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 method improves transfer and robustness of supervised contrastive learning.
We propose a way of computing 4-manifold invariants, old and new, as chiral correlation functions in half-twisted 2d theories that arise from compactification of fivebranes. Such formulation gives a new interpretation of some known statements about Seiberg-Witten invariants, such as the basic class …
New conformal prediction methods for long-tailed classification problems.
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 …
New framework for learning with class-conditional multi-label noise.
YuruGAN generates yuru-chara images using GANs and clustering for small datasets.
Algorithm improves binary classification of biased grouped data.
Method reduces categorical data to lower dimensions using density matrices.
SNS-GAN integrates class labels into generative models for images and time series.
Plug-and-play multimodal controller improves class-conditional image generation.
New method improves domain generalization by matching object representations.
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…
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…
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 …
Representing examples in a way that is compatible with the underlying classifier can greatly enhance the performance of a learning system. In this paper we investigate scalable techniques for inducing discriminative features by taking advantage of simple second order structure in the data. We focus on multiclass classi…
New method removes pseudo-label bias for unsupervised domain adaptation.
Generative models assess quality on time-series data using ITS and FITD.
Domain generalization aims to apply knowledge gained from multiple labeled source domains to unseen target domains. The main difficulty comes from the dataset bias: training data and test data have different distributions, and the training set contains heterogeneous samples from different distributions. Let denote …
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…
DeepCCG adapts classifiers to representation shifts in one step.
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 …
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 …
New method uses label-weighted conformal prediction for macro-coverage guarantees in classification.
Alternative hypothesis tests for class-conditional noise using local maximum likelihood.
Study reveals differences in label shift problem difficulty in supervised vs. unsupervised settings.
Due to the ability of deep neural nets to learn rich representations, recent advances in unsupervised domain adaptation have focused on learning domain-invariant features that achieve a small error on the source domain. The hope is that the learnt representation, together with the hypothesis learnt from the source doma…
Medical imaging models may encode demographic attributes without violating fairness, depending on the approach.
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…
Given a knot inside an integer homology sphere , the Casson-Lin-Herald invariant can be interpreted as a signed count of conjugacy classes of irreducible representations of the knot complement into which map the meridian of the knot to a fixed conjugacy class. It has the interesting feature that it deter…
New method ISR improves domain generalization with provable guarantees.
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…
Adversarial examples raise questions about whether neural network models are sensitive to the same visual features as humans. In this paper, we first detect adversarial examples or otherwise corrupted images based on a class-conditional reconstruction of the input. To specifically attack our detection mechanism, we pro…
Optimal transport aligns source and target distributions for domain adaptation.
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…
Local ancestry inference (LAI) allows identification of the ancestry of all chromosomal segments in admixed individuals, and it is a critical step in the analysis of human genomes with applications from pharmacogenomics and precision medicine to genome-wide association studies. In recent years, many LAI techniques have…
New algorithms identify invariant features for domain generalization.
Sparse coding has been popularly used as an effective data representation method in various applications, such as computer vision, medical imaging and bioinformatics, etc. However, the conventional sparse coding algorithms and its manifold regularized variants (graph sparse coding and Laplacian sparse coding), learn th…
Unified view of label shift estimation methods.
We prove Gray--Moser stability theorems for complementary pairs of forms of constant class defining symplectic pairs, contact-symplectic pairs and contact pairs. We also consider the case of contact-symplectic and contact-contact structures, in which the constant class condition on a one-form is replaced by the conditi…
New research shows input-gradients can be manipulated without changing model's core function, challenging their use for model interpretation.
This work introduces an efficient method to sample high-quality images from conditional GANs.
Enhanced Sampling Scheme improves masked generative modeling.
RFM improves CNFs by adding a boundary constraint term and matching velocity fields.