Graph neural networks learn decentralized controllers from data.
problem Finding optimal decentralized controllers for autonomous agents is challenging.
method Adapting graph neural networks to handle delayed communications and ensure scalability and transferability.
result Graph neural networks can learn decentralized controllers from data, addressing the scalability and practical implementation issues of centralized controllers.
A decentralized deep RL controller improves hexapod locomotion learning.
problem Deep RL struggles with real-world legged robot control.
method Decentralized deep RL on a hexapod robot.
result Decentralized approach learns better and faster.
Study uses multi-agent reinforcement learning to control self-assembly with high-resolution external control.
problem Designing effective external control protocols for self-assembly with high-resolution control.
method Investigated a multi-agent reinforcement learning approach, comparing fully decentralized and partially decentralized strategies.
result Partially decentralized approach outperforms fully decentralized in controlling self-assembly towards target structures.
Decentralized detection avoids sharing data, controls false discoveries.
problem Global false discovery rate control in decentralized novelty detection.
method Quantized surrogate models for low-precision sharing, preserving exchangeability.
result Quantized composite scores maintain competitive statistical power with reduced communication.
A framework for decentralized optimization using first-order methods.
problem Optimization of finite sums over networked nodes.
method Decentralized first-order gradient and stochastic methods.
result General framework for undirected and directed networks.
DePAint solves MARL for agents with local constraints, privacy, and no central controller.
problem Training multi-agent systems to optimize rewards while adhering to safety constraints in a decentralized setting.
method Formulated as a decentralized constrained multi-agent Markov Decision Problem, proposed DePAint method using momentum-based decentralized policy gradient.
result First privacy-preserving fully decentralized MARL algorithm considering both peak and average constraints.
Decentralized solutions to finite-sum minimization are of significant importance in many signal processing, control, and machine learning applications. In such settings, the data is distributed over a network of arbitrarily-connected nodes and raw data sharing is prohibitive often due to communication or privacy constr…
Exploiting capacity of sewer system using decentralized control is a cost effective mean of minimizing the overflow. Given the size of the real sewer system, exploiting all the installed control structures in the sewer pipes can be challenging. This paper presents a divide and conquer solution to implement decentralize…
New proof shows D-SGD and SAM are equivalent, revealing advantages of decentralization.
problem The generalization benefits of decentralized learning.
method Proved D-SGD implicitly minimizes SAM's loss function.
result Decentralized SGD and Average-direction SAM are asymptotically equivalent.
Delegated votes in Uniswap DAO favor parties with less self-owned votes and a16z-affiliated entities.
problem Incentives for vote delegation in decentralized governance systems.
method Analysis of Uniswap governance DAO using vote delegation data.
result Vote delegation patterns suggest window-dressing around decentralization and merit-based delegation.
Improves data efficiency in multi-agent control tasks using model-based reinforcement learning.
problem Limited data efficiency in reinforcement learning for multi-agent tasks.
method Decentralized model-based policy optimization (DMPO) framework.
result DMPO achieves superior data efficiency and matches model-free methods using true models.
The paper tackles dynamic collateral control for spot-perpetual basis trading in decentralized finance.
problem Dynamic control of collateral in spot-perpetual basis trading in decentralized finance.
method Solves a static control problem and derives an asymmetric dynamic extension, validated with live execution.
result The dynamic control approach provides a more robust operating benchmark and shows significant rebalancing effects.
We consider the networked multi-agent reinforcement learning (MARL) problem in a fully decentralized setting, where agents learn to coordinate to achieve the joint success. This problem is widely encountered in many areas including traffic control, distributed control, and smart grids. We assume that the reward functio…
Improves decentralized learning by optimizing graph mixing for data heterogeneity.
problem Data heterogeneity impacts convergence in decentralized learning, but existing methods ignore this.
method Characterized and quantified the relationship between graph mixing and data heterogeneity. Proposed an optimization approach to improve convergence.
result Our approach leads to improved test performance across various tasks.
Most distributed machine learning systems nowadays, including TensorFlow and CNTK, are built in a centralized fashion. One bottleneck of centralized algorithms lies on high communication cost on the central node. Motivated by this, we ask, can decentralized algorithms be faster than its centralized counterpart? Althoug…
Privacy preserving networks can be modelled as decentralized networks (e.g., sensors, connected objects, smartphones), where communication between nodes of the network is not controlled by an all-knowing, central node. For this type of networks, the main issue is to gather/learn global information on the network (e.g.,…
Despite the increasing interest in multi-agent reinforcement learning (MARL) in multiple communities, understanding its theoretical foundation has long been recognized as a challenging problem. In this work, we address this problem by providing a finite-sample analysis for decentralized batch MARL with networked agents…
Federated framework learns causal states to predict counterfactuals without centralizing data.
problem Decentralized counterfactual reasoning in coupled industrial systems with private data.
method Federated causal representation learning in state-space systems.
result Proves convergence to centralized oracle and provides privacy guarantees.
Wide and Deep GNN learns from distributed graphs and retrain online.
problem Decentralized graph support changes over time, causing mismatch between training and testing graphs.
method Wide and Deep GNN architecture with distributed online learning.
result Convergence guarantees for online retraining of the wide part of the GNN.
We propose a decentralized Maximum Likelihood solution for estimating the stochastic renewable power generation and demand in single bus Direct Current (DC) MicroGrids (MGs), with high penetration of droop controlled power electronic converters. The solution relies on the fact that the primary control parameters are se…
Expectation maximization (EM) has recently been shown to be an efficient algorithm for learning finite-state controllers (FSCs) in large decentralized POMDPs (Dec-POMDPs). However, current methods use fixed-size FSCs and often converge to maxima that are far from optimal. This paper considers a variable-size FSC to rep…
New algorithms optimize decentralized convex optimization with near optimal communication and computation.
problem Decentralized convex optimization in large-scale machine learning and sensor networks.
method Novel algorithms combining Nesterov's acceleration, multi-consensus, and gradient-tracking.
result Achieves optimal computation and near optimal communication complexity, matching lower bounds.
Optimizes Ethena's yield strategy by controlling stETH and ETH futures positions.
problem Maximizes Ethena's yield while managing price impacts.
method Formulates and solves stochastic control problems for Ethena's yield-generating strategy.
result Explicitly determines optimal control rates for stETH and ETH futures.
Multi-agent reinforcement learning (MARL) has long been a significant and everlasting research topic in both machine learning and control. With the recent development of (single-agent) deep RL, there is a resurgence of interests in developing new MARL algorithms, especially those that are backed by theoretical analysis…
New approach estimates treatment effects from decentralized data.
problem Estimating treatment effects from multiple studies with limited data.
method Three classes of ATE estimators derived from Plug-in G-Formula.
result Asymptotic variance of estimators for linear models derived.
Electronic power inverters are capable of quickly delivering reactive power to maintain customer voltages within operating tolerances and to reduce system losses in distribution grids. This paper proposes a systematic and data-driven approach to determine reactive power inverter output as a function of local measuremen…
New algorithm for decentralized online convex optimization with unknown delays.
problem Decentralized online convex optimization with unknown, time-varying feedback delays.
method Proposes a novel algorithm that incorporates adaptive learning rates and gossip-based delay estimation.
result Achieves improved regret bounds of O(N √d tot + N √T (1-σ^2)^(1/4)) and O(N δmax ln T α) for different settings.
The implementation of optimal power flow (OPF) methods to perform voltage and power flow regulation in electric networks is generally believed to require extensive communication. We consider distribution systems with multiple controllable Distributed Energy Resources (DERs) and present a data-driven approach to learn c…
This work enables UAVs to autonomously form desired trajectories without needing a central plan.
problem Autonomous formation of complex trajectories in UAVs.
method Decentralized control system using geometric embeddings.
result Quadcopters self-organize into desired trajectories while maintaining separation.
Decor protects decentralized learning models from curious users.
problem Privacy violation in decentralized learning.
method Decor uses correlated Gaussian noises to protect local models in decentralized SGD with differential privacy guarantees.
result Decor matches central DP optimal privacy-utility trade-off for arbitrary connected graphs.
This study compares CeFi and DeFi, finding some DeFi assets are not truly decentralized.
problem Understanding the differences and boundaries between CeFi and DeFi.
method Systematic analysis covering legal, economic, security, privacy, and market manipulation aspects.
result Certain DeFi assets may not be truly decentralized and pose security risks.
Modeling financial systemic risk with optimal control theory for stability.
problem Analyzing and stabilizing systemic risk in interconnected financial entities.
method Developed a theoretical model using optimal control theory, including steps for synthesizing stabilizing controllers.
result The model ensures that the H∞ norms of the mappings from disturbance to output are less than a predefined constant, stabilizing the system. A decentralized routing framework for lunar exploration robots.
problem Routing data in intermittent connectivity lunar networks.
method Graph Attention-based Multi-Agent Reinforcement Learning (GAT-MARL).
result Higher delivery rates, no duplications, fewer packet losses.
Framework for responsible LLM deployment with human involvement and decentralized technologies.
problem Challenges in deploying LLMs for high-stakes decisions, including data security and accountability.
method Interactive human involvement through multiple iterations, decentralized technologies, and automated auditing.
result Enhanced security and accountability in LLM deployment for financial decisions.
Paper introduces ITD for detecting distributional changes in decentralized learning environments.
problem Detecting distributional changes in decentralized learning environments with data privacy and heterogeneity concerns.
method Introduces Integrated Transportation Distance (ITD) for two-sample testing in federated learning.
result ITD effectively aggregates information across distributed clients, detecting subtle distributional shifts.
A new algorithm for decentralized optimization over directed graphs.
problem Decentralized stochastic optimization over directed networks.
method Gradient tracking and S-ADDOPT algorithm with constant and decaying step-sizes.
result S-ADDOPT converges linearly with constant step-size and sublinearly with decaying step-size.
This paper considers the problem of adaptively searching for an unknown target using multiple agents connected through a time-varying network topology. Agents are equipped with sensors capable of fast information processing, and we propose a decentralized collaborative algorithm for controlling their search given noisy…
Optimizes liquidations in decentralized finance to manage credit risk.
problem Managing and liquidating positions in decentralized finance exchanges.
method Formulated as an ergodic optimal control problem, derived closed-form solutions for optimal liquidation strategies.
result Closed-form solutions balance immediate executions with price impacts and long-term rewards.
Model analyzes optimal interbank networks during liquidity shocks, revealing core-periphery structures and co-investment requirements.
problem Formation of optimal interbank networks during liquidity shocks.
method Solves system-wide optimal control problem in two settings: decentralized and centralized.
result Decentralized setting leads to less cash reserves and greater vulnerability to shocks; core banks have highest co-investment requirements.
Motivated by the emerging use of multi-agent reinforcement learning (MARL) in engineering applications such as networked robotics, swarming drones, and sensor networks, we investigate the policy evaluation problem in a fully decentralized setting, using temporal-difference (TD) learning with linear function approximati…
We consider the fully decentralized machine learning scenario where many users with personal datasets collaborate to learn models through local peer-to-peer exchanges, without a central coordinator. We propose to train personalized models that leverage a collaboration graph describing the relationships between user per…
DE-SGD shows heavy-tailed behavior in decentralized settings.
problem Heavy-tailed behavior in decentralized SGD.
method Analyzes the emergence of heavy-tails in DE-SGD, considering both quadratic and twice continuously differentiable strongly convex loss functions.
result DE-SGD exhibits heavier tails than centralized SGD, and tail behavior depends on network parameters.
Optimizes cryptocurrency trading pairs for efficiency and decentralization.
problem Finding optimal trading pairs among many cryptocurrencies without direct volume data.
method Two-stage process: 1) Fill missing values using eigenvalue decomposition with regularization, 2) Optimize pairs using branch and bound with pruning.
result Optimal trading pairs lead to more decentralized markets and better liquidity.
Swarm systems constitute a challenging problem for reinforcement learning (RL) as the algorithm needs to learn decentralized control policies that can cope with limited local sensing and communication abilities of the agents. While it is often difficult to directly define the behavior of the agents, simple communicatio…
This study compares decentralized banks and finds some lack decentralization.
problem Decentralized banks do not fully decentralize transactions as expected.
method Network analysis of transaction data from four banks using core-periphery features.
result MakerDao and Compound are more decentralized than Aave and Liquity.
A new algorithm reduces regret in multi-player bandits without collision info.
problem Decentralized multi-player multi-armed bandits with no collision info.
method EC-SIC algorithm using optimal error correction coding for reward statistics.
result Regret approaches that of centralized with collision info.
New asynchronous algorithms improve speed in decentralized optimization networks.
problem Hard convergence analysis for asynchronous decentralized optimization.
method Continuized framework to analyze heterogeneous delays in event-driven updates.
result Achieves asynchronous speedup with convergence rate controlled by eigengap weighted by local delays.
Regret analysis is challenging in Multi-Agent Reinforcement Learning (MARL) primarily due to the dynamical environments and the decentralized information among agents. We attempt to solve this challenge in the context of decentralized learning in multi-agent linear-quadratic (LQ) dynamical systems. We begin with a simp…