method for multi-defect microscopy image restoration with limited training data.
problem Challenges in applying deep learning methods due to limited training data for multi-defect microscopy images.
method Two-stage approach: data augmentation with GAN and conditional GAN training.
result Proposed method gives comparable or superior results to existing methods in image quality restoration.
Study evaluates how limited training data affects streamflow predictions.
problem Limited historical meteorological and streamflow data affects streamflow prediction accuracy.
method Evaluated tree- and LSTM-based models on CAMELS dataset with varying training data sizes and time spans.
result Tree- and LSTM-based models provide similarly accurate predictions on small datasets, but LSTMs are superior with more training data.
Band-limited training reduces resource usage without sacrificing accuracy.
problem Resource constraints in training Convolutional Neural Networks (CNNs).
method Artificially constraining the frequency spectra of convolutional filters during training.
result CNNs can leverage lower-frequency components effectively, reducing resource usage.
Adversarially-trained models transfer better in limited data scenarios.
problem Improving transfer learning performance with limited data.
method Adversarially-train deep nets, freeze early layers, fine-tune last layers, observe shape vs texture bias.
result Adversarially-trained models transfer better than non-adversarially-trained models, especially with limited data.
Proposes a method to forecast spatial-temporal data with limited training data.
problem Forecasting with nodes having no temporal training data.
method Temporal data augmentation and spatial graph topology learning.
result Improves forecasting performance on nodes without training data.
Improved CSKS with limited data using novel loss functions and transfer learning.
problem Spotting keywords in continuous speech with limited training data.
method Combination of Prototypical networks' loss and metric loss with transfer learning.
result Improves F1 score by over 10%
Quantum SVMs outperform classical ones on limited data.
problem Classifying and regressing with limited training data.
method Trained SVMs on D-Wave quantum annealer and compared to classical SVMs.
result Quantum SVMs often generalize better to unseen data.
Study improves breast lesion segmentation with limited in vivo data using simulated and natural images.
problem Challenges in automatic breast lesion segmentation due to limited annotated data.
method Pre-training a segmentation network on simulated and natural images, followed by fine-tuning with limited in vivo data.
result Fine-tuning improves dice score by 21% with as little as 19 in vivo images.
Data selection boosts fact memorization in language models.
problem Language models struggle to accurately memorize factual knowledge.
method Formalizes fact memorization, proposes data selection schemes based on training loss.
result Data selection boosts fact accuracy to model capacity and improves performance.
Quantum machine learning generalizes well from limited data.
problem Generalization in quantum machine learning from few training data.
method Optimizing parameterized quantum circuits on training data sets and analyzing generalization error.
result Generalization error scales at worst as √(T/N) and improves to √(K/N) when only K gates change.
Out-of-Distribution Detection from Small Training Sets using Bayesian Neural Network Classifierscs.LG
Bayesian Neural Networks improve OOD detection with limited data.
problem Limited training data hinders reliable OOD detection.
method Bayesian Neural Networks with expected logit vectors.
result Bayesian methods outperform deterministic methods in small data settings.
OTS error shows small training error doesn't guarantee small test error.
problem The relationship between training and test errors is unclear.
method An analysis of the conditions under which small training set error guarantees small OTS error.
result The theorem is limited to models with distinct training and test distributions.
One of the big restrictions in brain computer interface field is the very limited training samples, it is difficult to build a reliable and usable system with such limited data. Inspired by generative adversarial networks, we propose a conditional Deep Convolutional Generative Adversarial (cDCGAN) Networks method to ge…
The paper establishes limits of transfer learning with neural networks.
problem Understanding the fundamental limits of transfer learning.
method Statistical minimax framework for regression with linear and neural network models.
result Lower bounds for target generalization error.
Machine learning has been applied to a broad range of applications and some of them are available online as application programming interfaces (APIs) with either free (trial) or paid subscriptions. In this paper, we study adversarial machine learning in the form of back-box attacks on online classifier APIs. We start w…
Theoretical study shows AI models can recover from contaminated training data.
problem Data contamination in AI training can degrade model performance.
method Theoretical analysis and experiments on various data types.
result Models converge to true distribution under mild conditions, with rate dependent on real data fraction.
Derives ideal train/test split for ridge regression in large data limit.
problem Finding optimal train/test split for ridge regression in large data scenarios.
method Mathematical derivation of optimal train/test split, considering ridge tuning parameter and asymptotic behavior.
result The optimal train/test split for ridge regression in the large data limit depends weakly on the ridge tuning parameter alpha.
Deep learning reduces artifacts in limited angle X-ray microscopy.
problem Artifacts in image reconstruction from limited angle data in TXM.
method Training a U-Net deep neural network from synthetic data to reduce artifacts.
result Significant improvement in image quality and structural similarity.
Synthetic speech data improves keyword spotting models with fewer real examples.
problem Training models for recognizing spoken keywords with limited real data.
method Used a pre-trained speech embedding model to extract features for training a small keyword spotting model.
result A model trained on synthetic speech data can detect 10 keywords with the same accuracy as a model trained on over 500 real examples.
At initialization, artificial neural networks (ANNs) are equivalent to Gaussian processes in the infinite-width limit, thus connecting them to kernel methods. We prove that the evolution of an ANN during training can also be described by a kernel: during gradient descent on the parameters of an ANN, the network functio…
A novel approach of training data augmentation and domain adaptation is presented to support machine learning applications for cognitive radio. Machine learning provides effective tools to automate cognitive radio functionalities by reliably extracting and learning intrinsic spectrum dynamics. However, there are two im…
New method models PDEs from noisy, limited data.
problem Modeling PDEs with incomplete, noisy data.
method Learned linear transformation of spatial grid points, followed by dynamics learning in a reduced basis, then back transformation.
result Rapid high-resolution simulations with smaller training data sets.
Study compares new audio representation methods for limited data music retrieval.
problem Improving machine learning for audio data with limited training data.
method Investigated mel-spectrogram and Mel scattering representations, and augmented target loss function.
result All proposed methods outperform standard mel-spectrogram when using limited data.
New research limits how well attackers can guess if data points were in a model's training set.
problem Revealing membership of data points in machine learning models.
method Theoretical analysis of statistical limits for membership inference attacks.
result The effectiveness of membership inference attacks is limited by a constant that quantifies data distribution diversity.
Paper tackles representation learning with limited labels from crowdsourced data.
problem Limited labeled data and inconsistent crowdsourced labels.
method Grouping-based deep neural network and Bayesian confidence estimator.
result Framework learns effective representations from limited data with crowdsourced labels.
Paper proposes efficient GCN learning method for limited data.
problem Learning GCNs from data with extremely limited annotations.
method Adaptive sampling strategy and model compression.
result Cut down annotation requirement by 90% and compress parameters 6x.
Recursively Trained Diffusion Models: Limiting Collapse Distribution and Spectral Characterizationstat.ML
Recursive training of generative models can lead to model collapse, and the recursion converges to a unique limiting distribution.
problem Model collapse in recursive training of generative models
method Recursive training on their own outputs
result Recursive training converges to a unique limiting distribution
We study the limits and methods of training two-layer autoencoders.
problem Understanding the limits and methods of training two-layer autoencoders.
method Focus on non-linear two-layer autoencoders trained in the proportional regime, using gradient methods.
result Gradient methods achieve the minimizers of the population risk and reveal the structure of the features.
Support Vector Data Description (SVDD) is a popular outlier detection technique which constructs a flexible description of the input data. SVDD computation time is high for large training datasets which limits its use in big-data process-monitoring applications. We propose a new iterative sampling-based method for SVDD…
New method improves ensemble diversity and generalization.
problem Ensemble diversity does not guarantee practical generalization.
method Introduced a new diversity metric and training method for extrapolating differently on local data patches.
result Improves generalization and diversity in practical settings, especially under data limits and covariate shift.
Improved audio classification with limited labels using multitask and self-supervised learning.
problem Limited labeled data for audio classification.
method Multitask learning and self-supervised learning on unlabeled data.
result Significant improvement in performance (up to 6%) through multitask and self-supervised learning.
Detects out-of-domain cases with limited training data.
problem Detecting out-of-domain cases with insufficient in-domain training data.
method Proposes an OOD-resistant Prototypical Network.
result Outperforms state-of-the-art methods in zero-shot OOD detection.
The paper analyzes the maximum margin algorithm's performance on noisy data.
problem Analyzing the performance of maximum margin algorithm on noisy data.
method Finite-sample analysis of maximum margin algorithm applied to noisy data.
result The maximum margin algorithm can achieve nearly optimal population risk with sufficient over-parameterization.
Large batch sizes improve model performance but have limits; we found a simple predictor.
problem Understanding the limits of large batch sizes across different domains.
method Empirical model using gradient noise scale to predict optimal batch size.
result Gradient noise scale predicts the largest useful batch size across various domains.
A simple GI loss improves temporal generalization without complex methods.
problem Temporal drift between train and test distributions in evolving data.
method Gradient Interpolation (GI) loss to regularize temporal complexity.
result GI loss outperforms complex methods on real-world datasets.
IST trains neural networks locally, reducing memory and communication costs.
problem Challenges in distributed learning due to mandatory data separation.
method Independent subnet training (IST) decomposes the network into narrow subnetworks.
result IST reduces training times compared to common distributed learning approaches.
The paper examines how adversarial training and noise affect neural network performance.
problem Overfitting in adversarial training and data augmentation.
method Adversarial training and data augmentation with noise in the context of regularized regression in RKHS.
result Appropriate regularization can prevent overfitting and improve performance.
This work improves medical image segmentation with limited annotations using contrastive learning.
problem Lack of labeled data for medical image segmentation.
method Contrastive learning framework for semi-supervised segmentation with domain-specific and problem-specific cues.
result Significant improvements in segmentation performance compared to other methods.
New MIP methods improve training of integer-valued neural networks.
problem Training integer-valued neural networks with limited data and resources.
method Formulated new MIP models to optimize training efficiency and handle more data.
result Significantly outperforms previous state-of-the-art methods in accuracy, training time, and data usage.
New research shows label refinement and weak training have limitations for aligning LLMs.
problem Limitations of refinement methods for aligning large language models.
method Analyzed probabilistic assumptions and alternative approaches to label refinement and weak training.
result Label refinement and weak training suffer from irreducible error, leaving a performance gap.
Gradient descent dynamics in wide neural networks are analyzed using a dynamical CLT.
problem Understanding the fluctuations in wide shallow neural networks trained via gradient descent.
method Dynamical Central Limit Theorem (CLT) applied to neural network dynamics.
result Asymptotic fluctuations remain bounded in mean square throughout training.
New technique improves time series forecasting with less data.
problem Challenges in time series forecasting with limited data.
method Random sampling of non-consecutive time steps to increase training samples and capture finer temporal dependencies.
result Competitive results achieved compared to state-of-the-art on real-world datasets.
Neural networks trained with Q-learning converge to optimal control.
problem Optimal control of reinforcement learning with neural networks.
method Analysis of a limit differential equation derived from Q-learning.
result The limit differential equation has a unique stationary solution that is optimal.
SynthER uses generative models to augment limited RL experience.
problem Limited data for reinforcement learning agents.
method SynthER leverages diffusion models to generate synthetic experience data.
result SynthER significantly improves sample efficiency and training of RL agents.
Paper detects Trojan neural networks with limited or no data.
problem Robustness of DNNs against Trojan attacks in data-scarce scenarios.
method Proposes data-limited and data-free TrojanNet detectors.
result Demonstrates effectiveness of detectors on various datasets.
Recurrent neural networks (RNNs), particularly long short-term memory (LSTM), have gained much attention in automatic speech recognition (ASR). Although some successful stories have been reported, training RNNs remains highly challenging, especially with limited training data. Recent research found that a well-trained …