Meta-learning helps use small data from many tasks to compensate for lack of big data.
problem How to leverage small labeled data from many tasks to improve learning when big labeled data is scarce.
method Introduced a novel spectral approach to efficiently utilize small data tasks with the help of medium data tasks.
result The total number of examples necessary with only small data tasks scales similarly as when big data tasks are available.
Method predicts spatial values with few data using GP framework.
problem Few data limit predictive performance in spatial regression.
method Trains neural network to infer task representation from small data, uses GP framework to predict spatial values.
result Proposed method achieves better predictive performance than meta-learning methods.
In this paper, we confront the problem of deep learning's big labeled data requirements, offer a rule based strategy for extreme augmentation of small data sets and apply that strategy with the image to image translation model by Isola et al. (2016) to automate cel style cartoon coloring with very limited training data…
The Era of Big Data has forced researchers to explore new distributed solutions for building fuzzy classifiers, which often introduce approximation errors or make strong assumptions to reduce computational and memory requirements. As a result, Big Data classifiers might be expected to be inferior to those designed for …
Improves probability estimates for small datasets in multi-class problems.
problem Inaccurate probability estimates in classification tasks, especially on small datasets.
method Introduced Data Generation and Grouping algorithm to improve calibration on small datasets, then applied to multi-class problems.
result Calibration error can be decreased using the proposed approach.
Infinitely wide neural nets perform well on small datasets.
problem Performing well on small datasets with limited training samples.
method Using Neural Tangent Kernels (NTKs) for kernel regression.
result NTK SVM outperforms Random Forests and Convolutional NTK on CIFAR-10 with 10-640 training samples.
Fragment-based autoencoder improves molecule screening with little data.
problem Limited experimental data for molecular optimization.
method Fragment-based graphical autoencoding to generate structural fingerprints.
result Fragment-based autoencoding reduces prediction error in small data.
Paper tackles object detection in limited data scenarios.
problem Limited annotated data for object detection.
method Generative modeling with a novel unrolling mechanism to optimize both generation and detection.
result Improves object detection performance on NIH Chest X-ray dataset by 20%.
GOAL algorithm reduces and rotates feature space for small data classification.
problem Challenges in identifying important features for classification in small data settings.
method GOAL algorithm reduces and rotates feature space in a lower-dimensional gauge, providing an analytically tractable solution.
result GOAL algorithm outperforms state-of-the-art ML tools in synthetic and real-world applications.
A new meta-meta classification method tackles few-shot learning tasks.
problem Learning with limited data in small-data settings.
method Designing an ensemble of learners for a large set of problems, then learning how to combine them for a new problem.
result Meta-meta classification outperforms traditional meta-learning and ensembling approaches in one-shot learning tasks.
VAE improves semi-supervised learning in small data.
problem Limited data in biological samples.
method Applied VAE to capture features in a lower-dimension.
result Improved performance in semi-supervised learning.
A robust approach compensates for small-data tasks in mixed linear regression.
problem Learning from small batches of data in tasks with many similar but insufficiently labeled examples.
method Spectral approach combining outlier-robust PCA and sum-of-squares algorithms.
result The approach achieves a graceful statistical trade-off, allowing smaller tasks than previously required.
Paper introduces a method to infer causal direction from limited data.
problem Inference of causal direction from limited observational data.
method Meta learning combined with causal inference to create a generative model.
result The method accurately infers causal direction across various dataset sizes.
Model learns to select relevant clinical variables for disease subtype prediction from small data.
problem Few-shot disease subtype prediction from small genomic data.
method Meta learning Prototypical Network with feature selection and sample reweighting.
result Superior performance in predicting disease subtypes and identifying genes.
Bayesian methods reduce variance in subspace identification for small data sets.
problem High variance in traditional subspace identification methods for large models or small sample sizes.
method Investigation of Bayesian estimation solutions (regularized and shrinkage estimators) for subspace identification.
result Bayesian estimators reduce estimation risk by up to 40% compared to traditional methods.
Learning from small data sets is critical in many practical applications where data collection is time consuming or expensive, e.g., robotics, animal experiments or drug design. Meta learning is one way to increase the data efficiency of learning algorithms by generalizing learned concepts from a set of training tasks …
New regularization method corrects over-shrinkage in small data regression.
problem Over-shrinkage in small data regression leading to underfitting.
method Negative-capable ridge family that permits negative regularization.
result Negative regularization acts as controlled anti-shrinkage, increasing effective complexity.
Physics-enhanced NNs improve predictive accuracy in small data scenarios.
problem Predicting physical systems dynamics with limited data.
method Integrating physical principles (Hamiltonian/Lagrangian) and regularization term based on energy level into neural networks.
result Significant gains in predictive accuracy for small data cases.
Deep kernels learn from embeddings to capture data similarity efficiently.
problem Capturing similarity between high-dimensional data points with small labeled data.
method Probabilistic neural network to learn deep kernels on probabilistic embeddings.
result Our approach outperforms state-of-the-art GP kernel learning in various settings.
The automated construction of coarse-grained models represents a pivotal component in computer simulation of physical systems and is a key enabler in various analysis and design tasks related to uncertainty quantification. Pertinent methods are severely inhibited by the high-dimension of the parametric input and the li…
The paper explores how smaller data sets can lead to better model selection decisions.
problem Model selection in small data regimes.
method Empirical study of generalization performance with varying training set sizes.
result Training on smaller subsets of data can lead to more reliable model selection decisions.
SmallML predicts customer churn for SMEs with small data, improving accuracy by 24.2 points.
problem AI exclusion of SMEs due to data scale mismatch.
method Bayesian transfer learning with hierarchical pooling and conformal prediction.
result 96.7% AUC on 100 obs SMEs, 24.2 point improvement over logistic regression.
Scaling clustering algorithms to massive data sets is a challenging task. Recently, several successful approaches based on data summarization methods, such as coresets and sketches, were proposed. While these techniques provide provably good and small summaries, they are inherently problem dependent - the practitioner …
The CLT fails for LLM evaluations with small data, leading to underestimation of uncertainty.
problem Inaccurate uncertainty estimates in LLM evaluations with small datasets.
method Alternative frequentist and Bayesian methods for uncertainty quantification.
result CLT-based methods underestimate uncertainty in small data settings.
Better calibration for small datasets improves probability estimates.
problem Limited data hinders traditional calibration methods.
method Generating additional calibration data improves classifier performance.
result The proposed approach enhances calibration for small datasets.
DEN learns diverse tasks to generalize to unseen tasks.
problem Generalization from a diverse set of classification tasks with limited data.
method Three-block architecture: covariate transformation, distribution embedding, and classification.
result DEN outperforms existing methods in various synthetic and real tasks.
Estimates policy performance in small-data settings without sacrificing data.
problem Poor performance of cross-validation in small-data optimization.
method Uses sensitivity analysis to estimate gradient of optimal objective value.
result Explicit high-probability bounds on error of estimator for small-data, large-scale problems.
New method for density estimation without approximating posterior distributions.
problem Challenges in non-smooth data distributions for Bayesian density estimation.
method Autoregressive likelihood decomposition and Gaussian process prior in a quasi-Bayesian framework.
result Achieves state-of-the-art results in small-data regimes.
The paper tackles Bayesian inference with small datasets using manifold learning.
problem Small datasets challenge Bayesian inference with non-Gaussian models.
method Manifold learning and sampling for Bayesian posterior approximation.
result The method effectively samples Bayesian posteriors with non-Gaussian models from small datasets.
Learning from small amounts of labeled data is a challenge in the area of deep learning. This is currently addressed by Transfer Learning where one learns the small data set as a transfer task from a larger source dataset. Transfer Learning can deliver higher accuracy if the hyperparameters and source dataset are chose…
Investigates tight PAC-Bayes bounds for small datasets.
problem Tightening PAC-Bayes bounds for small data.
method Generic PAC-Bayes theorem, meta-learning, synthetic tasks.
result PAC-Bayes bounds are competitive with Chernoff bounds but not as tight.
Study examines mean estimation in high dimensions with small data.
problem Efficiently estimating mean in high-dimensional data with limited data size.
method Extensive experimentation of various mean estimation techniques.
result Developed robust methods for mean estimation with low data size.
Paper improves sample efficiency of transfer learning in diffusion models.
problem Diffusion models need too much data to train from scratch.
method Assumes shared low-dimensional representation across tasks for improved sample efficiency.
result Sample complexity of target tasks can be reduced with a well-learned representation.
Bayesian model updating uses VAEs to approximate likelihood with small data.
problem Approximating likelihood for small data sets in structural analysis.
method Uses multimodal VAEs to approximate likelihood, suitable for high-dimensional correlated observations.
result Demonstrates computational efficiency and accuracy compared to original VAE approach.
Improved continual learning method using variational inference and FiLM layers.
problem Training models on new tasks and datasets in an online fashion.
method Generalized Variational Continual Learning (GVCL) with likelihood-tempering and FiLM layers.
result GVCL outperforms existing baselines in both small and large datasets, providing better calibration.
This paper introduces a simple and efficient density estimator that enables fast systematic search. To show its advantage over commonly used kernel density estimator, we apply it to outlying aspects mining. Outlying aspects mining discovers feature subsets (or subspaces) that describe how a query stand out from a given…
This article provides the role of big idea statisticians in future of Big Data Science. We describe the `United Statistical Algorithms' framework for comprehensive unification of traditional and novel statistical methods for modeling Small Data and Big Data, especially mixed data (discrete, continuous).
Convolutional neural networks (CNNs) work well on large datasets. But labelled data is hard to collect, and in some applications larger amounts of data are not available. The problem then is how to use CNNs with small data -- as CNNs overfit quickly. We present an efficient Bayesian CNN, offering better robustness to o…
Deep learning models can infer individual trajectories from sparse data.
problem Learning individual dynamics from limited data points.
method Combining variational autoencoders (VAEs) with ordinary differential equations (ODEs) for dynamic modeling.
result Deep learning can recover individual trajectories from sparse data, but requires careful adaptation.
In this paper, we prove that the Schrödinger map flows from Rd with d≥3 to compact Kähler manifolds with small initial data in critical Sobolev spaces are global. This is a companion work of our previous paper [23] where the energy critical case d=2 was solved. In the first part of this paper, for heat f…
Proposes a model to generate high-dimensional financial returns using latent factor structure.
problem Challenges in financial scenario simulation, especially in high-dimensional and small data settings.
method Integrates latent factor structure into generative diffusion processes, decomposing the score function using time-varying orthogonal projections.
result Establishes rigorous statistical guarantees for score estimation and generated distribution, surpassing dimension-dependent limits.
In this paper we develop a Bayesian optimization based hyperparameter tuning framework inspired by statistical learning theory for classifiers. We utilize two key facts from PAC learning theory; the generalization bound will be higher for a small subset of data compared to the whole, and the highest accuracy for a smal…
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.
Deep kernel learning improves performance on complex tasks.
problem Limited flexibility of classical kernel methods for complicated tasks.
method Random Fourier Features (RFF) integrated into deep architecture.
result Significantly boosts flexibility and richness of kernel machines.
Learning predictive models from small high-dimensional data sets is a key problem in high-dimensional statistics. Expert knowledge elicitation can help, and a strong line of work focuses on directly eliciting informative prior distributions for parameters. This either requires considerable statistical expertise or is l…
Bayesian method predicts individual and crowd preferences from small data.
problem Difficult to predict preferences from limited personal data and noisy labels.
method Combines matrix factorization with Gaussian processes for scalable inference.
result Method predicts preferences for new users and items not in training set.
Study shows low-complexity models can perform as well as state-of-the-art on small datasets.
problem Performance of deep learning models on small datasets.
method Wide variety of experiments with different deep learning architectures on small datasets.
result Low-complexity models can perform comparably well or better than state-of-the-art models on small datasets.
PSiLON Net uses L1 weight normalization and 1-path-norm regularization for efficient learning and sparsity.
problem Efficient learning and sparsity in neural networks with limited data.
method PSiLON Net employs L1 weight normalization and 1-path-norm regularization to simplify the 1-path-norm and achieve efficient learning and near-sparse parameters. result PSiLON Net achieves reliable optimization and strong performance in the small data regime.