Study on random matrices in deep neural networks with IID entries.
problem Distribution of singular values in product of random matrices for deep neural networks.
method Random matrix theory with a streamlined approach for non-Gaussian data.
result Generalization of macroscopic universality property to non-Gaussian data.
In this note we answer a question of G. Lecué, by showing that column normalization of a random matrix with iid entries need not lead to good sparse recovery properties, even if the generating random variable has a reasonable moment growth. Specifically, for every 2≤p≤c1logd we construct a random vector …
We consider a sparse high dimensional regression model where the goal is to recover a k-sparse unknown vector β∗ from n noisy linear observations of the form Y=Xβ∗+W∈Rn where X∈Rn×p has iid N(0,1) entries and W∈Rn has iid N(0,σ2) entries. Under certa…
Study finds non-IID data causes FL performance issues.
problem Reduced performance in federated learning due to non-IID data.
method Investigated from IID to non-IID settings, categorized methods into two strategies.
result Inconsistencies in client loss landscapes are the primary cause of performance degradation.
We consider a high dimensional linear regression problem where the goal is to efficiently recover an unknown vector β∗ from n noisy linear observations Y=Xβ∗+W∈Rn, for known X∈Rn×p and unknown W∈Rn. Unlike most of the literature on this model we make no spa…
This study assesses the impact of non-IID data in federated learning, revealing significant performance drops.
problem The impact of non-IID data on federated learning model performance.
method Empirical analysis using Hellinger Distance to measure distribution differences, benchmarking four strategies for handling non-IID data.
result Significant performance drops occur at specific HD thresholds, especially for extreme non-IIDness.
Federated multi-mini-batch improves efficiency in non-IID environments.
problem Performance and communication efficiency challenges in federated learning with non-IID data.
method Introduces federated multi-mini-batch approach to balance performance and communication.
result Federated multi-mini-batch outperforms federated averaging in non-IID settings.
Quantum federated learning improves with non-IID data using one-shot communication.
problem Performance degradation in federated learning with non-IID data.
method Quantum algorithms and local density estimators for non-IID data.
result One-shot communication complexity for non-IID quantum federated learning.
FL+HC improves federated learning on non-iid data by clustering local updates.
problem FL struggles with non-iid data, leading to suboptimal models.
method Introduce hierarchical clustering to separate and train clusters of clients independently.
result FL+HC converges faster and achieves higher accuracy than standard FL.
FedCD improves non-IID federated learning performance.
problem Learning from non-IID data in federated learning.
method FedCD dynamically groups devices with similar data.
result FedCD achieves higher accuracy and faster convergence.
Machine learning experiments show IID assumption is flawed for bathymetry editing.
problem Flawed IID assumption in machine learning for bathymetry editing.
method Real-world computer-assisted labeling task, IID assumption analysis.
result Common random split leads to poor performance in machine learning.
New framework detects outliers in non-IID categorical data.
problem Existing outlier detection methods fail in non-IID data.
method Value-value graph-based representation and outlierness propagation.
result Significant improvement in AUC on complex data sets.
We consider the finite sample properties of the regularized high-dimensional Cox regression via lasso. Existing literature focuses on linear models or generalized linear models with Lipschitz loss functions, where the empirical risk functions are the summations of independent and identically distributed (iid) losses. T…
Paper argues for using functional theory of randomness for better understanding of data exchangeability and conformal prediction.
problem Understanding relationships between IID data assumptions and data exchangeability.
method Translation of conformal prediction results into the language of functional theory of randomness.
result Every confidence predictor valid for IID data can be transformed to a conformal predictor without losing much predictive efficiency.
Client adaptation improves federated learning performance with non-IID data.
problem Improving model performance in federated learning with non-identically and non-independently distributed data.
method Simulates heterogeneous clients to learn client-specific conditioning using a conditional gated activation unit.
result Client adaptation enhances model performance across balanced and imbalanced data sets from audio and image domains.
Paper proposes FedAMP for improved federated learning with non-IID data.
problem Challenges of federated learning with non-IID data.
method FedAMP: Federated attentive message passing for pairwise client collaborations.
result FedAMP improves federated learning performance with non-IID data.
This paper proposes a cooperative mechanism for mitigating the performance degradation due to non-independent-and-identically-distributed (non-IID) data in collaborative machine learning (ML), namely federated learning (FL), which trains an ML model using the rich data and computational resources of mobile clients with…
FedFMC improves federated learning on non-iid data without sharing data or increasing communication costs.
problem Efficiently updating a global model on non-iid data in federated learning.
method FedFMC dynamically forks devices into different global models, merges and consolidates them.
result FedFMC substantially improves upon earlier approaches to non-iid data in federated learning.
We prove new fast learning rates for the one-vs-all multiclass plug-in classifiers trained either from exponentially strongly mixing data or from data generated by a converging drifting distribution. These are two typical scenarios where training data are not iid. The learning rates are obtained under a multiclass vers…
Study on estimating rank-one tensors in noisy data with heavy tails.
problem Estimating rank-one spiked tensors in the presence of heavy tailed errors.
method Analysis of spectral norm of random tensors with iid entries.
result Signal strength requirements for optimal estimation are similar for heavy tailed and Gaussian noise, but vanish for noise with finite fourth moment.
Clust-PSI-PFL uses PSI to improve accuracy and fairness in federated learning.
problem Non-IID data biases federated learning performance.
method Clust-PSI-PFL uses clustering and PSI to form homogeneous groups of clients.
result Clust-PSI-PFL delivers up to 18% higher global accuracy and improves client fairness.
FedSmart optimizes federated learning models for non-IID data.
problem Model performance on non-IID data is poor and privacy is at risk.
method FedSmart optimizes models by sharing global gradients and adjusting weights based on local validation set accuracy.
result FedSmart improves model performance by allocating more weight to similar data distributions.
New learnability criteria for non-iid processes equivalent to online learning.
problem Statistical learning under non-iid stochastic processes is underdeveloped.
method Defined two learnability notions and showed their equivalence to online learning.
result Learnability criteria for non-iid processes are equivalent to online learning.
IDA adapts to non-iid data in federated learning for medical imaging.
problem Statistical heterogeneity in federated learning data, especially in medical imaging.
method IDA (Inverse Distance Aggregation) is a novel adaptive weighting approach for clients based on meta-information.
result IDA outperforms Federated Averaging in handling unbalanced and non-iid data in federated learning.
New federated learning methods improve model performance on non-IID data.
problem Improving model performance on non-IID decentralized data.
method Proposed Federated AGMs using adaptive gradient methods with first-order and second-order momenta.
result The proposed Federated AGMs converge to a first-order stationary point under non-IID and unbalanced data settings for nonconvex optimization.
On-device machine learning (ML) enables the training process to exploit a massive amount of user-generated private data samples. To enjoy this benefit, inter-device communication overhead should be minimized. With this end, we propose federated distillation (FD), a distributed model training algorithm whose communicati…
tsbootstrap handles time series uncertainty without assuming independence.
problem Time series data violate IID assumptions, leading to undercoverage in traditional methods.
method Provides various resampling and bootstrap methods, including classical and adaptive conformal calibration.
result Dependence-aware methods reduce coverage deficits, with sieve resampling performing best.
Transformers can learn noisy linear systems with depth and IID data.
problem Learning noisy linear dynamical systems with transformers.
method Theoretical analysis of multi-layer and single-layer transformers with respect to L2-testing loss. result Single-layer transformers have a non-diminishing lower bound on approximation error, suggesting depth separation.
LotteryFL improves federated learning efficiency and personalization.
problem Statistical heterogeneity and communication efficiency in federated learning.
method Exploiting Lottery Ticket hypothesis to learn compact lottery networks.
result LotteryFL achieves better personalization and reduces communication cost.
A new algorithm improves federated learning by combining knowledge distillation and weighted combination loss.
problem Non-IID client data in federated learning leads to model drift and poor generalization.
method pFedKD-WCL integrates knowledge distillation with bi-level optimization to address non-IID challenges.
result pFedKD-WCL outperforms state-of-the-art algorithms in accuracy and convergence speed.
Intensive care data are valuable for improvement of health care, policy making and many other purposes. Vast amount of such data are stored in different locations, on many different devices and in different data silos. Sharing data among different sources is a big challenge due to regulatory, operational and security r…
Federated learning enables resource-constrained edge compute devices, such as mobile phones and IoT devices, to learn a shared model for prediction, while keeping the training data local. This decentralized approach to train models provides privacy, security, regulatory and economic benefits. In this work, we focus on …
Paper proposes CCVR to improve classifier calibration in federated learning with non-IID data.
problem Improving classifier calibration in federated learning with non-IID data.
method Proposes CCVR, a simple algorithm that adjusts the classifier using virtual representations.
result CCVR achieves state-of-the-art performance on popular federated learning benchmarks.
A Bayesian treatment of latent directed graph structure for non-iid data is provided where each child datum is sampled with a directed conditional dependence on a single unknown parent datum. The latent graph structure is assumed to lie in the family of directed out-tree graphs which leads to efficient Bayesian inferen…
Optimal recovery framework for non-IID data in Hilbert spaces.
problem Generalization in non-IID data scenarios.
method Optimal recovery perspective, semidefinite programming, kernel ridgeless regression.
result Optimal recovery formula coincides with kernel ridgeless regression in some cases.
New bound for neural nets on non-iid data.
problem Generalization of deep nets for dependent data.
method Establishes a generalization bound for feed-forward neural networks on φ-mixing data. result Proves neural nets can generalize well on non-iid data.
Paper addresses generalization error bounds for learning with censored feedback.
problem Impact of censored feedback on generalization error bounds.
method Derives an extension of DKW inequality for non-IID data due to censored feedback and uses it to bound generalization error.
result Existing generalization error bounds fail to account for censored feedback, necessitating new bounds.
This paper extends the Gaussian process interpretation of deep networks to more varied weight distributions.
problem Understanding the impact of different weight initialization schemes on deep learning dynamics.
method Extending the Gaussian process interpretation to PSEUDO-IID weight distributions, including sparse and low-rank networks.
result PSEUDO-IID initialized networks are effectively equivalent up to variance, enabling tractable posterior distributions.
Fed-TDA augments federated tabular data to improve performance and privacy.
problem Non-IID data challenges in federated learning.
method Synthesizes tabular data using simple statistics for augmentation.
result Fed-TDA improves test performance and communication efficiency.
A framework for large-scale federated learning with non-IID data.
problem Stability of models trained on non-IID data in federated learning.
method Generation of non-IID datasets and modular evaluation framework.
result Open-source benchmark for large-scale federated learning research.
This work improves federated learning privacy and accuracy with non-private data sharing and approximate gradient coding.
problem Challenges of non-IID data and stragglers in federated learning.
method Data-driven strategy combining offline data sharing and approximate gradient coding.
result Achieves a trade-off between privacy and utility, leading to improved model convergence and accuracy.
FedACS uses attention to select clients with similar data for federated learning.
problem Non-IID data and data scarcity in federated learning.
method FedACS integrates an attention mechanism to prioritize clients with similar data distributions.
result FedACS improves federated learning performance by addressing non-IID data and data scarcity.
DPMM-CFL clusters clients for federated learning without fixed K, improving performance.
problem Improving federated learning performance under non-IID client heterogeneity.
method DPMM-CFL uses a Dirichlet Process Mixture Model to infer both cluster number and client assignments.
result DPMM-CFL optimizes per-cluster federated objectives and jointly infers cluster number and assignments.
Semi-Federated Learning clusters clients for efficient model training.
problem Efficiency and data distribution challenges in Federated Learning.
method Local clustering and in-cluster training with a sequential training manner.
result Semi-Federated Learning reduces communication costs and improves robustness to Non-IID data.
New methods improve distributed optimization on non-iid data.
problem Communication bottleneck in distributed machine learning models.
method Two types of distributed gradient compression methods (D-QSGD and D-EF-SGD) analyzed for non-iid data.
result D-EF-SGD performs better than D-QSGD on non-iid data but can still slow down with high data skewness.
Study of a generalized geometric Brownian motion with varying entry and exit rates.
problem Understanding the long-run behavior of economic systems with growth, volatility, entry, and exit.
method Generalized geometric Brownian motion framework with varying entry and exit rates, analyzing moments and survival probability.
result Optimal exit rate minimizes mean first-passage time, influencing system outcome.
New research shows larger language models improve data processing for diverse entries.
problem Optimizing data processing for tables with diverse string entries.
method Analytical tasks on tables with varying language model sizes and a fuzzy join benchmark.
result Larger language models improve data processing for diverse entries, but fine-tuning is necessary.
A framework for federated graph classification over non-IID graphs.
problem Training graph mining models collaboratively across different domains with non-IID graphs.
method Graph Clusters Federated Learning (GCFL) framework, dynamically finding clusters based on GNN gradients, and a gradient sequence-based clustering mechanism (GCFL+).
result Demonstrated effectiveness of GCFL+ in reducing structure and feature heterogeneity among graphs.