Large-batch SGD is important for scaling training of deep neural networks. However, without fine-tuning hyperparameter schedules, the generalization of the model may be hampered. We propose to use batch augmentation: replicating instances of samples within the same batch with different data augmentations. Batch augment…
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.
168,695 papers · 148 categories
Trend · papers per month
48 results for “batch augmentation”
Online data augmentation improves forecasting performance in deep learning.
problem Insufficient training data for forecasting tasks.
method An online data augmentation framework that generates synthetic samples during training.
result Online data augmentation leads to better forecasting performance.
SBA improves neural network generalization by dynamically augmenting data.
problem Lack of direct supervision in data augmentation for generalization.
method Stochastic Batch Augmentation with dynamic soft label regularization.
result SBA improves generalization and speeds up training.
BYOL learns useful representations without batch statistics.
problem BYOL's reliance on batch statistics for representation learning.
method Training BYOL without batch normalization and using alternative normalization schemes.
result BYOL performance comparable to vanilla BYOL without batch normalization.
A new framework reduces traffic congestion by 36%.
problem Efficient traffic signal control in a metropolitan area.
method Two-stage framework combining Evolution Strategies and multi-agent reinforcement learning.
result Reduces traffic congestion by 36%.
Study examines how data augmentation impacts optimization in linear regression.
problem Understanding how data augmentation schedules affect optimization in linear regression.
method Analyzed the effect of augmentation on optimization in linear regression with MSE loss, using classical convex optimization and recent work on implicit bias.
result Proved that under certain joint schedules for learning rate and augmentation scheme, augmented gradient descent converges and characterized the resulting minimum.
Paper analyzes gradient descent with noisy data copies for linear regression, showing regularization and acceleration effects.
problem Improving generalization in machine learning through data augmentation with noise.
method Gradient descent with on-line noisy copies for linear regression analysis.
result Training with on-line noisy copies is equivalent to ridge regularization with a specific regularization parameter.
With the large rising of complex data, the nonconvex models such as nonconvex loss function and nonconvex regularizer are widely used in machine learning and pattern recognition. In this paper, we propose a class of mini-batch stochastic ADMMs (alternating direction method of multipliers) for solving large-scale noncon…
Attention augments forest for tabular data accuracy.
problem Training tabular data models with high accuracy and efficiency.
method Tree Attention Block (TAB) in differentiable forest framework.
result Attention augmented differentiable forest achieves comparable and sometimes higher accuracy than GBDT models.
The paper proposes an iterative approach to batch reinforcement learning for safer and more informative data collection.
problem Learning policies that are too rigid and do not adapt to new data.
method Safe diversified model-based policy search in an iterative batch reinforcement learning framework.
result Improved learned policies through continuous data collection and adaptation.
A novel approach learns goal-conditioned policies for locomotion using batch RL.
problem Training goal-conditioned policies for rotation invariant locomotion.
method Data augmentation and Siamese framework for invariance.
result Our approach outperforms existing RL algorithms on 3D locomotion agents.
i-Mix improves contrastive learning across domains without domain-specific augmentations.
problem Improving contrastive representation learning for unlabeled data across diverse domains.
method i-Mix treats contrastive learning as a non-parametric classifier problem, mixing data in input and virtual label spaces.
result i-Mix consistently improves representation quality across image, speech, and tabular data domains.
New method trains deep ResNets without normalization, achieving state-of-the-art performance.
problem Training deep ResNets without normalization layers leads to instability and lower accuracy.
method Adaptive gradient clipping and Normalizer-Free ResNets design.
result Normalizer-Free ResNets achieve 86.5% top-1 accuracy on ImageNet, matching EfficientNet-B7.
Poly-view contrastive learning improves image representation learning.
problem Learning representations from multiple related views in image data.
method Developed new representation learning objectives for poly-view tasks using information maximization and sufficient statistics.
result Poly-view contrastive models trained for fewer epochs and with smaller batch sizes outperform models trained for more epochs and with larger batch sizes.
We propose sequenced-replacement sampling (SRS) for training deep neural networks. The basic idea is to assign a fixed sequence index to each sample in the dataset. Once a mini-batch is randomly drawn in each training iteration, we refill the original dataset by successively adding samples according to their sequence i…
CoDA augments data with counterfactuals from local causal structures.
problem Improving sample efficiency in RL with complex dynamic processes.
method Local causal models (LCMs) and Counterfactual Data Augmentation (CoDA).
result CoDA significantly improves RL agent performance in locally factored tasks.
FSGD uses latent factors to scale SGD for high-dimensional learning.
problem Scalable optimization in high-dimensional machine learning.
method Factor-Augmented SGD (FSGD) that operates on streaming data.
result Established theoretical framework for latent factor estimation error in SGD.
Self-augmentation improves deep networks for few-shot learning with minimal training data.
problem Improving deep networks' generalization to unseen classes with limited training examples.
method Self-augmentation using self-mix and self-distillation techniques, combined with regional dropout and local representation learning.
result The method outperforms state-of-the-art few-shot learning methods on prevalent benchmarks.
Data augmentation is an effective technique for improving the accuracy of modern image classifiers. However, current data augmentation implementations are manually designed. In this paper, we describe a simple procedure called AutoAugment to automatically search for improved data augmentation policies. In our implement…
We outline new approaches to incorporate ideas from deep learning into wave-based least-squares imaging. The aim, and main contribution of this work, is the combination of handcrafted constraints with deep convolutional neural networks, as a way to harness their remarkable ease of generating natural images. The mathema…
Structured subsampling improves privacy in deep time series forecasting.
problem Incompatible privacy guarantees with time series forecasting.
method Structured subsampling of sequential data for privacy amplification.
result Structured subsampling enables training with strong privacy guarantees.
Online reinforcement learning agents are currently able to process an increasing amount of data by converting it into a higher order value functions. This expansion of the information collected from the environment increases the agent's state space enabling it to scale up to a more complex problems but also increases t…
Prediction-time batch normalization improves model robustness under covariate shift.
problem Dealing with covariate shift in deep learning models.
method Prediction-time batch normalization, a simple but effective method.
result Significantly improves model accuracy and calibration under covariate shift.
Data augmentation is essential for medical research to increase the size of training datasets and achieve better results. In this work, we experiment three GAN architectures with different loss functions to generate new brain MRIs. The results show the importance of hyperparameter tuning and the use of mini-batch simil…
cMIM improves representation learning without positive-pair augmentations.
problem Learning robust representations for diverse tasks.
method Contrastive Mutual Information Machine (cMIM) framework.
result cMIM outperforms MIM and InfoNCE on classification and regression tasks.
This paper uses GANs to generate synthetic Bitcoin address data.
problem Class imbalance in Bitcoin ground-truth datasets affects supervised machine learning results.
method Generative Adversarial Networks (GANs) for synthetic data generation.
result A 'good' GAN configuration can be found to generate synthetic Bitcoin address data with high similarity to real data.
Overfitting frequently occurs in deep learning. In this paper, we propose a novel regularization method called Drop-Activation to reduce overfitting and improve generalization. The key idea is to drop nonlinear activation functions by setting them to be identity functions randomly during training time. During testing, …
A DenseNet model classifies metastatic cancer in medical images.
problem Classifying metastatic cancer in medical images efficiently and accurately.
method Proposes a DenseNet-based model for metastatic cancer classification on medical images.
result The proposed model outperformed other classical methods like Resnet34, Vgg19.
Paper proposes a new method for efficient hyperparameter optimization.
problem Challenging task of optimizing hyperparameters in machine learning.
method Sequential Uniform Design (SeqUD) strategy for adaptive and efficient exploration of hyperparameter space.
result The proposed SeqUD strategy outperforms existing methods in hyperparameter optimization.
Subset pretraining speeds up neural network training.
problem Efficiently training neural networks with partial gradients.
method Use small subsets to approximate the loss minimum of the full training set.
result Subset minima can approximate the full training set's loss minimum efficiently.
In this paper, we investigate the problem of overfitting in deep reinforcement learning. Among the most common benchmarks in RL, it is customary to use the same environments for both training and testing. This practice offers relatively little insight into an agent's ability to generalize. We address this issue by usin…
Improving generalization is one of the main challenges for training deep neural networks on classification tasks. In particular, a number of techniques have been proposed, aiming to boost the performance on unseen data: from standard data augmentation techniques to the regularization, dropout, batch normalizat…
Augmenting a neural network with memory that can grow without growing the number of trained parameters is a recent powerful concept with many exciting applications. We propose a design of memory augmented neural networks (MANNs) called Labeled Memory Networks (LMNs) suited for tasks requiring online adaptation in class…
New algorithms improve estimation of treatment effects.
problem Estimating Average Treatment Effect (ATE) in adaptive settings.
method Optimistic algorithms for adaptive estimation using AIPW estimator.
result Significant theoretical and empirical gains over prior methods.
Bayesian methods promise to fix many shortcomings of deep learning, but they are impractical and rarely match the performance of standard methods, let alone improve them. In this paper, we demonstrate practical training of deep networks with natural-gradient variational inference. By applying techniques such as batch n…
G-SimCLR improves unsupervised learning by clustering images into pseudo labels.
problem Improving unsupervised learning for image recognition.
method Proposes a method to cluster images into pseudo labels to batch images of the same category.
result Comparable performance enhancements on CIFAR10 and ImageNet datasets.
New method improves neural network generalization and robustness.
problem Improving neural network generalization and robustness to input perturbations.
method Co-Mixup with supermodular diversity, optimizing data saliency and diversity.
result Achieves state-of-the-art generalization, calibration, and localization results.
Ensembling DNNs improves minority group performance, leading to fairness.
problem Improving subgroup performances in DNN classifiers.
method Simple homogeneous ensembling of DNNs.
result Fairness naturally emerges from ensembling, improving minority group performance.
Mean Shift Rejection: Training Deep Neural Networks Without Minibatch Statistics or Normalizationcs.LG
Deep convolutional neural networks are known to be unstable during training at high learning rate unless normalization techniques are employed. Normalizing weights or activations allows the use of higher learning rates, resulting in faster convergence and higher test accuracy. Batch normalization requires minibatch sta…
New framework PBBO optimizes latent functions with preferential feedback.
problem Optimizing latent functions with parallel preferential feedback.
method Gaussian process model with a likelihood for parallel comparisons.
result Framework PBBO generalizes and expands Bayesian optimization.
This paper introduces 'General Cyclical Training' for neural networks.
problem Improving training efficiency and performance of neural networks.
method Cyclical training phases with varying hyperparameters, batch sizes, loss functions, and data augmentation.
result Cyclical weight decay, softmax temperature, and gradient clipping enhance model accuracy.
Supervised contrastive learning improves image classification accuracy.
problem Improving image classification accuracy using supervised contrastive learning.
method Extending self-supervised batch contrastive approach to fully-supervised setting, leveraging label information.
result Top-1 accuracy of 81.4% on ImageNet dataset, outperforming cross-entropy.
We propose a predictive neural network architecture that can be utilized to update reference velocity models as inputs to the full waveform inversion. Deep learning models are explored to augment velocity model building workflows during processing the 3D seismic volume in salt-prone environments. Specifically, a neural…
We propose regularizing the empirical loss for semi-supervised learning by acting on both the input (data) space, and the weight (parameter) space. We show that the two are not equivalent, and in fact are complementary, one affecting the minimality of the resulting representation, the other insensitivity to nuisance va…
Proposes a method to learn conditional VAEs from datasets with missing covariates.
problem Learning conditional VAEs from datasets with missing covariates.
method Augments conditional VAEs with a prior distribution for missing covariates and estimates their posterior using amortised variational inference.
result The proposed method outperforms previous methods in learning conditional VAEs from non-temporal, temporal, and longitudinal datasets.
New research shows many batch selection methods for training work just as well as full batch training.
problem Finding optimal batch selection methods for training.
method Analysis of mini-batch Gradient Descent (GD) and Stochastic GD (SGD) with various batch selection rules.
result All mini-batch schedules, including deterministic ones, generalize optimally for smooth Lipschitz-convex/nonconvex/strongly-convex loss functions.
Determining the appropriate batch size for mini-batch gradient descent is always time consuming as it often relies on grid search. This paper considers a resizable mini-batch gradient descent (RMGD) algorithm based on a multi-armed bandit for achieving best performance in grid search by selecting an appropriate batch s…
Bayesian neural networks show complex posterior distributions that HMC can capture effectively.
problem Understanding and approximating the high-dimensional, non-convex posterior of Bayesian neural networks.
method Full-batch Hamiltonian Monte Carlo (HMC) on modern architectures.
result HMC provides a robust and comparable representation of the BNN posterior, with significant performance gains over standard training and deep ensembles.