Introduces a network-based framework to analyze swarm intelligence.
problem Lack of a common framework to compare swarm-based algorithms.
method Introduces an interaction network to examine swarm-based systems.
result Shows how swarm-based algorithms can be studied as systems.
New framework learns swarm behaviors from demonstrations.
problem Applying IRL to large-scale, homogeneous multi-agent systems.
method Introducing swarMDP, reducing multi-agent IRL to single-agent, proposing heterogeneous learning scheme.
result Value functions of swarm agents coincide, enabling single-agent solution.
New RL method for swarm systems improves agent communication.
problem Scaling deep RL to large homogeneous swarm systems.
method Mean embeddings of agent distributions for decentralized decision making.
result Neural network mean embedding representation enhances collective strategies.
Turing Learning infers system behavior without metrics, outperforming traditional methods.
problem Inferring complex behaviors of systems without predefined metrics.
method Simultaneously optimizes model and classifier populations using behavior data.
result Successfully infers behaviors of physical robot swarms and simulated systems.
The paper learns particle swarming models from data using Gaussian processes.
problem Understanding the link between individual interaction rules and swarming behavior.
method Proposes a learning approach using Gaussian processes to model latent radial interaction functions and scalar parameters in non-collective friction forces.
result Establishes that a coercivity condition is sufficient for recoverability and provides a finite-sample analysis showing optimal convergence rates.
DBS uses swarm intelligence to cluster data without needing a global objective function.
problem Clustering high-dimensional data with unknown natural clusters.
method Databionic swarm (DBS) system that self-organizes and adapts to data structures.
result DBS outperforms traditional clustering methods in scenarios with no prior knowledge.
Paper proposes a federated learning framework for UAV swarms, optimizing convergence rate and energy consumption.
problem Challenges of centralized ML in UAV swarms due to limited connections and large data volumes.
method Distributed federated learning within UAV swarm, joint power allocation and scheduling design.
result Joint design strategy reduces communication rounds by up to 35%.
Paper proposes communication protocols for RL in swarm robotics.
problem Learning decentralized control policies in multi-robot swarms with limited sensing and communication.
method Simple communication protocols based on histograms and task-specific information.
result Deep RL can find effective decentralized control policies using proposed communication protocols.
The ABC algorithm's social interactions are characterized through a novel interaction network.
problem Understanding complex behavior in swarm intelligence systems.
method Definition and analysis of the interaction network for the ABC algorithm.
result ABC exhibits dynamic information flow but lacks continuous coordination.
DeepSwarm uses swarm intelligence to optimize CNN architectures.
problem Optimizing Convolutional Neural Networks (CNNs).
method Ant Colony Optimization (ACO) for neural architecture search.
result DeepSwarm outperforms existing methods on MNIST, Fashion-MNIST, and CIFAR-10 datasets.
Guided deep RL for robot swarms with limited sensing.
problem Learning policies for cooperative agents with partial observability.
method Actor-critic approach with central critic for global state access.
result Algorithm successfully learned policies for swarm tasks.
ARS visualization improves t-SNE dynamics with tunable attraction and repulsion.
problem Improve data visualization techniques for complex data sets.
method ARS framework based on t-SNE dynamics with normalized interactions and tunable kernels.
result ARS visualization provides better control over cluster tightness and spacing.
Derives a fluid model for fish swarming in arbitrary dimensions.
problem Modeling fish swarming behavior in various dimensions.
method Develops a novel n-dimensional model using bundle geometry and variational formulation. result Derives the self-organized hydrodynamic model from the interacting particle system.
Model shows traders' swarm behavior in markets with subjective predictions.
problem Understanding swarm behavior in markets with traders having subjective market predictions.
method Combination of priority queueing model and mean field theory, nonlinear Markov model.
result Swarm behavior emerges due to traders' reactions to market conditions, not their subjective predictions.
MagNet uses neural networks to predict multi-agent dynamics from observations.
problem Predicting the evolution of complex multi-agent systems.
method Formulated a coupled non-linear network with ODE-based state evolution, trained a neural network to discover dynamics from observations.
result Orders of magnitude improvement in prediction accuracy over traditional models.
Swarming improves convergence speed in distributed stochastic optimization.
problem Faster convergence in distributed stochastic optimization.
method Inspired by swarming, each thread performs a stochastic gradient descent algorithm with a swarming potential, achieving better performance than a centralized algorithm.
result The swarming-based approach converges faster than a centralized algorithm, with a monotone decreasing error bound in network size and connectivity.
PolySwarm uses a swarm of LLMs to predict and arbitrage prediction markets.
problem Real-time prediction market trading and latency arbitrage inefficiencies.
method PolySwarm employs a swarm of 50 diverse LLMs, Bayesian combination, and risk-controlled execution.
result Swarm aggregation outperforms single-model baselines in prediction tasks.
In this study, we present a simple stochastic order-book model for investors' swarm behaviors seen in the continuous double auction mechanism, which is employed by major global exchanges. Our study shows a characteristic called "fat tail" is seen in the data obtained from our model that incorporates the investors' swar…
AdaSwarm optimizes deep learning models with swarm intelligence, outperforming Adam.
problem Optimization challenges in deep learning models.
method AdaSwarm uses EMPSO to approximate gradients for optimization.
result AdaSwarm outperforms Adam and handles various loss functions.
Modified swarm optimizers improve GD initialization for EEG spatial filtering.
problem Gradient Descent fails in complex, multi-scale convexity scenarios.
method Modified Swarm-based Optimizers (ICA and PSO) applied to GD initialization.
result The modified optimizers outperform baseline optimizers in EEG classification and loss function fitness.
Paper tackles missing data in high-dimensional datasets using deep learning and swarm intelligence.
problem Missing data in high-dimensional datasets, considering different mechanisms.
method Combines deep learning and swarm intelligence to estimate missing data.
result Promising approach to estimate missing data, despite longer running times.
New algorithm uses PSO to optimize DNN training parameters in distributed systems.
problem Reducing synchronization frequency in DNN training leads to poor convergence.
method Integrates PSO into distributed training to automatically compute new parameters.
result Proposed algorithm outperforms synchronous methods in distributed DNN training.
This paper reviews feature selection methods using swarm intelligence.
problem Reducing dimensionality in high-dimensional datasets.
method Comparative analysis of swarm intelligence-based feature selection methods.
result Evaluation of strengths and weaknesses of swarm intelligence-based methods.
Enhanced Particle Swarm Optimization improves ANN classification accuracy and stability.
problem Improving classification accuracy of ANN models.
method Proposes an enhanced Particle Swarm Optimization for ANN training.
result Significant improvement in classification accuracy through stability analysis.
New neural network learns set-equivariant functions efficiently.
problem Efficiently implementing and learning set-equivariant functions.
method Gated recurrent network applied iteratively to all entities and syncs with population progression.
result SWARM mappings achieve state-of-the-art performance in various applications.
Deep learning autoencoder detects bee colony anomalies.
problem Early detection of bee swarms and other unusual behaviors.
method Deep Recurrent Autoencoder model trained on sensor data.
result Autoencoder detects anomalies independent of their origin.
Optimized HMM using PSO overcomes constraints for better solutions.
problem Finding global optimal solutions for HMM parameters.
method Constrained Particle Swarm Optimization (PSO) to solve HMM parameters, re-normalization and re-mapping to enforce constraints.
result PSOHMM finds better solutions and converges faster than BWHMM.
We obtain the conditions for the emergence of the swarm intelligence effect in an interactive game of restless multi-armed bandit (rMAB). A player competes with multiple agents. Each bandit has a payoff that changes with a probability pc per round. The agents and player choose one of three options: (1) Exploit (a …
Study examines CSO algorithm for 3D swarming and tracking multiple targets.
problem Simulating and tracking multiple targets in 3D space.
method Cyclic Stochastic Optimization (CSO) algorithm implemented by mobile sensing agents.
result CSO algorithm converges in 3D space, minimizing uncertainty in targets' state estimates.
Estimates interaction laws from agent trajectories without assuming their form.
problem Inferring interaction laws from observational data in complex systems.
method Non-parametric statistical learning approach from trajectory data.
result Effectiveness demonstrated in various disciplines, including physics, opinion dynamics, and biology.
Extends FC-RAG to anytime-valid sequential coverage for language model swarms.
problem Maintain distribution-free coverage for a swarm of weak language models over time.
method Introduces Anytime-FC-RAG, a sequential extension with a summable calibration-deviation budget.
result Achieves time-uniform alarm validity and safety under predictable adaptive control.
New approach generates black-box attacks on neural networks using swarm evolutionary algorithm.
problem Adversarial samples attack neural networks.
method Swarm evolutionary algorithm for black-box attacks.
result 100% success rate on MNIST and CIFAR-10 images.
Paper uses averaging from many particle filters to approximate posterior predictive distributions.
problem Approximating posterior predictive distributions efficiently and accurately.
method Particle swarm filter algorithm that averages many particle filter approximations.
result Law of large numbers and central limit theorem support the method's effectiveness.
Optimizes K-means clustering with PSO for better accuracy.
problem Improving the accuracy of K-means clustering.
method Uses Particle Swarm Optimization (PSO) to find optimal initial centroids for K-means.
result Optimal centroids found using PSO lead to better clustering accuracy.
The paper connects PSO and CBO methods using stochastic modeling and mean-field limits.
problem Global optimization problems with particle swarm optimization and consensus based optimization.
method Stochastic differential equations and mean-field approximation to derive macroscopic hydrodynamic equations.
result Derives mean-field approximation for PSO and links it to CBO methods.
A new optimizer, MVO, improves nonlinear regression performance.
problem Finding optimal coefficients in nonlinear regression models.
method Multi-Verse Optimizer (MVO) compared to Particle Swarm Optimizer (PSO).
result MVO statistically outperforms PSO in 10 nonlinear regression problems.
AdversarialPSO uses fewer queries to create high-success-rate adversarial examples.
problem Creating imperceptible adversarial examples with high success rates in black-box settings.
method AdversarialPSO, a black-box attack using Particle Swarm Optimization.
result Achieved high success rates (99.6% on CIFAR-10, 96.3% on MNIST, 82.0% on Imagenet) with fewer queries.
PSO optimizes model parameters in nonstandard distributions.
problem Estimating model parameters in nonstandard distributions using existing algorithms.
method Particle Swarm Optimization (PSO) as an alternative optimization routine.
result PSO produces more optimal or convergent results than existing algorithms.
A new method for steering large agent populations efficiently.
problem Controlling the configuration of a swarm of identical, interacting cooperative agents.
method Mean-Field Schrodinger Bridges with Gaussian Mixture Models.
result A highly efficient parameterization to approximate optimal solutions of the MFSB problem in closed form.
Empirical comparison of 18 hyperparameter tuning algorithms for SVM.
problem Tuning hyperparameters C and γ for SVM with RBF kernel. method Compared 18 search algorithms on 115 real-life data sets.
result Trees of Parzen estimators and particle swarm optimization perform similarly to grid search.
PBO methods improve RNN performance in learning long-term dependencies.
problem Training RNNs to learn long-term dependencies is challenging.
method Population-based global optimisation (PBO) techniques, including evolution strategies and particle swarm optimisation.
result PBO methods lead to performance improvements in RNNs for volatility forecasting.
Randomized feature models learn interaction kernels from agent paths.
problem Learning interaction kernels from noisy agent paths.
method Randomized feature algorithm and sparse regression.
result Pruned features reduce overfitting and lower simulation cost.
A new time-series clustering method using slope-based similarity and PSO.
problem Clustering time-series data efficiently and accurately.
method Developed a novel slope-based similarity measure combined with Particle Swarm Optimization (PSO) for clustering.
result The proposed similarity measure outperforms existing measures in clustering time-series data.
mFI-PSO generates effective adversarial images for DNNs.
problem Vulnerability of DNNs to small perturbations in images.
method Uses mFI for pixel selection and PSO for objective functions.
result mFI-PSO effectively designs flexible adversarial images.
Detects changes in signal covariance matrix using extreme eigenvalues.
problem Detects abrupt changes in signal covariance matrix from identity to low-rank.
method Sequential detection based on extreme eigenvalues of sample covariance matrix.
result Effective detection of behavior changes in swarm data.
Transformers approximate mean-field dynamics of indistinguishable particles.
problem Approximating the dynamics of indistinguishable particles in complex systems.
method Using transformers to model the mean-field dynamics of interacting particle systems.
result Theoretical bounds on the distance between true and transformer-obtained mean-field dynamics.
Hybrid ANN model predicts firm bankruptcy with improved PSO and SA.
problem Predicting firm failure for investors and decision makers.
method Hybrid ANN model using improved PSO and SA for variable selection and optimization.
result The hybrid model outperforms in convergence and accuracy compared to traditional methods.
Optimal income crossover found using particle swarm optimization.
problem Determining the crossover point between two income distributions.
method Particle swarm optimization for finding crossover income, temperature, and Pareto index.
result Optimization method finds boundaries of two income distributions.