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.
New framework for learning with class-conditional multi-label noise.
SNS-GAN integrates class labels into generative models for images and time series.
We investigate the problem of classification in the presence of unknown class-conditional label noise in which the labels observed by the learner have been corrupted with some unknown class dependent probability. In order to obtain finite sample rates, previous approaches to classification with unknown class-conditiona…
In many real-world classification problems, the labels of training examples are randomly corrupted. Most previous theoretical work on classification with label noise assumes that the two classes are separable, that the label noise is independent of the true class label, or that the noise proportions for each class are …
Alternative hypothesis tests for class-conditional noise using local maximum likelihood.
Learning with noisy labels, which aims to reduce expensive labors on accurate annotations, has become imperative in the Big Data era. Previous noise transition based method has achieved promising results and presented a theoretical guarantee on performance in the case of class-conditional noise. However, this type of a…
The real-world data is often susceptible to label noise, which might constrict the effectiveness of the existing state of the art algorithms for ordinal regression. Existing works on ordinal regression do not take label noise into account. We propose a theoretically grounded approach for class conditional label noise i…
Paper tackles noisy labels for non-decomposable performance measures.
Method reduces categorical data to lower dimensions using density matrices.
New conformal prediction methods for long-tailed classification problems.
DeepCCG adapts classifiers to representation shifts in one step.
YuruGAN generates yuru-chara images using GANs and clustering for small datasets.
Method estimates noise transition matrix from noisy labels without relying on unreliable class-posterior estimation.
Well-known for its simplicity and effectiveness in classification, AdaBoost, however, suffers from overfitting when class-conditional distributions have significant overlap. Moreover, it is very sensitive to noise that appears in the labels. This article tackles the above limitations simultaneously via optimizing a mod…
A method to approximate instance-dependent label noise using instance-confidence embedding.
In this paper, we study a classification problem in which sample labels are randomly corrupted. In this scenario, there is an unobservable sample with noise-free labels. However, before being observed, the true labels are independently flipped with a probability , and the random label noise can be class-co…
Proposes a new model for noisy labels considering multiple labelers and adversarial attacks.
New method improves false-/true-positive-rate estimation in fraud detection with noisy labels.
Generative adversarial networks (GANs) are a framework that learns a generative distribution through adversarial training. Recently, their class-conditional extensions (e.g., conditional GAN (cGAN) and auxiliary classifier GAN (AC-GAN)) have attracted much attention owing to their ability to learn the disentangled repr…
Entropy tracking reveals class commitment transitions in diffusion models.
Develops NPMC method for noisy labels, improving multiclass classification accuracy.
Proposes a method to improve class-conditional conformal prediction for many classes.
We introduce advocacy learning, a novel supervised training scheme for attention-based classification problems. Advocacy learning relies on a framework consisting of two connected networks: 1) Advocates (one for each class), each of which outputs an argument in the form of an attention map over the input, and 2) a …
We present a simple generative framework for learning to predict previously unseen classes, based on estimating class-attribute-gated class-conditional distributions. We model each class-conditional distribution as an exponential family distribution and the parameters of the distribution of each seen/unseen class are d…
Class-conditional generative models are crucial tools for data generation from user-specified class labels. Existing approaches for class-conditional generative models require nontrivial modifications of backbone generative architectures to model conditional information fed into the model. This paper introduces a plug-…
We propose a new algorithm to incorporate class conditional information into the critic of GANs via a multi-class generalization of the commonly used Hinge loss that is compatible with both supervised and semi-supervised settings. We study the compromise between training a state of the art generator and an accurate cla…
The paper analyzes the maximum margin algorithm's performance on noisy data.
In this draft, which reports on work in progress, we 1) adapt the information bottleneck functional by replacing the compression term by class-conditional compression, 2) relax this functional using a variational bound related to class-conditional disentanglement, 3) consider this functional as a training objective for…
We show how to compute lower bounds for the supremum Bayes error if the class-conditional distributions must satisfy moment constraints, where the supremum is with respect to the unknown class-conditional distributions. Our approach makes use of Curto and Fialkow's solutions for the truncated moment problem. The lower …
Ridge regression shows different behaviors in binary classification with noisy labels.
New method improves transfer and robustness of supervised contrastive learning.
The paper introduces a Hessian-based method to improve generalization in fine-tuned deep neural networks.
New method removes pseudo-label bias for unsupervised domain adaptation.
The paper tackles noisy labels in high-dimensional data, showing low-dimensional intuitions fail and proposing an optimized method.
Unified framework improves cross-corpus EEG emotion recognition by aligning prototypes and refining decision boundaries.
Generative models assess quality on time-series data using ITS and FITD.
DiffWave generates high-fidelity audio waveforms efficiently.
Generative model uses SDEs to transform data distributions.
We associate determinant lines to objects of the extended abelian category built out of a von Neumann category with a trace. Using this we suggest constructions of the combinatorial and the analytic L^2 torsions which, unlike the work of the previous authors, requires no additional assumptions; in particular we do not …
Conformal prediction fails to cover minority classes in imbalanced datasets, but a class-conditional fix improves coverage.
We develop a novel method for training of GANs for unsupervised and class conditional generation of images, called Linear Discriminant GAN (LD-GAN). The discriminator of an LD-GAN is trained to maximize the linear separability between distributions of hidden representations of generated and targeted samples, while the …
New method uses label-weighted conformal prediction for macro-coverage guarantees in classification.
Study reveals differences in label shift problem difficulty in supervised vs. unsupervised settings.
Learning exists in the context of data, yet notions of confidence typically focus on model predictions, not label quality. Confident learning (CL) is an alternative approach which focuses instead on label quality by characterizing and identifying label errors in datasets, based on the principles of pruning noisy data, …
Image classification datasets are often imbalanced, characteristic that negatively affects the accuracy of deep-learning classifiers. In this work we propose balancing GAN (BAGAN) as an augmentation tool to restore balance in imbalanced datasets. This is challenging because the few minority-class images may not be enou…
We introduce DeepInversion, a new method for synthesizing images from the image distribution used to train a deep neural network. We 'invert' a trained network (teacher) to synthesize class-conditional input images starting from random noise, without using any additional information about the training dataset. Keeping …
Paper proposes a new method for supervised manifold learning using random forest proximities.
Electroencephalography (EEG) data are difficult to obtain due to complex experimental setups and reduced comfort with prolonged wearing. This poses challenges to train powerful deep learning model with the limited EEG data. Being able to generate EEG data computationally could address this limitation. We propose a nove…