Research
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

155310464619 · Jun 202019922001200920172026
48 results for few samples

Learning with few samples is a major challenge for parameter-rich models like deep networks. In contrast, people learn complex new concepts even from very few examples, suggesting that the sample complexity of learning can often be reduced. Many approaches to few-shot learning build on transferring a representation fro…

2019-06-10abs ↗pdf ↗

The paper proposes methods to predict classifier generalization with few labeled samples.

problem Measuring classifier generalization with limited labeled data.
method Analysis of generalization variability, transfer-based solutions in supervised, semi-supervised, and unsupervised settings.
result Simple measures correlate with classifier generalization and can predict it with confidence.

FROB model improves robustness and reliable confidence for few-shot OoD detection.

problem Challenges in few-shot classification and OoD detection due to limited samples and adversarial attacks.
method FROB model combines support boundary generation and few-shot Outlier Exposure (OE) for improved robustness and reliable confidence.
result FROB achieves generalization to unseen OoD and maintains robustness independent of few-shot number.

IMM generates high-quality samples in few steps with stable training.

problem Slow inference and instability in generating high-quality samples using diffusion models and Flow Matching.
method Inductive Moment Matching (IMM) is a new generative model for one- or few-step sampling with a single-stage training procedure.
result IMM achieves state-of-the-art 2-step FID of 1.98 on CIFAR-10 for a model trained from scratch.

New research shows CI in few-shot learning is misleading due to sampling with replacement.

problem Misleading confidence intervals in few-shot learning due to sampling with replacement.
method Comparative analysis of CIs computed with and without replacement.
result Significant underestimation of CI by the predominant method.

Paper proposes a new pipeline for few-shot classification using forget-update module and channel vector sequence.

problem Few-shot classification with limited support samples.
method Channel vector sequence construction module and forget-update module.
result Pipeline achieves state-of-the-art results on various datasets.

Scalable method completes ill-conditioned matrices from few samples.

problem Matrix completion from few samples for ill-conditioned matrices.
method Iterative algorithm combining IRLS, smoothing Newton, and proximal gradient methods.
result Local quadratic convergence rate and well-conditioned linear systems.

A new method for few-sample FS using manifold learning.

problem Few-sample supervised feature selection in high-dimensional spaces.
method Learn feature associations on manifolds, compute composite kernel, and use spectral analysis for FS score.
result Our method outperforms competitors in feature selection and classification accuracy.

Learning new tasks with few samples using related task evaluations.

problem Learning a new task with limited data and related task evaluations.
method Modeling task relatedness through weak monotonicity and leveraging it in transfer learning and model selection aggregation.
result Pruning the model class based on monotonicity and hedging on the task frontier.

Paper tackles few-shot class-incremental learning with a neural gas network.

problem Incrementally learn new classes from very few labelled samples without forgetting old classes.
method Proposes TOPIC framework using a neural gas network to preserve class topology and adapt to new samples.
result Significantly outperforms other methods on CIFAR100, miniImageNet, and CUB200 datasets.

The paper shows how to learn causal representations with few environments and finite samples.

problem Learning causal representations from limited data and environments.
method Explicit, finite-sample guarantees with a logarithmic number of interventions.
result Consistent recovery of latent causal graph, mixing matrix, and unknown intervention targets.

OPSRL algorithm reduces regret with few samples in reinforcement learning.

problem High regret in reinforcement learning with limited data.
method Optimistic Posterior Sampling (OPSRL) with logarithmic sample complexity.
result Guaranteed high-probability regret bound of O~(H3SAT)\widetilde{\mathcal{O}}(\sqrt{H^3SAT}).

Paper improves few-shot classification accuracy using feature distribution preprocessing.

problem Challenges of few-shot classification due to limited labelled samples.
method Proposes a novel transfer-based method that preprocesses feature vectors to Gaussian-like distributions and uses optimal-transport inspired algorithms.
result Achieves state-of-the-art accuracy on standardized vision benchmarks.

Unified framework explains few-shot multimodal medical imaging performance.

problem Limited labeled data in rare diseases and low-resource settings.
method PAC learning, VC theory, PAC Bayesian analysis, information gain, Chain of Thought reasoning.
result Unified theoretical framework for few-shot multimodal medical imaging.

Few-shot visual reasoning model learns analogical relationships from small data.

problem Training deep models on few samples for visual reasoning tasks.
method Meta-analogical contrastive learning to enforce structural similarity between training and test samples.
result Method outperforms state-of-the-art on RAVEN dataset with scarce training data.

This paper explains how overparameterization aids in meta-learning with few samples.

problem Building a generalizable model with few samples in meta-learning.
method Analyzes the optimal linear representation and sample complexity for meta-learning tasks.
result Overparameterization naturally answers fundamental meta-learning questions, reducing sample complexity.

This paper proposes a multi-layer neural network structure for few-shot image recognition of novel categories. The proposed multi-layer neural network architecture encodes transferable knowledge extracted from a large annotated dataset of base categories. This architecture is then applied to novel categories containing…

2019-12-10abs ↗pdf ↗

In few-shot learning, typically, the loss function which is applied at test time is the one we are ultimately interested in minimising, such as the mean-squared-error loss for a regression problem. However, given that we have few samples at test time, we argue that the loss function that we are interested in minimising…

2019-11-29abs ↗pdf ↗

Improves generalization with few samples using a new regularization method.

problem Training deep neural networks with limited data leads to overfitting.
method Sample-based regularization (SBR) to improve generalization without relying on source model knowledge.
result SBR outperformed existing methods in various configurations.

Deep neural networks (DNNs) have achieved state-of-the-art results on time series classification (TSC) tasks. In this work, we focus on leveraging DNNs in the often-encountered practical scenario where access to labeled training data is difficult, and where DNNs would be prone to overfitting. We leverage recent advance…

2019-09-13abs ↗pdf ↗

Paper introduces negative margin loss for better few-shot classification accuracy.

problem Improving few-shot classification accuracy with metric learning.
method Introduces negative margin loss and analyzes its impact on feature discriminability.
result Negative margin loss outperforms regular softmax loss on few-shot classification benchmarks.

We propose a new setting for testing properties of distributions while receiving samples from several distributions, but few samples per distribution. Given samples from ss distributions, p1,p2,,psp_1, p_2, \ldots, p_s, we design testers for the following problems: (1) Uniformity Testing: Testing whether all the pip_i's are …

2019-11-17abs ↗pdf ↗

Meta-learning has been proposed as a framework to address the challenging few-shot learning setting. The key idea is to leverage a large number of similar few-shot tasks in order to learn how to adapt a base-learner to a new task for which only a few labeled samples are available. As deep neural networks (DNNs) tend to…

2019-10-07abs ↗pdf ↗

Paper introduces CoD for few-shot task-aware knowledge distillation using counterfactual explanations.

problem Lack of data for task-aware distillation in resource-constrained scenarios.
method Counterfactual-explanation-infused Distillation CoD for few-shot task-aware knowledge distillation.
result CoD achieves superior performance with significantly fewer samples than baseline methods.

New framework minimizes model complexity for improved few-shot learning.

problem Empirical benefits of pre-training scale with data size but lack theoretical explanation.
method Complexity Minimization framework for meta-representation learning.
result Theoretical analysis shows error rate improves with more meta-training data.

The paper reduces sample complexity for estimating novel task parameters with few meta-learning tasks.

problem Meta-learning sparse linear regression with limited data.
method Accessing multiple similar tasks to recover common support and reduce novel task sample complexity.
result The sample complexity for estimating the parameter of a novel task is greatly reduced to O(1) with respect to the number of tasks.

Few-shot learning has become essential for producing models that generalize from few examples. In this work, we identify that metric scaling and metric task conditioning are important to improve the performance of few-shot algorithms. Our analysis reveals that simple metric scaling completely changes the nature of few-…

2018-05-23abs ↗pdf ↗

Personalizes pre-trained models for nonparametric regression with limited data.

problem Improving data efficiency in nonparametric regression with few samples.
method Develops a theoretical framework and algorithms for few-shot personalization of black-box models.
result Achieves minimax optimal rate for personalization in nonparametric regression.