Survey on distributed machine learning to handle large data.
problem Training large models requires vast amounts of data.
method Distribute workload across multiple machines.
result Efficient parallelization and coherent model creation.
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
48 results for “Distributed Machine Learning”
Paper explores sustainable machine learning with energy harvesting.
problem Energy-efficient distributed machine learning in resource-constrained devices.
method Developed a practical learning framework with theoretical guarantees for distributed learning over energy-harvesting devices.
result Demonstrated significant performance improvement over non-harvesting benchmarks.
This work develops secure distributed algorithms for machine learning to protect against data poisoning and network attacks.
problem Vulnerability of distributed machine learning algorithms to cyber threats.
method Game-theoretic framework to capture conflicting goals of a learner and an attacker, iterative distributed algorithm.
result Distributed SVM is prone to fail in different types of attacks, with impact depending on network structure and attack capabilities.
TonY simplifies distributed ML job management.
problem Managing distributed ML jobs is complex and resource-intensive.
method TonY is an open-source orchestrator for distributed ML jobs.
result TonY simplifies distributed ML job management.
Develops robust coresets for distributed machine learning problems.
problem Need different coresets for various machine learning problems, increasing communication overhead.
method Introduces robust coreset construction algorithms for multiple machine learning tasks.
result Established theoretical conditions and developed algorithms for generating coresets that approximate various machine learning problems.
Optimal Transport enhances machine learning with new methods.
problem Comparing and manipulating probability distributions in machine learning.
method Probabilistic framework rooted in rich history and theory.
result New solutions in generative modeling and transfer learning.
New SDE model from machine learning optimization with unique stationary distribution.
problem Stationary distribution of machine learning optimization models.
method Proved ergodicity and unique stationary distribution of power-law dynamic SDE.
result Power-law dynamic has a unique stationary distribution and is ergodic.
TBMs learn Gibbs distribution adaptively from data.
problem Combinatorial explosion in Boltzmann machines.
method Adaptive construction of minimum required sample space.
result TBMs outperform other Boltzmann machines in efficiency and effectiveness.
Survey on importance weighting in machine learning applications.
problem Distribution shift in supervised learning.
method Weighting objective function or probability distribution based on instance importance.
result Importance weighting can guarantee desirable statistical properties in distribution shift scenarios.
New approach to machine learning optimization using distribution space.
problem Optimization challenges in machine learning with non-convex constraints.
method Relaxation to convex optimization in distribution space, numerical algorithm based on mixture distributions.
result Approximate optimization in distribution space is consistent and effective.
New algorithm for safer machine learning with different testing and training distributions.
problem Challenges in modern machine learning where training and testing distributions differ.
method First-order optimization algorithm for superquantile-based learning.
result Promising numerical results show the approach's effectiveness.
The paper connects three machine learning methods to reduce generalization errors.
problem Reducing generalization errors in machine learning models.
method Distributionally robust optimization, Bayesian methods, and regularization.
result Machine learning models can be characterized using distributional uncertainty and robustness measures.
MLI is an Application Programming Interface designed to address the challenges of building Machine Learn- ing algorithms in a distributed setting based on data-centric computing. Its primary goal is to simplify the development of high-performance, scalable, distributed algorithms. Our initial results show that, relativ…
Method improves treatment effect estimation in randomized experiments.
problem Estimating distributional treatment effects in randomized experiments.
method Distributional regression framework with machine learning for variance reduction.
result The proposed method reduces variance of distributional treatment effect estimators.
Nonparametric Conditional Density Estimation In A Deep Learning Framework For Short-Term Forecastingstat.ML
Paper proposes a method for estimating tropical cyclone intensity distribution using deep learning.
problem Lack of full accounting of prediction variability in single-point forecasts.
method Smooth model over target and covariates, logistic transformation for conditional density, case-control sampling approximation.
result Method provides insights into predicted response behavior, improving decision-making and policy.
Deep learning outperforms classic machine learning in DAS event detection.
problem Event detection in Distributed Acoustic Sensing (DAS).
method Comparison of classic machine learning and image-based deep learning approaches.
result Image-based deep learning offers significantly faster event detection and execution times.
Paper proposes P-ADMM for ADMM in distributed medical machine learning with differential privacy.
problem Privacy leakage in ADMM for distributed machine learning with sensitive data.
method Integrates Gaussian noise with linearly decaying variance to provide dynamic zCDP.
result P-ADMM achieves the same convergence rate as non-private ADMM while ensuring differential privacy.
CAP-BM learns complex-valued data's amplitude and phase distributions.
problem Learning from complex-valued data with amplitude variation.
method Complex Amplitude-Phase Boltzmann machine (CAP-BM) with Gibbs sampling.
result Necessity of amplitude-amplitude coupling term in CAP-BM.
Distributed SVM algorithm improves performance in real-world applications.
problem Improving SVM performance in distributed computing environments.
method Proposes HPSVM, a distributed SVM algorithm that minimizes inter-machine communications.
result HPSVM achieves similar or better results than state-of-the-art SVM techniques.
Secure and efficient distributed learning on devices with limited communication.
problem Limited communication and security in distributed on-device learning.
method Proposes SLSGD, a robust distributed optimization algorithm with efficient communication and attack tolerance.
result Stabilizes convergence and tolerates data poisoning on a small number of workers.
The paper presents a probabilistic framework for SPD matrices in machine learning.
problem Machine learning on SPD matrices is fragmented; this paper aims to unify it.
method Unified probabilistic framework using Gaussian distributions and Bayes classifiers.
result Different SPD machine learning tools can be reinterpreted and extended using Gaussian distributions.
Chicle tackles elastic machine learning training by avoiding micro-tasks.
problem Elasticity and load balancing in distributed machine learning training.
method Chicle is a new elastic distributed training framework that exploits machine learning algorithms to implement elasticity and load balancing without micro-tasks.
result Chicle achieves performance competitive with state-of-the-art rigid frameworks while enabling elastic execution and dynamic load balancing.
We introduce DQFIM to quantify and improve generalization of quantum machine learning models.
problem Understanding and improving generalization of quantum machine learning models.
method Data quantum Fisher information metric (DQFIM) to quantify circuit parameters and training data.
result Improves generalization by breaking symmetries of training data and using a low number of training states.
Low-dimensional embedding, manifold learning, clustering, classification, and anomaly detection are among the most important problems in machine learning. The existing methods usually consider the case when each instance has a fixed, finite-dimensional feature representation. Here we consider a different setting. We as…
Learning where to learn: Training data distribution optimization for scientific machine learningcs.LG
Paper optimizes training data distribution for better model performance across various deployment conditions.
problem Improving model accuracy when deployed with parameters far from training data.
method Developed adaptive algorithms based on bilevel or alternating optimization in the space of probability measures.
result Optimized training distributions lead to models with improved sample complexity and robustness to distribution shift.
Proposes Bayesian differential privacy for machine learning.
problem Traditional differential privacy does not fit machine learning contexts.
method Bayesian differential privacy (BDP) accounting for data distribution.
result Models maintain high accuracy while providing stronger privacy guarantees.
Paper introduces elastic consistency for distributed SGD, enabling convergence analysis.
problem Training large-scale machine learning models in distributed environments.
method Introduces elastic consistency as a general consistency model for distributed SGD.
result Derives convergence bounds for various distributed SGD methods.
Study quantifies distribution shifts and uncertainties to improve machine learning model robustness.
problem Distribution shifts between training and test datasets impact model generalization and robustness.
method Synthetic data generation and quantitative measures (KL divergence, JS distance, Mahalanobis distance) to assess data similarity and model uncertainty.
result Utilizing statistical measures like Mahalanobis distance helps assess distribution shift and model uncertainty.
Machine learning techniques improve Bayesian computation for complex data.
problem Infeasible posterior computation in high-dimensional models.
method Improving posterior computation using machine learning techniques.
result Potential to enhance Bayesian computation efficiency.
Market incentivizes parties to share high-quality data for collaborative machine learning tasks.
problem Fair revenue distribution and data replication threats in collaborative machine learning markets.
method Introduces a novel payment division function robust to replication and customized output models.
result Validated assumptions and showed approximate satisfaction for commonly used models.
SwitchML accelerates machine learning training by aggregating model updates in the network.
problem Training machine learning models in parallel consumes a lot of data.
method Designing a communication primitive that uses a programmable switch to aggregate model updates.
result SwitchML reduces data exchange by up to 5.5 times, speeding up training.
TF-Replicator simplifies distributed ML for researchers.
problem Complex distributed ML code for researchers.
method Abstraction over TensorFlow, data-parallel and model-parallel.
result Strong scalability without distributed systems expertise.
We optimize distributed learning algorithms to maintain linear convergence with limited communication.
problem Limited communication time affects the convergence of distributed learning algorithms.
method We design quantizers to compress algorithm information while preserving linear convergence and characterize communication time.
result We show how to co-design machine learning and communication protocols for optimal performance.
Contrast trees assess machine learning accuracy, boosting improves performance.
problem Lack of accuracy assessment for machine learning results.
method Contrast trees and distribution boosting methods.
result Distribution boosting provides an assumption-free method for estimating outcome distributions.
Paper learns tree-structured models from distributed data efficiently.
problem Learning tree-structured Gaussian graphical models from distributed data with limited communication.
method Communication-efficient strategies for central node to learn structure from distributed data.
result Tree structure can be reliably recovered even with limited information (signs of local data samples).
Surveying machine learning for combinatorial optimization problems.
problem Hard combinatorial optimization problems with expensive or undefined solutions.
method Integrating machine learning to make decisions in optimization problems.
result Machine learning can optimize decisions in optimization problems more efficiently.
This paper reviews methods for distributed training of machine learning models from high-rate streams.
problem Training machine learning models from high-rate distributed streams in a compute- and bandwidth-limited setting.
method Recently developed methods for large-scale distributed stochastic optimization.
result There exist regimes where systems can learn from distributed, streaming data at order-optimal rates.
Paper explores Elliptical Wishart distributions in signal processing and machine learning.
problem Estimating parameters of Elliptical Wishart distributions.
method Proposes fixed point and Riemannian optimization algorithms for maximum likelihood estimation.
result Characterizes existence, uniqueness, and convergence of the MLE.
DeepGG generates graph distributions for drug discovery and molecular design.
problem Learning graph distributions for various applications.
method Improved deep graph generator based on deep state machines with graph and node embeddings.
result The state machine design favors specific graph distributions.
This paper proposes a new D2D data sharing approach to improve distributed machine learning training speed.
problem Straggler dilemma in distributed edge learning.
method Proposes a D2D data sharing approach to balance computation loads and optimize radio resource allocation.
result Significantly reduces training delay and enhances training accuracy in non-i.i.d. data environments.
A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learningcs.LG
The Gumbel-max trick and its extensions simplify sampling from categorical distributions in machine learning.
problem Sampling from categorical distributions with unnormalized probabilities.
method Extensions of the Gumbel-max trick for various applications.
result Simplified and efficient methods for sampling and gradient estimation.
DP-ADMM provides differential privacy for ADMM-based distributed learning.
problem Privacy concerns in ADMM-based distributed machine learning.
method Combines approximate augmented Lagrangian function with time-varying Gaussian noise addition.
result Achieves higher utility for general objective functions under the same differential privacy guarantee.
A Stochastic Large-scale Machine Learning Algorithm for Distributed Features and Observationsstat.ML
As the size of modern data sets exceeds the disk and memory capacities of a single computer, machine learning practitioners have resorted to parallel and distributed computing. Given that optimization is one of the pillars of machine learning and predictive modeling, distributed optimization methods have recently garne…
New regularizer for machine learning using private data.
problem Machine learning with private data.
method Distributionally-robust optimization with locally-differentially-private datasets.
result New regularizer for training linear regression models.
We study the problem of distributed multi-task learning with shared representation, where each machine aims to learn a separate, but related, task in an unknown shared low-dimensional subspaces, i.e. when the predictor matrix has low rank. We consider a setting where each task is handled by a different machine, with sa…
We consider the problem of distributed multi-task learning, where each machine learns a separate, but related, task. Specifically, each machine learns a linear predictor in high-dimensional space,where all tasks share the same small support. We present a communication-efficient estimator based on the debiased lasso and…
ATA: Adaptive Task Allocation for Efficient Resource Management in Distributed Machine Learningcs.LG
ATA optimizes task allocation in distributed machine learning.
problem Greedy task allocation leads to inefficiencies in distributed machine learning.
method Adaptive Task Allocation (ATA) adapts to unknown computation time distributions.
result ATA identifies optimal task allocation without prior knowledge of computation times.
Proposes MRO to achieve uniformly low regret in distributionally robust learning.
problem Learning under unknown test distributions (distribution shift).
method Minimax Regret Optimization (MRO) for robust machine learning.
result MRO achieves uniformly low regret across all test distributions.