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.
Paper proposes ADC framework to reduce ViT SL training communication overhead.
problem Reducing communication overhead in ViT SL training.
method Two parallel compression strategies: class-agnostic merging and token discarding.
result Significantly reduces communication overhead without sacrificing accuracy.
G-CREWE efficiently aligns large networks using node embeddings and compression.
problem Efficiently aligning large networks for various applications.
method Uses node embeddings and compression to align networks at fine and coarse resolutions.
result G-CREWE achieves efficient and accurate network alignment, twice as fast as existing methods.
Proposes a new linearity-based neural network compression method.
problem Reduction of neural network model size while maintaining accuracy.
method Integrates linearity-based intuition with ReLU activation functions to merge layers.
result Achieves up to 75% reduction in model size without loss of accuracy.
HOPE uses Hilbert space to deconstruct deep network representations.
problem Deconstructing learned representations in deep networks is challenging.
method Introduces Hilbert Operator for Progressive Encoding (HOPE) to deconstruct network weights.
result HOPE provides an unbiased approach to network compression and fine-tuning.
The paper defines and studies discrete p-density and compression-radius profiles of lattice knots.
problem Understanding geometric properties of lattice knots.
method Develops a framework for discrete p-density and compression-radius profiles of lattice knots, studying them on length-filtered sets and finite move-graph exploration.
result Density and compression-radius values are not monotone, illustrating distinct optimization problems.
Deep neural network compression techniques such as pruning and weight tensor decomposition usually require fine-tuning to recover the prediction accuracy when the compression ratio is high. However, conventional fine-tuning suffers from the requirement of a large training set and the time-consuming training procedure. …
A new method reduces communication costs in distributed learning.
problem Reduces communication bottlenecks in distributed learning.
method Local SGD with communication-computation overlap and delay-corrected sparse model averaging.
result Theoretical convergence guarantees for smooth non-convex objectives.
The paper connects disentanglement to manifold charts and commutativity.
problem Discovering local charts of the data manifold for disentanglement.
method Interpreting disentanglement as local charts of the data manifold and studying commutativity.
result Commutativity is a central property in disentanglement, as shown in manifold, group theoretic, and probabilistic frameworks.
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.
Modern vehicles are equipped with increasingly complex sensors. These sensors generate large volumes of data that provide opportunities for modeling and analysis. Here, we are interested in exploiting this data to learn aspects of behaviors and the road network associated with individual drivers. Our dataset is collect…
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.
Deep reinforcement learning (DRL) on Markov decision processes (MDPs) with continuous action spaces is often approached by directly training parametric policies along the direction of estimated policy gradients (PGs). Previous research revealed that the performance of these PG algorithms depends heavily on the bias-var…
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.
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.
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.
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…
COMET is a single-pass MapReduce algorithm for learning on large-scale data. It builds multiple random forest ensembles on distributed blocks of data and merges them into a mega-ensemble. This approach is appropriate when learning from massive-scale data that is too large to fit on a single machine. To get the best acc…
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.
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.
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 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…
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.
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 …
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…
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…
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.
We propose a greedy mixture reduction algorithm which is capable of pruning mixture components as well as merging them based on the Kullback-Leibler divergence (KLD). The algorithm is distinct from the well-known Runnalls' KLD based method since it is not restricted to merging operations. The capability of pruning (in …
To backpropagate the gradients through stochastic binary layers, we propose the augment-REINFORCE-merge (ARM) estimator that is unbiased, exhibits low variance, and has low computational complexity. Exploiting variable augmentation, REINFORCE, and reparameterization, the ARM estimator achieves adaptive variance reducti…