arXiv research

PiNGDA learns beneficial noise for graph augmentation stability.

SapAugment learns adaptive augmentation policies for better model training.

PANDA augments data to regularize GLM estimation and inference.

Enhanced financial forecasting using supervised autoencoders with noise augmentation and triple labeling.

We propose an AdaPtive Noise Augmentation (PANDA) technique to regularize the estimation and construction of undirected graphical models. PANDA iteratively optimizes the objective function given the noise augmented data until convergence to achieve regularization on model parameters. The augmented noises can be designe…

Dropout is typically interpreted as bagging a large number of models sharing parameters. We show that using dropout in a network can also be interpreted as a kind of data augmentation in the input space without domain knowledge. We present an approach to projecting the dropout noise within a network back into the input…

Theoretical framework for data augmentation in finance improves portfolio construction.

The ability to detect sparse signals from noisy high-dimensional data is a top priority in modern science and engineering. A sparse solution of the linear system $A ρ= b_0$ can be found efficiently with an $l_1$-norm minimization approach if the data is noiseless. Detection of the signal's support from data corrupted b…

Deploying machine learning systems in the real world requires both high accuracy on clean data and robustness to naturally occurring corruptions. While architectural advances have led to improved accuracy, building robust models remains challenging. Prior work has argued that there is an inherent trade-off between robu…

The paper examines how adversarial training and noise affect neural network performance.

CutMix enhances feature learning in neural networks, improving test accuracy.

Diffusion models optimize objectives similar to ELBO with Gaussian noise augmentation.

Large datasets often have unreliable labels-such as those obtained from Amazon's Mechanical Turk or social media platforms-and classifiers trained on mislabeled datasets often exhibit poor performance. We present a simple, effective technique for accounting for label noise when training deep neural networks. We augment…

Introduces data augmentation for graph convolutional networks, proposing Monte Carlo Graph Learning.

AugBagg improves random forest accuracy with added noise variables.

NA$_0$CT$^2$ improves tensor regression predictions with $\ell_0$ regularization.

Researchers use human-in-the-loop to create counterfactually augmented data, improving model performance.

NAPP-ERM improves ERM with differential privacy guarantees by iteratively achieving target regularization and delivering strong convexity.

DACL tackles domain-specific contrastive learning by using Mixup noise.

AugLoss combines data augmentation and robust loss functions for robust DL models.

Study examines how data augmentation impacts optimization in linear regression.

Real-time speech enhancement model removes various noises and reverb.

Transfer learning and data augmentation improve stock classification performance.

Novel bio-inspired masking for robust speech emotion recognition.

Optimistic RL algorithms are simplified for deep RL with competitive performance.

This paper explores the use of adversarial examples in training speech recognition systems to increase robustness of deep neural network acoustic models. During training, the fast gradient sign method is used to generate adversarial examples augmenting the original training data. Different from conventional data augmen…

Semi-supervised learning lately has shown much promise in improving deep learning models when labeled data is scarce. Common among recent approaches is the use of consistency training on a large amount of unlabeled data to constrain model predictions to be invariant to input noise. In this work, we present a new perspe…

The paper provides theoretical guarantees for behavior cloning using generative models.

This paper improves generative models by using data scaling and theoretical analysis.

Cross-regularization adapts model complexity during training.

Bayesian classification improves with explicit aleatoric uncertainty.

Heavy Lasso improves robustness in high-dimensional linear regression with heavy-tailed errors.

Improves fault detection models in noisy data.

Recently, deep models have had considerable success in several tasks, especially with low-level representations. However, effective learning from sparse noisy samples is a major challenge in most deep models, especially in domains with structured representations. Inspired by the proven success of human guided machine l…

Unified theory explains how data augmentation improves deep learning models.

Noisy Feature Mixup improves model robustness with noise-perturbed convex combinations.

Enhances robustness of AT frameworks to multiple perturbations without increasing training complexity.

Model classifies hand gestures with low EMG samples augmented with noise.

We propose regularization strategies for learning discriminative models that are robust to in-class variations of the input data. We use the Wasserstein-2 geometry to capture semantically meaningful neighborhoods in the space of images, and define a corresponding input-dependent additive noise data augmentation model. …

Synthetic augmentation improves financial machine learning performance in variance-dominant regimes.

Achieving robustness to distributional shift is a longstanding and challenging goal of computer vision. Data augmentation is a commonly used approach for improving robustness, however robustness gains are typically not uniform across corruption types. Indeed increasing performance in the presence of random noise is oft…

Graph neural networks (GNNs) are an emerging model for learning graph embeddings and making predictions on graph structured data. However, robustness of graph neural networks is not yet well-understood. In this work, we focus on node structural identity predictions, where a representative GNN model is able to achieve n…

Ensemble learning is a standard approach to building machine learning systems that capture complex phenomena in real-world data. An important aspect of these systems is the complete and valid quantification of model uncertainty. We introduce a Bayesian nonparametric ensemble (BNE) approach that augments an existing ens…

A new hybrid framework reduces quantum runtime and noise effects.

Enhanced financial forecasting with supervised autoencoders for S&P 500 and cryptocurrencies.

Boomerang generates nonidentical images similar to input on image manifolds.

Framework adds invariance to pretrained networks without fine-tuning.

Data augmentation (DA) is commonly used during model training, as it significantly improves test error and model robustness. DA artificially expands the training set by applying random noise, rotations, crops, or even adversarial perturbations to the input data. Although DA is widely used, its capacity to provably impr…