Study integrates attentional and spacing factors to improve category learning models.
problem Understanding the impact of training sequences on category learning.
method Introduced a novel integration of attentional factors and spacing into logistic knowledge tracing models.
result Enhanced model predicts students' learning outcomes better than existing models.
Develops a framework for identifying mispriced assets through attention factors for statistical arbitrage.
problem Identifying mispriced assets in statistical arbitrage trading.
method Uses conditional latent factors learned from firm characteristic embeddings to identify time-series signals and form a trading strategy.
result Achieves an out-of-sample Sharpe ratio above 4 on the largest U.S. equities over a 24-year period.
Bayesian Attention Networks compress data by focusing on key training samples.
problem Lossless data compression for efficiency.
method Bayesian Attention Networks with attention factors and latent space.
result Efficient prediction using a few correlated training samples.
MPTE uses Transformer attention to estimate mixed-frequency factor models.
problem Estimating factor models in panel datasets with mixed frequencies and nonlinear signals.
method Mixed-Panels-Transformer Encoder (MPTE) with attention mechanisms.
result MPTE achieves competitive performance in nonlinear forecasting environments.
Develops a deep multi-factor model for factor investing with clear financial insights.
problem Lack of interpretability and unclear financial insights in non-linear factor models.
method Industry and market neutralization modules, graph attention modules, factor-attention module.
result Demonstrates effectiveness in factor investing with real-world stock market data.
A framework for disentangling class-related and class-independent factors in data.
problem Learning disentangled representations in variational autoencoders.
method Attention mechanism in latent space, mixture models, Bhattacharyya coefficient, semi-supervised training.
result Disentangles class-related and class-independent factors of variation.
Gradient descent converges geometrically to optimal self-attention parameters.
problem Training softmax self-attention layers for linear regression.
method Structure-aware gradient descent with preconditioner and regularizer.
result Gradient descent converges geometrically to global minima.
Graph neural networks speed up nonnegative matrix factorization.
problem Efficiently factorize nonnegative matrices for various applications.
method Developed a graph neural network that combines bipartite self-attention with ADMM updates.
result Significant acceleration achieved in nonnegative matrix factorization.
EFA extends self-attention to handle mixed data types and dynamic relevance.
problem Handling high-dimensional, mixed data types with dynamic relevance.
method Probabilistic generative model using self-attention and latent factor model.
result EFA consistently outperforms existing models in complex latent structure capture and reconstruction.
New model mimics neural next item recommendation using Hankel matrices.
problem Next item recommendation efficiency and structural knowledge capture.
method Tensor factorization with Hankel matrix representation.
result Model performs competitively with neural networks but is simpler.
FMA-ETA predicts travel time using FFN with attention.
problem Estimating travel time from spatial-temporal data.
method FFN with Multi-factor self-attention mechanism.
result FMA-ETA outperforms state-of-the-art methods in prediction accuracy with faster inference.
Study optimizes resource allocation in noisy systems for better control.
problem Limited attention in stochastic systems with multiplicative noise.
method Analytical and numerical methods for optimal attention allocation.
result Effective resource allocation enhances noise estimation and control decisions.
Dynamic portfolio strategy using generative model with attention mechanism.
problem Dynamic modeling of multivariate stock returns with tail-side properties.
method Dynamic generative factor model using Attention-GRU network for dynamic learning and forecasting.
result The proposed model leads to wiser investments with higher reward-risk ratios and lower tail risks.
AGBoost uses attention weights to improve GBM for regression problems.
problem Improving gradient boosting machine for regression tasks.
method Attention-based modification of GBM with trainable attention weights.
result AGBoost achieves better performance on regression datasets.
This paper explores how combining quantitative factors and news from LLMs improves stock return prediction.
problem Improving stock return prediction using quantitative factors and news.
method Introduces a fusion learning framework to learn unified representations from factors and LLM-generated newsflow, comparing combination, summation, and attentive methods. Explores mixture models and decoupled training approaches.
result Effective multimodal modeling of factors and news improves stock return prediction and selection.
Bi-LSTM with attention predicts gold and bitcoin prices accurately.
problem Predicting prices of gold and bitcoin in financial derivatives markets.
method Bidirectional LSTM neural network with attention mechanism, feature engineering, two-layer deep learning.
result Achieved 71.94% and 73.03% accuracy for bitcoin and gold respectively.
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…
Skeinformer accelerates self-attention for long sequences with linear complexity.
problem Efficiency of Transformer models in processing long sequences.
method Matrix sketching and column sampling to reduce quadratic complexity to linear.
result Skeinformer outperforms alternatives with smaller time/space footprint.
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…
HAMN combines CF models to improve drug repositioning.
problem Efficient drug repositioning with cold start problem.
method Hybrid Attentional Memory Network (HAMN) integrating memory and attention mechanisms.
result HAMN outperforms other models in drug repositioning tasks.
AI2V learns user representations by focusing on recent interests.
problem User interests and behavior change over time, affecting recommendation quality.
method Introduces AI2V, a neural attentive model that learns user representations by focusing on recent interests.
result AI2V outperforms other models on various datasets.
Survey on factor models and their applications in econometrics.
problem Estimating low-rank structures in high-dimensional models.
method Low-rank recovery techniques for factor model estimation.
result New insights into factor model applications in econometrics.
New framework shows cross-attention improves multi-modal in-context learning.
problem Understanding multi-modal in-context learning in neural networks.
method Mathematical framework and linearized cross-attention mechanism.
result Cross-attention mechanism is provably optimal for multi-modal in-context learning.
H-GAT improves stock selection by capturing complex higher-order stock relations and integrating both technical and fundamental analysis.
problem Stock selection difficulty and lack of comprehensive analysis.
method Higher-order Graph Attention Network (H-GAT) that incorporates both technical and fundamental analysis.
result H-GAT outperforms existing methods in stock selection metrics.
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…
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…
New approach reduces model size for Transformer architectures.
problem Large embedding dimensions limit model applicability.
method Identified low-rank bottleneck in multi-head attention.
result Reducing head size to sequence length improves model performance.
A3T-GCN improves traffic forecasting by capturing spatial and temporal dependencies.
problem Accurate real-time traffic forecasting in complex road networks.
method Attention Temporal Graph Convolutional Network (A3T-GCN) integrating recurrent units and graph convolutional network.
result Improved prediction accuracy through attention mechanism and global temporal information.
The study compares feed-forward and attention layers in language models.
problem Understanding the role of feed-forward and attention layers in language models.
method Empirical and theoretical analysis in a synthetic setting.
result Feed-forward layers learn simple distributional associations, while attention layers focus on in-context reasoning.
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 n ) O(n \sqrt{n}) O ( n n ) . We also introduce a) a variation on architecture and initialization to train deeper net…
New approach shows why overparameterized neural nets generalize well.
problem Understanding why overparameterized neural nets generalize well in practice.
method An alternative notion of capacity for attention-based models based on the effective rank of attention matrices.
result Generalization bound matches empirical scaling laws observed in large language models.
CoT improves transformer sample efficiency by reducing input token dependencies and attention sparsity.
problem Transformer sample inefficiency in simple tasks.
method Demonstrated through parity-learning setup, showing CoT reduces required samples from exponential to polynomial.
result Transformer learns function within polynomial samples with CoT, requiring exponential samples without CoT.
Intelligent Momentum Transformer outperforms traditional trading strategies.
problem Improving time-series momentum and mean-reversion trading strategies.
method Attention-based deep-learning architecture (Momentum Transformer) combining attention and LSTM.
result Momentum Transformer outperforms benchmarks and adapts to new market regimes.
A new model uses attention and Gaussian processes for efficient time-series generation.
problem Computational inefficiency and uncertainty underestimation in sequence transduction.
method Attention-based Gaussian process network for real-valued sequence generation.
result The model improves training efficiency and learns factorized generative distribution.
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.
problem Understanding the training dynamics and emergent patterns in multi-head softmax attention models.
method Extensive empirical experiments and rigorous theoretical analysis.
result Multi-head softmax attention models approximate a debiased gradient descent predictor, outperforming single-head attention and achieving near-Bayesian optimality.
Study on multi-head softmax attention dynamics for in-context learning.
problem Understanding and optimizing multi-head softmax attention models for multi-task linear regression.
method Gradient flow analysis and spectral mapping technique.
result Gradient flow converges to optimal multi-head softmax attention model, with task allocation emerging during training.
Softmax is found ineffective for NL block, leading to improved performance.
problem Inefficiency of softmax in NL block for global context modeling.
method Empirical analysis and replacement of softmax with scaling factor.
result Improved performance on various datasets with reduced computational cost.
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.
problem Modeling interest rates and credit risk in fixed income portfolios.
method Proposes a two-factor model for the time evolution of the efficient frontier.
result The efficient frontier is mainly controlled by linear constraints, with standard deviation less important.
FMT model improves multimodal sequential learning across language, vision, and acoustic data.
problem Modeling spatio-temporal dynamics across multiple modalities.
method Factorized Multimodal Transformer (FMT) that models intramodal and intermodal dynamics in a factorized manner.
result FMT outperforms existing models on 3 datasets and 21 labels, setting new state of the art.
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.
problem Maximizing exposure for content creators on algorithmic platforms.
method Formalized exposure game model, proving effects of algorithmic choices on equilibria, proposing tools for finding equilibria.
result Algorithmic choices significantly affect content exposure and creator behavior.
Improved text summarization using neural semantic encoders with hierarchical structure.
problem Capturing long-term dependencies in text summarization.
method Proposed a novel hierarchical Neural Semantic Encoder (NSE) model augmented with lemma and PoS tags.
result Significantly outperformed state-of-the-art models in ROUGE metric.
The team predicts foreign exchange rates using clustering and attention models.
problem Complexity and unexpected events in foreign exchange markets.
method Clustering and attention models applied to historical data.
result Improved event-driven price prediction for oversold scenarios.
Crypto markets show negative spillovers between chains, not positive co-movements.
problem Negative spillovers in crypto asset returns across different blockchains.
method On-chain data from multiple blockchains (Ethereum, Solana, Binance, Arbitrum, Avalanche) analyzed over 2022-2025.
result Surges on one chain often coincide with declines on others, especially during attention shocks.
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…