Research
On-device research index

arXiv research

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.

168,657 papers · 148 categories

Trend · papers per month

52104155207 · May 202619922001200920172026
48 results for head direction

Minimalistic model captures head direction system properties.

problem Representing head direction system in a high-dimensional space.
method A minimalistic representation model of the rotation group U(1), including fully connected and convolutional versions.
result Emergence of Gaussian-like tuning profiles and 2D circle geometry in both model versions.

Transformers without skip connections collapse token representations to a single direction.

problem Rapid convergence of token representations to a single direction in self-attention-only Transformers.
method Analysis of layer normalization, residual connections, and multi-head attention mechanisms.
result Residual connections prevent rank collapse in real Transformers, while MLPs generate new feature directions.

DDCL-INCRT learns its own structure during training, reducing unnecessary complexity.

problem Fixed-size neural network architectures require manual tuning, leading to overfitting.
method Combines DDCL (Deep Dual Competitive Learning) and INCRT (Incremental Transformer) to self-organize network structure.
result The network self-organizes into a hierarchy of heads, reducing unnecessary complexity.

Multi-head attention outperforms single-head in in-context linear regression tasks.

problem Comparing performance of transformer with single-/multi-head attention in in-context learning.
method Theoretical analysis of performance of transformers with different attention mechanisms in linear regression tasks.
result Multi-head attention with a substantial embedding dimension outperforms single-head attention in in-context linear regression tasks.

New theory shows how multi-head attention reduces variance and decorrelates outputs.

problem Understanding and optimizing multi-head attention in neural networks.
method Developed a statistical theory linking multi-head attention to ensemble Nadaraya-Watson estimators.
result MHA variance reduction depends on head decorrelation, not just head count.

Geometric theory of projection heads in self-supervised learning.

problem Dimensional collapse and information invariance trade-off in projection heads.
method Geometric modeling of projection heads as Riemannian metrics, analyzing Hessian eigenvalues, and tracking optimization geometry.
result Smooth nonlinear heads induce negative curvature, preventing collapse; linear and ReLU heads cannot.

New approach improves multi-head attention by making heads less similar.

problem Multi-head attention can lead to similar features, reducing model expressiveness.
method Proposes a non-parametric approach using Bayesian techniques to make heads repel each other.
result Improves feature diversity, leading to better representations and performance.

Deep forecasting models show output heads significantly improve performance on fat-tailed financial returns.

problem Improving deep learning models for forecasting fat-tailed financial returns.
method Comparison of backbone architectures and output heads (point, Gaussian, Gaussian mixture) on S&P 500 monthly log-returns.
result Switching from point to Gaussian heads improves CRPS by about 1.3 percent, and from Gaussian to mixture adds another 2.4 percent.

A new optimizer DDC improves deep learning models by respecting symmetries.

problem Deep networks' loss is invariant to continuous symmetries, leading to optimization issues.
method DDC builds a Dead-Direction Conditioner that lifts a base optimizer into a G-equivariant one, preserving the quotient geometry.
result DDCAdam and DDCMuon outperform standard optimizers in various tasks, improving validation-train loss gaps and learning dynamics.

Test-time training adapts a pretrained model to each prompt via parameter updates, improving accuracy under pretraining-to-test distribution shifts.

problem Improving accuracy of pretrained models under distribution shifts.
method Explaining TTT behavior through a decision-theoretic lens.
result TTT reduces prediction error when updates are spectrally matched to the prompt's signal-to-noise ratio and aligned with query-relevant eigen-directions.

Multi-head attention mechanism is capable of learning various representations from sequential data while paying attention to different subsequences, e.g., word-pieces or syllables in a spoken word. From the subsequences, it retrieves richer information than a single-head attention which only summarizes the whole sequen…

2019-10-10abs ↗pdf ↗

Attention mechanisms have become ubiquitous in NLP. Recent architectures, notably the Transformer, learn powerful context-aware word representations through layered, multi-headed attention. The multiple heads learn diverse types of word relationships. However, with standard softmax attention, all attention heads are de…

2019-08-30abs ↗pdf ↗

This work proposes a collaborative multi-head attention layer to reduce model size without sacrificing accuracy.

problem Over-parameterization in transformer models trained with large datasets.
method Proposes a collaborative multi-head attention layer that shares key/query projections.
result Reduction in model size by 4 for same accuracy and speed.

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.

Transformer-MGK replaces redundant heads with Gaussian key mixtures, improving efficiency and performance.

problem Redundant attention heads in transformers degrade performance and efficiency.
method Transformer-MGK replaces redundant heads with a mixture of Gaussian keys.
result Transformer-MGK accelerates training and inference, reduces parameters and FLOPs, and achieves comparable or better accuracy.

Attention based Transformer architecture has enabled significant advances in the field of natural language processing. In addition to new pre-training techniques, recent improvements crucially rely on working with a relatively larger embedding dimension for tokens. Unfortunately, this leads to models that are prohibiti…

2020-02-17abs ↗pdf ↗

We consider the Zermelo navigation problem on the ellipsoid of revolution (spheroid) in the presence of a perturbation WW determined by a mild velocity vector field, W<1|W|<1, with application of Finsler metric of Randers type in the context of the corresponding optimal control represented by a time-efficient ship's he…

2016-01-30abs ↗pdf ↗

Develops a mean-field theory for multi-head self-attention under cross-entropy training.

problem Mean-field analysis of multi-head self-attention under cross-entropy training.
method Mean-field theory for a simplified single-layer causal multi-head self-attention model.
result Proves a static finite-head approximation bound for the optimal risk.

Investigates the benefits of multi-head attention in Transformers, deriving convergence and generalization guarantees.

problem Underexplored dynamics of multi-head attention in Transformer training and generalization.
method Derives convergence and generalization guarantees for gradient-descent training of a multi-head self-attention model.
result Establishes conditions for initialization that ensure multi-head attention's realizability.

Investigates optimal parameter allocation in Transformers for efficiency and expressivity.

problem Balancing expressivity and efficiency in Transformer model parameters.
method Mathematical analysis and theoretical characterization of attention heads and head dimensions.
result Later layers can operate more efficiently with reduced parameters due to saturation of softmax activations.

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.

Improved robot navigation using multi-head attention for natural language instructions.

problem Improving robot navigation in unfamiliar environments.
method Proposes a multi-head attention mechanism blending layer in a neural network model.
result Significant performance gains in translating instructions for unseen environments.

Study shows the number of attention heads affects transformer performance.

problem Understanding how the number of attention heads impacts transformer performance.
method Introduced a generalized DD-retrieval task, established upper and lower bounds on parameter complexity, and validated with experiments.
result Transformers with many heads can efficiently approximate functions, while few heads require a large number of parameters.

We show that the head and tail functions of the colored Jones polynomial of adequate links are the product of head and tail functions of the colored Jones polynomial of alternating links that can be read-off an adequate diagram of the link. We apply this to strengthen a theorem of Kalfagianni, Futer and Purcell on the …

2013-10-16abs ↗pdf ↗

New method removes contrastive loss by adding a prediction head, revealing learning mechanisms.

problem Understanding why neural networks learn competitive representations despite trivial optima.
method Empirical and theoretical analysis of a trainable, identity-initialized prediction head.
result The trainable prediction head enables learning all features, preventing dimensional collapse.

This study examines abnormal geodesics in 2D-Zermelo navigation problems, revealing their role in separating time minimal and maximal curves.

problem The role of abnormal geodesics in planar Zermelo navigation problems with strong current.
method Geometric time optimal control approach, focusing on the heading angle of the ship.
result Abnormal geodesics separate time minimal and maximal curves, and are both small-time minimizing and maximizing.

As the Portable Document Format (PDF) file format increases in popularity, research in analysing its structure for text extraction and analysis is necessary. Detecting headings can be a crucial component of classifying and extracting meaningful data. This research involves training a supervised learning model to detect…

2018-08-31abs ↗pdf ↗

Single-head attention approximates any function under various norms.

problem Universal approximation of functions using attention mechanisms.
method Interpreting attention as partitioning and summing linear transformations.
result Single-head attention can approximate any continuous function under LL_\infty-norm and Lebesgue integrable functions under LpL_p-norm.

The paper introduces a method to decompose variance in twin networks for better treatment effect estimation.

problem Accurate treatment effect estimation requires reliable uncertainty measures to locate model failures.
method Layer-wise variance decomposition using Monte Carlo Dropout in twin networks.
result The encoder component dominates under distributional shift, providing a practical diagnostic for data collection.

Unified model predicts stock and systemic risks from diverse financial data.

problem Isolating financial tasks leads to missed cross-scale dependencies.
method Shared Transformer backbone with modular task heads for cross-modal attention and multi-task optimization.
result Uni-FinLLM significantly outperforms baselines in stock forecasting, credit-risk assessment, and systemic-risk detection.

Annealing Double-Head calibrates deep neural networks during training.

problem Overestimation or underestimation of predictive confidence in deep neural networks.
method An additional calibration head and Annealing technique to dynamically scale logits.
result State-of-the-art model calibration performance achieved without post-processing.