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.
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.
Efficiently clusters data with weak assumptions, robust to contamination.
problem General-shaped clustering under weak parametric assumptions with data contamination.
method Two-step hybrid robust clustering algorithm combining trimmed k-means and hierarchical agglomeration.
result Outperforms state-of-the-art methods in various applications.
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.
Develops a new method to recover large latent tree models efficiently.
problem Inference of large latent tree structures from terminal node observations.
method Spectral Top-Down Recovery (STDR) using Fiedler vector partitioning.
result Proves statistical consistency and sample complexity for accurate tree recovery.
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.
New Bayesian method improves Pareto front estimation in multitask finetuning.
problem Efficiently estimating Pareto fronts for multitask finetuning.
method Variational Model Merging using non-Gaussian posteriors.
result More flexible posteriors lead to better Pareto front estimates.
Study on merging predictors in causal and anticausal directions using CMAXENT.
problem Comparing merging predictors in causal and anticausal directions.
method Using CMAXENT as inductive bias, study differences in merging predictors.
result CMAXENT solution reduces to logistic regression in causal direction and LDA in anticausal direction.
In this paper, a similarity-driven cluster merging method is proposed for unsuper-vised fuzzy clustering. The cluster merging method is used to resolve the problem of cluster validation. Starting with an overspecified number of clusters in the data, pairs of similar clusters are merged based on the proposed similarity-…
New method merges MCMC samples without distributional assumptions.
problem Efficiently merging MCMC samples from disjoint subsets.
method Diffusion generative modelling for density approximation.
result Outperforms existing methods on high-dimensional problems.
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.
Budgeted Stochastic Gradient Descent (BSGD) is a state-of-the-art technique for training large-scale kernelized support vector machines. The budget constraint is maintained incrementally by merging two points whenever the pre-defined budget is exceeded. The process of finding suitable merge partners is costly; it can a…
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.
Efficiently estimates longitudinal networks by merging sparse networks.
problem Estimating longitudinal networks with sparse and temporal data.
method Adaptive network merging, tensor decomposition, point process.
result Significantly reduces estimation error and provides guidance for network merging.
A new method reduces task interference in model merging.
problem Model merging overlooks structural information and is susceptible to task interference.
method Task Singular Vectors (TSV) and TSV-Compress for compression and interference reduction.
result TSV-Merge significantly outperforms existing methods.
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.
Boosting strategies for merging vs. ensembling studies analyzed.
problem Deciding between merging and ensembling studies for boosting.
method Analytical transition point and bias-variance decomposition for boosting with linear learners.
result Theoretical guidelines for merging vs. ensembling studies.
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.
Deep learning algorithms for connectomics rely upon localized classification, rather than overall morphology. This leads to a high incidence of erroneously merged objects. Humans, by contrast, can easily detect such errors by acquiring intuition for the correct morphology of objects. Biological neurons have complicated…
Single global merging boosts decentralized learning performance.
problem Limited communication in decentralized learning hinders performance.
method Scheduled communication, focusing on final step with global merging.
result Single global merging improves global test performance.
Parallel neural networks estimate TVD for merging over-clustered datasets.
problem Merging over-partitioned clusters in unsupervised learning.
method Use neural networks to estimate TVD between clusters in parallel.
result Neural network estimates of TVD lead to better merge decisions.
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.
Aggregates predictions from multiple regression models using random projections and kernel methods.
problem Combining predictions from multiple regression models to improve accuracy.
method Random projection of high-dimensional feature space, followed by kernel-based consensual aggregation.
result The aggregation scheme performs similarly to using the original high-dimensional features, with high probability.
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.
In order to drive safely and efficiently under merging scenarios, autonomous vehicles should be aware of their surroundings and make decisions by interacting with other road participants. Moreover, different strategies should be made when the autonomous vehicle is interacting with drivers having different level of coop…
New methods merge discrete gradient fields from patches to correct errors.
problem Correctly merging partially defined discrete gradient fields from patches.
method Developed general and lean merging procedures for specific covering patterns.
result Corrected errors in merging discrete gradient fields from patches.
The paper extends two-step homogeneous geodesics to homogeneous Finsler spaces.
problem Extending two-step homogeneous geodesics to Finsler spaces.
method Providing sufficient conditions for (α,β) spaces and decomposable cubic spaces to have two-step Finsler geodesic orbit spaces. result Presented examples of two-step Finsler geodesic orbit spaces.
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…
Classifies two-step solvable Lie groups with SKT structures.
problem Classifying Lie groups with SKT structures.
method Shear construction and analysis of SKT shear data on Abelian Lie algebras.
result Large part of the classification for two-step solvable SKT algebras of dimension six.
We consider a method popular in the literature of associating a two-step nilpotent Lie algebra with a finite simple graph. We prove that the two-step nilpotent Lie algebras associated with two graphs are Lie isomorphic if and only if the graphs from which they arise are isomorphic.
The article improves the display of acceptable exchange ratios for merging companies.
problem Determining feasible exchange ratios for merging companies.
method Exploits a diagrammatic approach to display the bargaining region.
result Shares face upper and lower bounds for acceptable exchange ratios.
Paper introduces new actuarial-consistent valuations for insurance liabilities.
problem Valuation of insurance liabilities considering both financial and actuarial risks.
method Proposes two-step actuarial valuations and actuarial-consistent procedures.
result Actuarial-consistent valuations are equivalent to two-step actuarial valuations under coherence.
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.
The MAXENT principle helps merge datasets to infer causal effects.
problem Inferring causal effects from unobserved variables.
method Using the maximum entropy principle with causal sufficiency and faithfulness assumptions.
result Identifies causal edges among variables from merged datasets.
A critical decision point when training predictors using multiple studies is whether studies should be combined or treated separately. We compare two multi-study prediction approaches in the presence of potential heterogeneity in predictor-outcome relationships across datasets: 1) merging all of the datasets and traini…
Split-Merge MCMC (Monte Carlo Markov Chain) is one of the essential and popular variants of MCMC for problems when an MCMC state consists of an unknown number of components. It is well known that state-of-the-art methods for split-merge MCMC do not scale well. Strategies for rapid mixing requires smart and informative …
Embedding models, which learn latent representations of users and items based on user-item interaction patterns, are a key component of recommendation systems. In many applications, contextual constraints need to be applied to refine recommendations, e.g. when a user specifies a price range or product category filter. …
Proves conjecture about compatible SKT and balanced metrics on compact solvmanifolds.
problem Compact complex manifolds with both SKT and balanced metrics.
method Shear construction and classification of two-step solvable Lie algebras.
result Proves conjecture for compact two-step solvmanifolds with invariant complex structures.
Finding the optimal k-means clustering is NP-hard in general and many heuristics have been designed for minimizing monotonically the k-means objective. We first show how to extend Lloyd's batched relocation heuristic and Hartigan's single-point relocation heuristic to take into account empty-cluster and single-poin…
We prove that two-step analytic sub-Riemannian structures on a compact analytic manifold equipped with a smooth measure and Lipschitz Carnot groups satisfy measure contraction properties.
Merging datasets is a key operation for data analytics. A frequent requirement for merging is joining across columns that have different surface forms for the same entity (e.g., the name of a person might be represented as "Douglas Adams" or "Adams, Douglas"). Similarly, ontology alignment can require recognizing disti…
A Riemannian Einstein solvmanifold (possibly, any noncompact homogeneous Einstein space) is almost completely determined by the nilradical of its Lie algebra. A nilpotent Lie algebra, which can serve as the nilradical of an Einstein metric solvable Lie algebra, is called an Einstein nilradical. Despite a substantial pr…
Improved sampling for network community detection.
problem Inefficient sampling from network partition posterior distributions.
method Merge-split Markov chain Monte Carlo for efficient sampling.
result Significantly improved mixing time and correct sampling.
Locally adaptive clustering for tree delineation.
problem Tree delineation from distance data.
method Locally adaptive hierarchical cluster termination.
result Multi-scale alternative to conventional termination criteria.