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.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

11 results for “gossip-based”

GADGET SVM: A Gossip-bAseD sub-GradiEnT Solver for Linear SVMscs.LG

GADGET SVM uses gossip-based distributed learning for scalable SVMs.

problem Scalability issues in traditional SVM algorithms for large datasets.

method Gossip-based distributed learning for the primal SVM formulation.

result Performance comparable to centralized and online SVM algorithms.

SVM distributed learning scalable algorithms gossip-based sub-gradient

2018-12-05abs ↗pdf ↗

Gossip-based Actor-Learner Architectures for Deep Reinforcement Learningcs.LG

Gossip-based actor-learner architectures improve deep reinforcement learning efficiency and scalability.

problem Stabilizing and scaling deep reinforcement learning through multi-simulator training.

method Gossip-based communication among actor-learners in a peer-to-peer topology, reducing synchronization.

result Gossip-based architectures outperform A2C in terms of robustness and sample efficiency.

Deep Reinforcement Learning Actor-Learner Gossip Multi-Simulator Scalability

2019-06-09abs ↗pdf ↗

Decentralized Gossip-Based Stochastic Bilevel Optimization over Communication Networksstat.ML

This paper proposes a gossip-based algorithm for distributed bilevel optimization over networks.

problem Distributed bilevel optimization over networks with limited communication.

method Gossip-based distributed bilevel learning algorithm.

result Achieves optimal sample complexities for general and strongly convex objectives.

bilevel optimization distributed learning gossip networked agents meta learning

2022-06-22abs ↗pdf ↗

Fast and Efficient Gossip Algorithms for Robust and Non-smooth Decentralized Learningcs.LG

AsylADMM improves gossip-based learning for non-smooth objectives.

problem Efficient and robust decentralized learning on edge devices.

method Asynchronous gossip algorithm for non-smooth optimization.

result AsylADMM converges faster on non-smooth problems.

Decentralized Learning Gossip Algorithms Non-Smooth Optimization Robustness Edge Devices

2026-01-28abs ↗pdf ↗

Social Learning in Multi Agent Multi Armed Banditscs.LG

A novel algorithm reduces regret in multi-agent multi-armed bandits through gossip-based communication.

problem Minimizing average cumulative regret in a large number of agents solving the same MAB problem.

method A gossip-based protocol for decentralized decision-making and communication among agents.

result Achieves significant reduction in per-agent regret and communication complexity.

Multi-Agent Systems Multi-Armed Bandits Gossip Protocol Decentralized Decision-Making Regret Minimization

2019-10-04abs ↗pdf ↗

Asynchronous Gossip Algorithms for Rank-Based Statistical Methodsstat.ML

New gossip algorithms improve robustness of rank-based statistics in decentralized systems.

problem Ensuring robustness in decentralized AI and edge intelligence systems, especially in the presence of corrupted or adversarial data.

method Developed asynchronous gossip algorithms for computing rank-based statistics.

result First convergence rate bound for asynchronous gossip-based rank estimation.

decentralized systems gossip algorithms rank-based statistics robustness two-sample hypothesis testing

2025-09-09abs ↗pdf ↗

Fully Asynchronous Policy Evaluation in Distributed Reinforcement Learning over Networkscs.LG

A novel fully asynchronous scheme for distributed reinforcement learning over networks.

problem Policy evaluation in distributed reinforcement learning over networks.

method Design of a stochastic average gradient (SAG) based distributed algorithm and push-pull augmented graph approach.

result The proposed algorithm converges at a linear rate of \(\mathcal{O}(c^k)\) with \(c\in(0,1)\) and \(k\) increasing by one per node update.

distributed reinforcement learning fully asynchronous policy evaluation stochastic average gradient push-pull augmented graph

2020-03-01abs ↗pdf ↗

Decentralized Optimization in Time-Varying Networks with Arbitrary Delayscs.LG

Novel algorithm for decentralized optimization in time-varying networks with delays.

problem Decentralized optimization in networks with communication delays.

method DT-GO algorithm, applicable to general directed graphs, converges to same complexity as centralized SGD.

result Algorithm DT-GO achieves convergence rates for convex and non-convex objectives, similar to centralized SGD.

Decentralized Optimization Time-Varying Networks Gossip Algorithm Communication Delays Stochastic Gradient Descent

2024-05-29abs ↗pdf ↗

Asynchronous speedup in decentralized optimizationmath.OC

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.

decentralized optimization asynchronous algorithms straggler problem heterogeneous delays event-driven updates

2021-06-07abs ↗pdf ↗

Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communicationcs.LG

Novel gossip algorithms reduce communication in decentralized stochastic optimization with compressed updates.

problem Decentralized stochastic optimization with limited communication.

method Proposed CHOCO-SGD and CHOCO-GOSSIP algorithms for unbiased and biased compression, achieving linear convergence.

result Both algorithms outperform state-of-the-art, reducing communication by at least two orders of magnitude.

decentralized optimization stochastic gradient descent gossip algorithms compressed communication machine learning

2019-02-01abs ↗pdf ↗

Decentralized Online Convex Optimization with Unknown Feedback Delaysstat.ML

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.

Decentralized Optimization Online Convex Optimization Unknown Delays Federated Learning Sensor Networks

2026-01-12abs ↗pdf ↗