Research
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.

169,341 papers · 148 categories

Trend · papers per month

265177102 · Jun 202019922001200920182026
48 results for Posterior Server

Paper introduces SNEP for efficient Bayesian learning and posterior server for distributed data.

problem Efficient Bayesian learning with distributed data.
method SNEP (stochastic natural gradient expectation propagation) and posterior server architecture.
result SNEP converges and improves Bayesian learning efficiency.

Bayesian approach reduces FL communication cost by one-shot.

problem High communication cost in optimization-based FL for high-dimensional models.
method Bayesian pseudocoresets and function-space inference for one-shot FL.
result Achieves prediction performance competitive to state-of-the-art with up to 2 orders of magnitude reduction in communication cost.

New perspective on federated learning as posterior inference, improving optimization.

problem Optimizing global models in distributed learning settings.
method Formulated as posterior inference problem, using MCMC for approximate inference and federated averaging for refinement.
result Federated posterior averaging (FedPA) outperforms existing methods on benchmarks.

Improved speech recognition for voice assistants by analyzing speech data.

problem Reducing false triggers in speech-enabled assistants.
method Post-processing LVCSR hypothesis lattice with a Bidirectional Lattice Recurrent Neural Network (LatticeRNN).
result LatticeRNN significantly improves detection accuracy over traditional methods.

Lapse improves parameter servers by dynamically allocating parameters, achieving near-linear scaling.

problem Efficiently managing distributed training with reduced communication overhead.
method Integrate dynamic parameter allocation into parameter servers, proposing Lapse.
result Lapse provides near-linear scaling and can be orders of magnitude faster than existing parameter servers.

Proposes a Bayesian federated learning method for diverse tasks.

problem Current federated learning approaches focus on homogeneous tasks, ignoring task diversity.
method Integrates multi-task learning with MOGP at the local level and federated learning at the global level.
result Demonstrates superior predictive performance and uncertainty calibration on diverse tasks.

Algorithm stabilizes queues in asymmetric systems with unknown service rates.

problem Stabilizing queues in multi-class multi-server systems with unknown service rates.
method Proposes UCB and Thompson Sampling algorithms to stabilize queues while learning service rates.
result Achieves system stability with an average queue length bound of \(O(\min\{N,K\}/ε)\) for large time horizon \(T\).

Corella protects client data privacy in multi-server learning with correlated queries.

problem Protecting client data privacy in multi-server machine learning.
method Proposes a private multi-server learning approach using correlated queries and strong noise.
result Mitigates client data leakage with high accuracy and minimal computational effort.

LiuBei is a resilient ML algorithm that tolerates Byzantine workers and servers without trusting any component.

problem Byzantine failures in distributed ML solutions.
method Byzantine-resilient ML algorithm that aggregates gradients and replicates parameter servers, using a filtering mechanism and scatter/gather protocol.
result LiuBei achieves Byzantine resilience to both servers and workers and guarantees convergence, with an accuracy loss of around 5% and a 24% convergence overhead.

Paper introduces an asynchronous optimization algorithm for parameter servers.

problem Solving optimization problems with asynchrony and general regularizers.
method Asynchronous incremental aggregated gradient algorithm in a parameter server framework.
result Established linear convergence rate and step-size choices for strong convex data loss.

Paper explores differential privacy in high-dimensional federated learning, tackling server trustworthiness and estimation.

problem Maintaining privacy in distributed environments with high-dimensional data.
method Investigates scenarios with untrusted and trusted central servers, introduces novel federated estimation algorithms for linear regression models.
result Tight minimax rates depend on high-dimensionality even with sparsity assumptions, and novel algorithms handle slight variations among distributed models.

A smart device optimizes server selection for energy and latency in dynamic networks.

problem Optimizing server selection for mobile devices in edge computing with uncertainty and dynamic changes.
method Formulated as a budget-limited multi-armed bandit problem, a policy is proposed to minimize regret.
result The proposed method outperforms existing solutions in terms of energy and latency.

CSE-FSL reduces communication and storage costs in federated learning.

problem High communication and storage costs in federated learning.
method CSE-FSL uses an auxiliary network to locally update client models and sends only selected epochs' smashed data.
result Significant communication reduction with state-of-the-art convergence and model accuracy.

DSVGD improves federated learning with fewer communication rounds.

problem Federated learning scalability and trustworthiness.
method Distributed Stein Variational Gradient Descent (DSVGD) for non-parametric Bayesian inference.
result DSVGD achieves comparable accuracy and scalability to other methods, with well-calibrated predictions.

Enhanced federated learning reduces communication costs and improves model accuracy.

problem Reducing communication costs in federated learning.
method Asynchronous model update and temporally weighted aggregation.
result The proposed algorithm outperforms baseline in terms of communication cost and model accuracy.

Detects backdoors in outsourced models by replicating training steps across multiple servers.

problem Detecting backdoors in models trained on cloud providers without prior knowledge.
method Replicate training steps across multiple servers to identify deviations and malicious updates.
result 99.6% accuracy in identifying backdoored models out of 50% malicious providers.

Stanza separates convolutional and fully connected layers for faster deep learning training.

problem Heavy data transfer between workers and servers in distributed deep learning.
method Layer separation: most nodes train convolutional layers, others train fully connected layers only.
result Significant acceleration of training time (1.34x--13.9x) over current systems.

This paper improves privacy in federated learning without a trusted server.

problem Privacy in federated learning with silos that distrust each other.
method Introduces Inter-Silo Record-Level Differential Privacy (ISRL-DP) and accelerated algorithms for convex and smooth losses.
result Achieves optimal privacy and accuracy tradeoffs in federated learning.

BrainTorrent uses peer-to-peer FL for medical image segmentation without a central server.

problem Lack of sufficient annotated data for personalized medical models.
method Peer-to-peer federated learning framework without a central server.
result BrainTorrent outperforms traditional server-based FL and achieves similar performance to pooled data training.

This work provides bounds on generalization error and privacy leakage in federated learning.

problem Bounding generalization error and privacy leakage in federated learning.
method Information-theoretic framework for classical, distributed, and federated learning.
result Upper and lower bounds on generalization error and privacy leakage.

Paper tackles federated linear bandit learning with AirComp for noisy channels.

problem Minimize cumulative regret in federated linear bandit learning.
method Proposes a federated linear bandits scheme using over-the-air computation (AirComp) over noisy fading channels.
result Determines the regret bound of the proposed scheme.

Client-based machine learning uses mobile devices for computation, improving privacy and reducing data upload.

problem Exploiting mobile devices for machine learning tasks to protect privacy and reduce data upload.
method Leveraging local hardware and data on mobile devices for computation-intensive tasks, only uploading results.
result Client-based machine learning can relieve server burdens and protect user privacy.

Paper tackles nonparametric classification with privacy constraints, achieving optimal accuracy.

problem Nonparametric classification under distributed differential privacy constraints.
method Minimax and adaptive transfer learning, considering privacy, sample sizes, and heterogeneity.
result Developed an adaptive classifier achieving optimal misclassification rate with privacy constraints.

Paper proposes a GPU-based system for training massive deep learning models in ads systems.

problem Training massive deep learning models with terabyte-scale parameters in ads systems.
method Hierarchical GPU parameter server with 3-layer storage (GPU High-Bandwidth Memory, CPU main memory, SSD).
result 4-node hierarchical GPU parameter server trains a model 2X faster than a 150-node in-memory system.

DFedAvgM is a decentralized FedAvg with momentum for privacy and communication efficiency.

problem Efficiently train models with privacy and communication efficiency in federated learning.
method Decentralized Federated Averaging with Momentum (DFedAvgM) on clients connected by an undirected graph, using stochastic gradient descent with momentum and quantization.
result DFedAvgM converges under trivial assumptions and can be improved with the PŁ property, numerically verified.

Paper improves communication in distributed optimization, reducing worker-to-server data exchanges.

problem Efficiency in server-to-worker communication in distributed optimization.
method MARINA-P, a novel downlink compression method using correlated compressors; M3, combining MARINA-P with uplink compression.
result MARINA-P achieves provably superior server-to-worker communication complexity with increasing number of workers.

New strategies reduce FL's impact on client resources, enabling larger models and more users.

problem Communication bottleneck in Federated Learning on heterogeneous edge networks.
method Lossy compression and Federated Dropout to reduce client-to-server communication and local computation.
result Up to 14x reduction in server-to-client communication, 1.7x reduction in local computation, and 28x reduction in upload communication.

Byzantine-resilient federated learning with local iterations and robust mean estimation.

problem Byzantine clients disrupt federated learning with local iterations.
method Local SGD iterations, robust mean estimation, and matrix concentration result.
result Convergence analysis for strongly-convex and non-convex smooth objectives in heterogeneous data settings.

Paper studies IPG method's robustness in noisy distributed linear regression.

problem Distributed linear regression with noise.
method Iteratively Pre-conditioned Gradient-descent (IPG) method.
result IPG method's robustness against noise compared favorably to state-of-the-art algorithms.