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.
The paper compares one-hot encoding to Naïve Bayes for categorical variables.
Graph-based semi-supervised learning is the problem of propagating labels from a small number of labelled data points to a larger set of unlabelled data. This paper is concerned with the consistency of optimization-based techniques for such problems, in the limit where the labels have small noise and the underlying unl…
Paper tackles noisy labels in deep learning networks.
Improved DLG extracts accurate labels from gradients, overcoming DLG's convergence issues.
Paper introduces MLRH, a probabilistic model for multilabel classification.
Label smoothing improves model performance even with noisy labels.
New method improves conformal prediction for ambiguous labels.
One-hot encoding is a labelling system that embeds classes as standard basis vectors in a label space. Despite seeing near-universal use in supervised categorical classification tasks, the scheme is problematic in its geometric implication that, as all classes are equally distant, all classes are equally different. Thi…
Preventing early progression of epilepsy and so the severity of seizures requires an effective diagnosis. Epileptic transients indicate the ability to develop seizures but humans overlook such brief events in an electroencephalogram (EEG) what compromises patient treatment. Traditionally, training of the EEG event dete…
A framework learns dynamic soft labels to improve model generalization and accuracy.
Enhances GBDT robustness with one-hot encoding and regularization.
Proposes a probabilistic approach to semi-supervised learning using normalizing flows.
This paper deals with the problem of large-scale linear supervised learning in settings where a large number of continuous features are available. We propose to combine the well-known trick of one-hot encoding of continuous features with a new penalization called \emph{binarsity}. In each group of binary features comin…
Pairwise Label Smoothing improves deep model generalization by reducing overconfidence.
Distillation improves simple models by approximating complex labels.
NLE embeds labels for domain adaptation with neural networks.
Quasi-orthonormal encoding reduces high dimensionality for categorical data.
For statistical learning, categorical variables in a table are usually considered as discrete entities and encoded separately to feature vectors, e.g., with one-hot encoding. "Dirty" non-curated data gives rise to categorical variables with a very high cardinality but redundancy: several categories reflect the same ent…
Label smoothing improves model robustness against misspecification.
Statistical models usually require vector representations of categorical variables, using for instance one-hot encoding. This strategy breaks down when the number of categories grows, as it creates high-dimensional feature vectors. Additionally, for string entries, one-hot encoding does not capture information in their…
A fast graph embedding method for large graphs.
Enhances graph neural networks with structural message-passing for better generalization.
Method reduces categorical data to lower dimensions using density matrices.
MixUp is a recently proposed data-augmentation scheme, which linearly interpolates a random pair of training examples and correspondingly the one-hot representations of their labels. Training deep neural networks with such additional data is shown capable of significantly improving the predictive accuracy of the curren…
A new method improves uncertainty estimation in deep learning, especially for hard-to-label samples.
In recent years, deep neural network is widely used in machine learning. The multi-class classification problem is a class of important problem in machine learning. However, in order to solve those types of multi-class classification problems effectively, the required network size should have hyper-linear growth with r…
One of the ubiquitous representation of long DNA sequence is dividing it into shorter k-mer components. Unfortunately, the straightforward vector encoding of k-mer as a one-hot vector is vulnerable to the curse of dimensionality. Worse yet, the distance between any pair of one-hot vectors is equidistant. This is partic…
While the backpropagation of error algorithm enables deep neural network training, it implies (i) bidirectional synaptic weight transport and (ii) update locking until the forward and backward passes are completed. Not only do these constraints preclude biological plausibility, but they also hinder the development of l…
This technical report describes a practical field test on word-image classification in a very large collection of more than 300 diverse handwritten historical manuscripts, with 1.6 million unique labeled images and more than 11 million images used in testing. Results indicate that several deep-learning tests completely…
We propose a new STAcked and Reconstructed Graph Convolutional Networks (STAR-GCN) architecture to learn node representations for boosting the performance in recommender systems, especially in the cold start scenario. STAR-GCN employs a stack of GCN encoder-decoders combined with intermediate supervision to improve the…
A new sampler for FLMs improves token-level decoding controls.
This paper proposes a method to reduce complexity in GLMs with categorical predictors.
Conventional embedding methods directly associate each symbol with a continuous embedding vector, which is equivalent to applying a linear transformation based on a "one-hot" encoding of the discrete symbols. Despite its simplicity, such approach yields the number of parameters that grows linearly with the vocabulary s…
BUDS balances privacy and utility by shuffling data, achieving strong privacy with minimal loss.
Embedding methods such as word embedding have become pillars for many applications containing discrete structures. Conventional embedding methods directly associate each symbol with a continuous embedding vector, which is equivalent to applying linear transformation based on "one-hot" encoding of the discrete symbols. …
Efficient method for vertex embedding and community detection.
flexBART improves BART for categorical predictors by creating flexible tree partitions.
Paper proposes embedding models to capture semantic similarities of categorical attributes in financial bonds.
Conditional generative models have achieved considerable success in the past few years, but usually require a lot of labeled data. Recently, ClusterGAN combines GAN with an encoder to achieve remarkable clustering performance via unsupervised conditional generation. However, it ignores the real conditional distribution…
Many learning algorithms require categorical data to be transformed into real vectors before it can be used as input. Often, categorical variables are encoded as one-hot (or dummy) vectors. However, this mode of representation can be wasteful since it adds many low-signal regressors, especially when the number of uniqu…
Natural Language Processing models help encode categorical process inputs.
In this paper we propose a method to build a neural network that is similar to an ensemble of decision trees. We first illustrate how to convert a learned ensemble of decision trees to a single neural network with one hidden layer and an input transformation. We then relax some properties of this network such as thresh…
Missing data imputation can help improve the performance of prediction models in situations where missing data hide useful information. This paper compares methods for imputing missing categorical data for supervised classification tasks. We experiment on two machine learning benchmark datasets with missing categorical…
Imputation with missing-indicators improves machine learning performance, especially for categorical attributes.
A new metric for uncertainty quantification using class collisions.
Better uncertainty estimates for neural networks using Gaussian process priors.
StructureBoost improves gradient boosting for complex categorical variables efficiently.
Recurrent neural networks have been very successful at predicting sequences of words in tasks such as language modeling. However, all such models are based on the conventional classification framework, where the model is trained against one-hot targets, and each word is represented both as an input and as an output in …