Study proposes a statistical test for Vision Transformer's attention mechanisms.
problem ViT's attention mechanisms may focus on irrelevant regions, leading to unreliable evidence.
method Selective inference framework to quantify statistical significance of attentions as p-values.
result Proposed method enables reliable quantification of false positive detection probability of attentions.
Bidirectional attention is shown to be equivalent to a continuous bag of words model with mixture-of-experts.
problem Understanding the statistical underpinnings of bidirectional attention.
method Exploring bidirectional attention as a mixture-of-experts model and reparameterizing it.
result Bidirectional attention can be viewed as a continuous bag of words model with mixture-of-experts weights.
The study reveals how attention paths in Transformers influence learning outcomes.
problem Understanding the theoretical basis of Transformers' performance.
method Developed a statistical mechanics theory for a simplified attention network.
result The predictor statistics are influenced by the combination of attention paths.
Regularizes attention scores in vision transformers using bootstrapping.
problem Noisy and diffused attention maps in ViT limit interpretability.
method Statistical learning techniques, bootstrapping of attention scores.
result Improves shrinkage and sparsity of attention scores.
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.
SNI framework for mixed-type data imputation interprets and explains missing values.
problem Missing data in mixed-type databases skew analysis results.
method SNI couples statistical priors with neural attention to impute and explain missing values.
result SNI provides interpretable feature dependency diagnostics and soft regularization of attention.
AIM models explain deep learning in attention layers, offering solvable insights.
problem Understanding how deep learning models learn in attention layers.
method Statistical mechanics and random matrix theory.
result Closed-form predictions for Bayes-optimal generalization error and gradient descent performance.
A method to automatically choose feature dimensions in linear attention for better approximation quality.
problem Choosing the feature dimension in linear attention to balance quality and efficiency.
method Statistical degrees of freedom for determining feature dimension, layer-wise training strategy.
result Our method achieves smaller approximation error compared to fixed dimensions and improves model performance.
Unified thermodynamic approach to Transformer attention dynamics.
problem Understanding the statistical mechanics of Transformer attention.
method Constructing a Lagrangian on the information manifold to analyze attention dynamics.
result Establishes a formal correspondence between scaled dot-product attention and canonical ensemble statistics.
Proposes a channel pruning method using attention statistics for deep networks.
problem Manual setting of compression ratios in each layer for deep neural networks.
method Channel pruning based on attention statistics with automatic selection of compression ratio.
result Improved performance in terms of accuracy and computational costs compared to conventional methods.
Generative adversarial networks with attention improve financial time series simulation.
problem Limited real financial data for training and evaluation of trading strategies.
method Two generative adversarial networks (GANs) using convolutional networks with attention and transformers.
result Attention-based GANs better reproduce stylized facts and smooth returns autocorrelation.
Transformers' self-attention mechanism is mapped to a generalized Potts model.
problem Uncertainty in what type of data distribution self-attention can efficiently learn.
method Decouple word positions and embeddings, then show self-attention learns a generalized Potts model.
result Training self-attention is equivalent to solving the inverse Potts problem.
Paper extends sparse alternatives to softmax for continuous domains, enabling efficient attention mechanisms.
problem Efficiently assigning zero probability to irrelevant categories in continuous domains.
method Extend alpha-entmax to continuous domains, introducing continuous-domain attention mechanisms.
result Continuous attention allows attending to time intervals and compact regions, improving text classification, machine translation, and visual question answering.
Attention-only transformers learn from context via two stages of inference.
problem Learning from corrupted token sequences in minimal transformers.
method Two-stage empirical Bayes interpretation: kernel-weighted posterior mean and particle dynamics.
result Effective denoising without explicit noise schedules, showing posterior-mean recovery under asymptotic conditions.
Softmax attention approximates complex functions and subsumes many known universal approximators.
problem Universal approximation of continuous sequence-to-sequence functions.
method Interpolation-based analysis of attention's internal mechanism, showing its ability to approximate ReLU functions.
result Softmax attention is a universal approximator for continuous sequence-to-sequence functions.
Transformers simplify modeling of small longitudinal cohort data by reducing parameters and incorporating attention mechanisms.
problem Challenges in modeling longitudinal cohort data due to complex temporal dependencies and large dataset requirements.
method Simplified transformer architecture with attention mechanism, autoregressive model, and kernel-based temporal decay.
result The approach recovers contextual dependencies even with small datasets, identifying temporal patterns in stress and mental health.
The paper addresses the relevance problem in statistical inference.
problem The relevance problem in statistical inference from large-scale data.
method Not specified in the abstract, likely involves statistical methods and analysis of large-scale data.
result The relevance problem is a long-neglected topic in statistical inference.
Model traffic congestion events using multi-modal data and attention-based neural networks.
problem Capture non-homogeneous temporal and directional spatial dependencies in traffic congestion events.
method Attention-based neural networks for point processes, adapted tail-up model for spatial statistics.
result Superior performance compared to state-of-the-art methods on synthetic and real data.
Proposes SAHP for better Hawkes process modeling.
problem Predicting occurrence patterns of event sequences.
method Leverages self-attention to modify Hawkes process intensity function.
result Demonstrates effectiveness on real-world datasets.
Gated attention improves performance by using a hierarchical mixture of experts.
problem Improving performance of self-attention mechanisms in Transformers.
method Rigorously show that gated attention can be modeled as a hierarchical mixture of experts, providing a theoretical justification for its benefits.
result Gated attention is more sample-efficient than multi-head self-attention, requiring fewer data points to achieve the same estimation error.
Paper introduces kernel deformed exponential families for sparse continuous attention.
problem Creating efficient attention mechanisms for sparse data.
method Developed kernel deformed exponential families, theoretically and experimentally.
result Kernel deformed exponential families can attend to multiple compact regions of data.
Gated attention improves model curvature, enhancing performance on nonlinear tasks.
problem Understanding the geometric implications of gating in attention mechanisms.
method Modeling attention outputs as Gaussian distributions and analyzing Fisher--Rao geometry.
result Gated attention enables non-flat geometries, including positively curved manifolds.
Study shows attention-style models learn pairwise interactions efficiently.
problem Learning pairwise interactions in attention-style models.
method Proved minimax rate of convergence for learning pairwise interactions.
result Minimax rate is M−2β+12β independent of embedding dimension and token number. Transformers learn to integrate information from past positions incrementally, specializing heads in distinct patterns.
problem How transformers learn to integrate information from multiple past positions with varying statistical significance.
method High-order Markov chain task, incremental learning, sparse attention patterns, simplified differential equations, stage-wise convergence, early stopping as regularizer.
result Transformers learn to specialize heads in distinct patterns, shifting from competitive to cooperative learning dynamics.
New risk statistics for loss-based regulation.
problem Regulatory focus on losses over gains.
method Developed new risk statistics using scenario analysis.
result New risk statistics extend existing measures.
Paper connects MoE and self-attention, proposing active-attention.
problem Improving efficiency and performance of self-attention mechanisms.
method Established connection between MoE and self-attention, analyzed quadratic gating functions, proposed active-attention mechanism.
result Active-attention outperforms standard self-attention in various tasks.
This work explains the structural origins of attention sinks in LLMs.
problem Initial tokens disproportionately monopolize attention scores in LLMs.
method Traced to self-attention's value aggregation process and FFN layer activations.
result Attention sinks form due to variance discrepancy and dimension disparity.
Paper studies how few pretraining tasks are needed for a linear model to solve new tasks.
problem How many pretraining tasks are needed for a linear model to solve new tasks?
method Pretrained a linear attention model for linear regression with a Gaussian prior.
result Effective pretraining requires a small number of independent tasks, and the model closely matches Bayes optimal.
Unified framework for studying softmax attention under large prompts.
problem Challenges in theoretical analysis of softmax attention.
method Measure-based framework for finite and infinite prompts.
result Softmax attention converges to linear attention in the large-prompt regime.
Modeling Bitcoin prices and media attention using jump-type processes.
problem Capturing the dynamics of Bitcoin prices and media attention.
method Lévy processes and semiparametric estimation.
result Effective modeling of Bitcoin prices and media attention using Lévy processes.
WAVE improves time series forecasting by integrating AR and MA components.
problem Time series forecasting challenges.
method WAVE attention mechanism with AR and MA components.
result WAVE attention consistently improves TSF performance.
Establishes statistical and computational bounds for influence diagnostics.
problem Identifying influential datapoints or subsets in machine learning models.
method Finite-sample statistical bounds and computational complexity for influence functions and approximate maximum influence perturbations.
result Established statistical and computational guarantees for influence diagnostics.
OLS predictions are shown to be similar to attention mechanisms in models.
problem OLS in traditional statistics and econometrics.
method Rewriting OLS as an attention mechanism in a transformed space.
result OLS can be understood as minimizing squared prediction errors via optimal embedding and decoding.
DeepIFSAC uses attention mechanisms and contrastive learning to impute missing values in tabular data.
problem Missing values in tabular data, especially when high and not random.
method Row and column attention in a contrastive learning framework with CutMix data augmentation.
result Proposed method outperforms state-of-the-art methods for missing rates between 10% and 90% and various missing value types.
KFAtt improves CTR prediction by modeling user behavior with Kalman filtering attention.
problem Improving CTR prediction in personalized e-commerce search engines.
method KFAtt combines Kalman filtering with attention mechanisms to model user behavior.
result KFAtt outperforms existing methods in CTR prediction, achieving better performance in both offline and online settings.
Proposes RN for unsupervised attention in neural networks.
problem Limited, imbalanced, and non-stationary input distributions in various tasks.
method Inspired by neuronal adaptation, RN uses MDL principle and universal code length for incremental layer-wise computation.
result Outperforms existing normalization methods across diverse tasks.
Time-based model improves recommendation performance.
problem Efficiently handling sequences of varying lengths in recommendation systems.
method Embedding layer and TSL attention-like mechanism with inner products.
result Model outperforms complex models on Taobao User Behavior dataset.
Hybrid model integrates GATv2 and geostatistics for better spatial prediction and uncertainty.
problem Accurate spatial prediction and uncertainty quantification in epidemiology and risk analysis.
method Integrates Graph Attention Network (GATv2) with model-based geostatistics (MBG) to capture relational and spatial dependencies.
result Hybrid model improves predictive accuracy and uncertainty quantification compared to standalone models.
OLS is a special case of Transformer, revealing its linear nature.
problem Understanding the statistical essence of Transformer architecture.
method Algebraic proof and spectral decomposition of covariance matrix.
result Attention mechanism in Transformers is mathematically equivalent to OLS.
Proposes a novel node embedding framework for graphs using Fisher Information.
problem Lack of theoretical understanding of attention-based GNNs.
method Uses hierarchical kernels and Fisher Information to learn node embeddings.
result Proposed method outperforms existing GNNs on node classification benchmarks.
Self multi-head attention improves speaker recognition for long utterances.
problem Speaker recognition for long speech segments using Deep Learning.
method Convolutional Neural Network (CNN) for short-term features, self multi-head attention for long-term embeddings.
result Self multi-head attention outperforms other pooling methods by 18% relative EER on VoxCeleb1 dataset.
Lecture notes on reinforcement learning using statistical methods.
problem Addressing the exploration-exploitation dilemma in decision making.
method Frequentist and Bayesian approaches, function approximation, neural networks.
result Unified framework for decision making and estimation.
We analyze a family of methods for statistical causal inference from sample under the so-called Additive Noise Model. While most work on the subject has concentrated on establishing the soundness of the Additive Noise Model, the statistical consistency of the resulting inference methods has received little attention. W…
A-MMSE uses attention to learn efficient OFDM channel estimation.
problem Accurate OFDM channel estimation requires second-order statistics, which are hard to obtain in practice.
method A-MMSE is a model-based DNN framework that learns linear MMSE filters via Attention Transformer, reducing inference complexity.
result A-MMSE outperforms other methods in normalized MSE across various SNR conditions.
Topological attention improves forecasting of univariate time series.
problem Forecasting univariate time series using local topological features.
method Topological attention mechanism that integrates local topological properties into forecasting models.
result Topological attention leads to state-of-the-art performance on the M4 benchmark.
New method quantifies reliability of neural network image segmentation.
problem Assessing statistical reliability of neural network-based image segmentation results.
method Selective inference framework to compute exact p-values for DNN-driven hypotheses.
result Proposed method successfully controls false positive rate and provides good results for medical image data.
Unified theory of optimal transport for random measures.
problem Statistical uncertainty in optimal transport.
method Constructing L2 over Wasserstein space for random probability measures. result Unified treatment of random optimal transport and principled inference.
Study examines infinite limits of transformer dynamics, identifying key parameterizations.
problem Understanding the training dynamics of transformer models in the feature learning regime.
method Analysis of infinite scaling limits using dynamical mean field theory.
result Identified parameterizations that admit well-defined infinite width and depth limits.