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.
Paper identifies objective mismatch in MBRL, affecting control task performance.
We develop a model of issue-specific voting behavior. This model can be used to explore lawmakers' personal voting patterns of voting by issue area, providing an exploratory window into how the language of the law is correlated with political support. We derive approximate posterior inference algorithms based on variat…
While Bayesian neural networks (BNNs) have drawn increasing attention, their posterior inference remains challenging, due to the high-dimensional and over-parameterized nature. To address this issue, several highly flexible and scalable variational inference procedures based on the idea of particle optimization have be…
DGPs with variational inference suffer from SNR issues that degrade gradient estimates, leading to unreliable training.
Purpose: Malicious web domain identification is of significant importance to the security protection of Internet users. With online credibility and performance data, this paper aims to investigate the use of machine learning tech-niques for malicious web domain identification by considering the class imbalance issue (i…
Improved GANs mitigate forgetting and collapse issues.
GANs analyzed for performance and training issues.
Paper improves volatility forecasting for new issues and spin-offs.
The increasing inclusion of Machine Learning (ML) models in safety critical systems like autonomous cars have led to the development of multiple model-based ML testing techniques. One common denominator of these testing techniques is their assumption that training programs are adequate and bug-free. These techniques on…
Partial model averaging improves Federated Learning performance.
Graph Neural Networks (GNNs) have achieved promising performance on a wide range of graph-based tasks. Despite their success, one severe limitation of GNNs is the over-smoothing issue (indistinguishable representations of nodes in different classes). In this work, we present a systematic and quantitative study on the o…
Paper simplifies default process modeling and credit valuation.
This paper examines linear embeddings for high-dimensional Bayesian optimization, identifying and addressing issues to improve performance.
Enhances neural architecture search efficiency and prevents performance collapse.
A new technique normalizes nodes within groups to improve GNN performance.
KL-constrained API shows optimization issues and improved with regularization.
New approach to deeper graph neural networks to avoid performance degradation.
Study reveals significant performance flips in GLOD using repurposed graph classification datasets.
Graph transformation framework improves graph neural network performance.
This paper tackles ranking-based performance normalization for optimization algorithms.
GraphFL tackles semi-supervised node classification on graphs using federated learning.
FDS tackles long horizon hyperparameter optimization issues.
Supervised cross-modal hashing has gained increasing research interest on large-scale retrieval task owning to its satisfactory performance and efficiency. However, it still has some challenging issues to be further studied: 1) most of them fail to well preserve the semantic correlations in hash codes because of the la…
Word embeddings may not be uniquely defined due to incompatibility between invariant classes of transformations.
Risk control improves EENNs to make faster predictions without sacrificing accuracy.
We address some computational issues that may hinder the use of AMP chain graphs in practice. Specifically, we show how a discrete probability distribution that satisfies all the independencies represented by an AMP chain graph factorizes according to it. We show how this factorization makes it possible to perform infe…
The paper addresses poor calibration in fine-tuned LLMs after preference alignment.
Finding a well-performing architecture is often tedious for both DL practitioners and researchers, leading to tremendous interest in the automation of this task by means of neural architecture search (NAS). Although the community has made major strides in developing better NAS methods, the quality of scientific empiric…
This paper provides an empirical evaluation of recently developed exploration algorithms within the Arcade Learning Environment (ALE). We study the use of different reward bonuses that incentives exploration in reinforcement learning. We do so by fixing the learning algorithm used and focusing only on the impact of the…
New active learning method uses combinatorial coverage to improve data transfer and reduce bias.
New method tackles label noise on imbalanced datasets by considering class-specific uncertainty.
This paper tackles few-shot classification by improving GAN-based data augmentation.
Study finds non-IID data causes FL performance issues.
Extracting actionable intelligence from distributed, heterogeneous, correlated and high-dimensional data sources requires run-time processing and learning both locally and globally. In the last decade, a large number of meta-learning techniques have been proposed in which local learners make online predictions based on…
This review analyzes RL in finance, highlighting its advantages and challenges.
As more researchers have become aware of and passionate about algorithmic fairness, there has been an explosion in papers laying out new metrics, suggesting algorithms to address issues, and calling attention to issues in existing applications of machine learning. This research has greatly expanded our understanding of…
MiM-StocR combines momentum indicators and adaptive ranking loss for better stock recommendation.
Probabilistic k-nearest neighbour (PKNN) classification has been introduced to improve the performance of original k-nearest neighbour (KNN) classification algorithm by explicitly modelling uncertainty in the classification of each feature vector. However, an issue common to both KNN and PKNN is to select the optimal n…
A new graph neural network tackles oversmoothing and generalization issues.
Semi-supervised learning (SSL) provides a powerful framework for leveraging unlabeled data when labels are limited or expensive to obtain. SSL algorithms based on deep neural networks have recently proven successful on standard benchmark tasks. However, we argue that these benchmarks fail to address many issues that th…
Every year, thousands of people receive consumer product related injuries. Research indicates that online customer reviews can be processed to autonomously identify product safety issues. Early identification of safety issues can lead to earlier recalls, and thus fewer injuries and deaths. A dataset of product reviews …
Disagreement-based approaches generate multiple classifiers and exploit the disagreement among them with unlabeled data to improve learning performance. Co-training is a representative paradigm of them, which trains two classifiers separately on two sufficient and redundant views; while for the applications where there…
A new COVID-19 CT dataset helps develop AI diagnosis models.
Logistic Regression and Support Vector Machine algorithms, together with Linear and Non-Linear Deep Neural Networks, are applied to lending data in order to replicate lender acceptance of loans and predict the likelihood of default of issued loans. A two phase model is proposed; the first phase predicts loan rejection,…
Multiple Additive Regression Trees (MART), an ensemble model of boosted regression trees, is known to deliver high prediction accuracy for diverse tasks, and it is widely used in practice. However, it suffers an issue which we call over-specialization, wherein trees added at later iterations tend to impact the predicti…
CBDA improves active learning for semantic segmentation, especially with imbalanced classes.
Proposes a new approach to regression learning that addresses overfitting and underfitting.
A new multi-label classification model combining SVM and BR with low-rank learning.