arXiv research

Study integrates attentional and spacing factors to improve category learning models.

Develops a framework for identifying mispriced assets through attention factors for statistical arbitrage.

Bayesian Attention Networks compress data by focusing on key training samples.

MPTE uses Transformer attention to estimate mixed-frequency factor models.

Develops a deep multi-factor model for factor investing with clear financial insights.

A framework for disentangling class-related and class-independent factors in data.

Gradient descent converges geometrically to optimal self-attention parameters.

Graph neural networks speed up nonnegative matrix factorization.

EFA extends self-attention to handle mixed data types and dynamic relevance.

New model mimics neural next item recommendation using Hankel matrices.

FMA-ETA predicts travel time using FFN with attention.

Study optimizes resource allocation in noisy systems for better control.

Dynamic portfolio strategy using generative model with attention mechanism.

AGBoost uses attention weights to improve GBM for regression problems.

This paper explores how combining quantitative factors and news from LLMs improves stock return prediction.

Bi-LSTM with attention predicts gold and bitcoin prices accurately.

We aim to better understand attention over nodes in graph neural networks (GNNs) and identify factors influencing its effectiveness. We particularly focus on the ability of attention GNNs to generalize to larger, more complex or noisy graphs. Motivated by insights from the work on Graph Isomorphism Networks, we design …

In this paper, we generalize the parametric delta-VaR method from portfolios with normally distributed risk factors to portfolios with elliptically distributed ones. We treat both the expected shortfall and the Value-at-Risk of such portfolios. Special attention is given to the particular case of a multivariate t-distr…

In this paper, we generalize the parametric Delta-VaR methods from portfolios with elliptic distributed risk factors to portfolios with mixture of elliptically distributed ones. We treat both the Expected Shortfall and the Value-at-Risk of such portfolios. Special attention is given to the particular case of the mixtur…

Skeinformer accelerates self-attention for long sequences with linear complexity.

HAMN combines CF models to improve drug repositioning.

AI2V learns user representations by focusing on recent interests.

Survey on factor models and their applications in econometrics.

New framework shows cross-attention improves multi-modal in-context learning.

H-GAT improves stock selection by capturing complex higher-order stock relations and integrating both technical and fundamental analysis.

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…

Recommender systems (RS), which have been an essential part in a wide range of applications, can be formulated as a matrix completion (MC) problem. To boost the performance of MC, matrix completion with side information, called inductive matrix completion (IMC), was further proposed. In real applications, the factorize…

New approach reduces model size for Transformer architectures.

The complex world around us is inherently multimodal and sequential (continuous). Information is scattered across different modalities and requires multiple continuous sensors to be captured. As machine learning leaps towards better generalization to real world, multimodal sequential learning becomes a fundamental rese…

A3T-GCN improves traffic forecasting by capturing spatial and temporal dependencies.

Traditional sequence-to-sequence (seq2seq) models and other variations of the attention-mechanism such as hierarchical attention have been applied to the text summarization problem. Though there is a hierarchy in the way humans use language by forming paragraphs from sentences and sentences from words, hierarchical mod…

The study compares feed-forward and attention layers in language models.

Transformers are powerful sequence models, but require time and memory that grows quadratically with the sequence length. In this paper we introduce sparse factorizations of the attention matrix which reduce this to $O(n \sqrt{n})$. We also introduce a) a variation on architecture and initialization to train deeper net…

New approach shows why overparameterized neural nets generalize well.

CoT improves transformer sample efficiency by reducing input token dependencies and attention sparsity.

Intelligent Momentum Transformer outperforms traditional trading strategies.

A new model uses attention and Gaussian processes for efficient time-series generation.

Financial time series prediction, especially with machine learning techniques, is an extensive field of study. In recent times, deep learning methods (especially time series analysis) have performed outstandingly for various industrial problems, with better prediction than machine learning methods. Moreover, many resea…

We demystify attention patterns in multi-head softmax models for linear data.

Study on multi-head softmax attention dynamics for in-context learning.

Softmax is found ineffective for NL block, leading to improved performance.

Social-based recommendation systems exploit the selections of friends to combat the data sparsity on user preferences, and improve the recommendation accuracy of the collaborative filtering strategy. The main challenge is to capture and weigh friends' preferences, as in practice they do necessarily match. In this paper…

A simplified model for fixed income portfolio optimisation.

Inspired by the adaptation phenomenon of neuronal firing, we propose the regularity normalization (RN) as an unsupervised attention mechanism (UAM) which computes the statistical regularity in the implicit space of neural networks under the Minimum Description Length (MDL) principle. Treating the neural network optimiz…

Modeling incentives for content creators on algorithm-curated platforms.

The team predicts foreign exchange rates using clustering and attention models.

Crypto markets show negative spillovers between chains, not positive co-movements.

The problem of portfolio allocation in the context of stocks evolving in random environments, that is with volatility and returns depending on random factors, has attracted a lot of attention. The problem of maximizing a power utility at a terminal time with only one random factor can be linearized thanks to a classica…