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.

169,341 papers · 148 categories

Trend · papers per month

8162331 · May 202619922001200920182026
48 results for Merge distortion

The paper tightens bounds on distances between Reeb graphs.

problem Certifying quasi-universality of distances between Reeb graphs.
method Establishes tight bi-Lipschitz bounds for various distances.
result Proves strict universality of the functional contortion distance for contour trees and coincides with interleaving distance for merge trees.

LEWIS merges LLMs without training, improving performance on specific tasks.

problem Limited performance improvement of merged models on specific benchmarks.
method Guided model merging using layer-wise sparsity and task-vector pruning.
result Improved model performance by up to 11.3% on math-solving tasks.

New method separates graph structure from node attributes to recover lost signal.

problem Standard representation learning on attributed graphs merges incompatible metric spaces, leading to geometrically flawed alignment.
method Custom variational autoencoder that separates manifold learning from structural alignment.
result Transforms geometric conflict into interpretable structural descriptor, uncovering connectivity patterns and anomalies.

This paper merges deterministic policy gradient estimations to improve deep reinforcement learning performance.

problem The bias-variance tradeoff in estimating and using policy gradients for deep reinforcement learning.
method Introduces elite policy gradients and a two-step merging method to balance bias-variance tradeoffs.
result Two-step merging outperforms interpolation merging and state-of-the-art algorithms on benchmark control tasks.

Study shows training duration impacts model merging quality, suggesting joint selection of duration and method.

problem Impact of expert training duration on model merging quality for large language models (LLMs).
method Systematically fine-tuned experts on five domains across three model sizes, evaluating five merging methods at each duration.
result Training duration affects merging quality, with simple averaging degrading sharply and sparsification-based methods performing well past the validation optimum.

Study shows training duration affects model merging quality, suggesting joint selection of duration and method.

problem Impact of expert training duration on model merging quality for large language models (LLMs).
method Systematically fine-tuned experts on five domains across three model sizes, evaluated five merging methods at each duration.
result Training duration and merging method should be chosen jointly, not independently.

EpiMer merges models by solving Fréchet mean on a Riemannian manifold.

problem Integrating knowledge from multiple models without retraining.
method EpiMer casts model merging as solving the Fréchet mean on a Riemannian manifold, restricting computation to a low-rank subspace.
result EpiMer outperforms flat-geometry methods on image classification tasks.

Securely evaluates the benefits of merging datasets for causal estimation.

problem Challenges in assessing the value of merging datasets for causal treatment effect estimation.
method Cryptographically secure multi-party computation to evaluate Expected Information Gain (EIG) while ensuring privacy.
result Demonstrates the first privacy-preserving method for dataset acquisition tailored to causal estimation.

A new method merges neural networks using CCA to improve model performance.

problem Improving model accuracy through ensembling while reducing computational and storage costs.
method CCA Merge, a new model merging algorithm based on Canonical Correlation Analysis.
result CCA Merge leads to better model performance than past methods, especially in merging more than two models.

This paper reverses a construction by merging boundary critical points into an interior one.

problem Pushing interior critical points to the boundary and splitting them into two boundary points.
method Specific assumptions allow merging two boundary critical points into one interior critical point.
result Merging two boundary critical points into a single interior critical point.

NAMEx merges experts using Nash bargaining for improved performance.

problem Sparse Mixture of Experts merging strategies lack a principled weighting mechanism.
method Reinterpreting expert merging through game theory, introducing Nash Merging and complex momentum.
result NAMEx consistently outperforms competing methods across various tasks and system sizes.

IDAS approach for autonomous vehicles to make decisions under merging scenarios.

problem Decision making for autonomous vehicles in merging scenarios with varying driver cooperativeness.
method IDAS approach using multi-agent reinforcement learning (MARL) with curriculum learning and masking mechanism.
result IDAS approach can handle uncertainties in real-world scenarios and make strategic decisions.

Discrete knot theory models use lattice-filtered graphs to detect merging knot components.

problem Detecting merging knot components in discrete models.
method Lattice-filtered move graphs to model knot types, identifying connected components and merge scales.
result Merge scale defined by connected components of lattice-filtered move graphs, with specific examples for the figure-eight knot.

Analyzes merging vs. ensembling for multi-study prediction, showing transition point for better performance.

problem Choosing between merging or ensembling multiple studies for prediction.
method Analyzes ridge regression approaches, comparing merging and ensembling methods.
result There is a transition point where ensembling outperforms merging as cross-study heterogeneity increases.

Method constructs finance LLMs without instruction data using pretraining and model merging.

problem Developing domain-specific LLMs for finance is resource-intensive.
method Continual pretraining on financial data + model merging of instruction-tuned and domain-specific pretrained vectors.
result Successfully constructs instruction-tuned LLMs for finance without additional instruction data.

LiteMORT reduces memory usage for GBDT models by 30% with improved accuracy.

problem Memory inefficiency in GBDT models, especially with adaptive compact distributions.
method Share memory, implicit merging, adaptive histogram resizing.
result Significant reduction in memory usage with improved accuracy.

DPSM clusters nodes in data and graph spaces via density propagation and subcluster merging.

problem Automatic clustering of nodes in data and graph spaces.
method Density-based node clustering with propagation process and spectral clustering on subclusters.
result DPSM effectively clusters nodes in both data and graph spaces.

Bayesian Federated Inference improves survival model analysis without merging data.

problem Accurately estimating survival model parameters requires sufficient data and events, which is often lacking in practice.
method Bayesian Federated Inference (BFI) for survival models, where local centers perform analyses and combine results.
result Results from BFI are similar to those from merged data analyses, demonstrating excellent performance.

The hierarchical Dirichlet process (HDP) has become an important Bayesian nonparametric model for grouped data, such as document collections. The HDP is used to construct a flexible mixed-membership model where the number of components is determined by the data. As for most Bayesian nonparametric models, exact posterio…

2012-01-08abs ↗pdf ↗

We consider the problem of distortion minimal morphing of nn-dimensional compact connected oriented smooth manifolds without boundary embedded in Rn+1\R^{n+1}. Distortion involves bending and stretching. In this paper, minimal distortion (with respect to stretching) is defined as the infinitesimal relative change in vol…

2006-05-25abs ↗pdf ↗

NetFuse merges different DNN models with varying weights for faster inference.

problem Inference speed of DNN models with different weights cannot be improved using existing techniques.
method NetFuse merges models with the same architecture but different weights and inputs, replacing operations with more general ones.
result NetFuse can speed up DNN inference time up to 3.6x on a NVIDIA V100 GPU.

This paper shows how to calculate risk measures for sums of two counter-monotonic risks.

problem Calculating risk measures for sums of two counter-monotonic risks.
method Using a fixed distortion function and expressing the risk measure of a sum as the sum of two related measures of the marginals.
result The risk measure of a sum of two counter-monotonic risks can be expressed as the sum of two related distortion risk measures of the marginals.

A new family of stochastic dominance orders based on distortion functions.

problem Determining a continuum of dominance relations for risk assessment.
method Introducing H-distorted stochastic dominance, a generalized family of stochastic orders.
result Power-distorted stochastic dominance is particularly appealing due to its simplicity and statistical interpretations.

The distortion of a curve measures the maximum arc/chord length ratio. Gromov showed any closed curve has distortion at least pi/2 and asked about the distortion of knots. Here, we prove that any nontrivial tame knot has distortion at least 5pi/3; examples show that distortion under 7.16 suffices to build a trefoil kno…

2004-09-22abs ↗pdf ↗