Preserves sensitive data distribution for privacy while maintaining utility.
problem Protecting individual privacy while preserving data utility for specific analyses.
method Combines distribution-preserving quantization and k-member clustering.
result Demonstrates improved privacy and utility in real-world applications.
Privacy-preserving deep learning for medical data across distributed platforms.
problem Data leakage in medical platforms.
method Separates hidden layers; first layer local, others centralized for training.
result Improved learning performance with all data used during training.
Paper shows L∞-positivity and stochastic completeness are equivalent.
problem Analyzing L∞-positivity preserving property and stochastic completeness. method Using monotone approximation results for distributional solutions of −Δ+1≥0. result The L∞-positivity preserving property is equivalent to stochastic completeness. Empower efficient representation of distributions through moment-preserving methods.
problem Representing high-dimensional probability measures efficiently and accurately.
method Empower efficient representation of distributions through moment-preserving methods.
result Empowers efficient and accurate representation of high-dimensional probability measures.
Augmented bridge matching preserves coupling information between distributions.
problem Preserving the original empirical pairing in flow and bridge matching processes.
method Augmenting the velocity field with initial sample point information.
result Simple modification recovers coupling information without losing Markovian property.
Paper proposes a privacy-preserving method for estimating complex models.
problem Lack of flexibility in existing model classes for approximating data-generating processes.
method Privacy-preserving distributed estimation of generalized additive mixed models using component-wise gradient boosting.
result Proposed algorithm yields equivalent model estimates as component-wise gradient boosting on pooled data.
A new clustering method preserves data distribution.
problem Distorted cluster centers in k-means clustering.
method Distributional Clustering method ensuring cluster centers mimic data distribution.
result Cluster centers converge to data generating distribution.
Proposes lossy compression that preserves data distribution.
problem Distribution-preserving lossy compression of data.
method Optimizes rate-distortion tradeoff with distribution constraint.
result Smooth interpolation between generative model and perfect reconstruction.
Optimal transport for vector Gaussian mixtures improves efficiency and structure preservation.
problem Optimal mass transport for vector-valued Gaussian mixtures.
method Vectorizing Gaussian mixture models and studying optimal mass transport problems.
result Computational efficiency and structure preservation in optimal mass transport.
Proposes an accuracy-preserving calibration method for DNNs.
problem Calibration of deep neural networks (DNNs) to measure prediction reliability.
method Uses Concrete distribution on the probability simplex to calibrate DNNs without accuracy loss.
result The proposed method outperforms previous methods in accuracy-preserving calibration tasks.
PriDE preserves differential privacy in vertically-partitioned datasets.
problem Privacy issues in distributed machine learning with vertically-partitioned data.
method PriDE uses (ε,δ)-distributed differential privacy to ensure privacy while allowing statistical estimation. result PriDE achieves bounded estimation error compared to non-private methods in distributed settings.
The paper proves a conjecture about positivity preserving in Riemannian manifolds.
problem Proving positivity preserving for Lp functions on Riemannian manifolds. method New a-priori regularity result, Liouville type theorem, Brezis-Kato inequality.
result Proves a conjecture by M. Braverman, O. Milatovic, and M. Shubin (2002).
Proposes a method to preserve information in heterogeneous domain adaptation.
problem Preserving information in different feature spaces between domains.
method Joint information preservation method integrating paired and structural information.
result Superior performance compared to state-of-the-art HDA algorithms.
New framework explains normalizing flows' power and limitations.
problem Understanding the expressive power and limitations of normalizing flows.
method Theoretical framework for well-conditioned coupling-based normalizing flows and volume-preserving flows.
result RealNVP is distributionally universal, but volume-preserving flows are not.
Proposes a privacy-preserving sign selection method for distributed systems.
problem Sign selection in distributed differentially private settings.
method Iterative peeling of stability function combined with exponential mechanism.
result Recovery of support and signs with optimal signal-to-noise ratio.
Structure-preserving GANs learn distributions with group symmetry efficiently.
problem Learning distributions with group symmetry efficiently.
method Developed structure-preserving GANs by reducing the discriminator space and designing structured generators.
result Significantly improved sample fidelity and diversity in small data regimes.
DMT enhances deep neural networks to better preserve data structures.
problem Preserving geometric, topological, and distributional structures of data in NLDR.
method Deep manifold transformation (DMT) using cross-layer LGP constraints.
result DMT networks outperform existing NLDR methods in preserving data structures.
New method preserves privacy while detecting communities in distributed networks.
problem Privacy-preserving community detection in locally distributed multi-layer networks.
method Privacy-preserving Distributed Spectral Clustering (ppDSC) using randomized response mechanism.
result Developed a novel algorithm that maintains community structure while protecting privacy.
New distributions on manifolds for better sampling.
problem Creating flexible distributions on Riemannian manifolds.
method Area-preserving maps and isometries for constructing distributions.
result Flexibility and straightforward sampling of distributions.
New method protects sensitive data in deep learning training.
problem Protecting sensitive data in deep learning training.
method Distributed layer-partitioned training with step-wise activation functions.
result Experimental results show the method is simple and effective.
FRD protects privacy in distributed RL by sharing proxy experience memory.
problem Privacy violation in exchanging experience memory in distributed RL.
method Proposes FRD framework using proxy experience memory.
result Numerical evaluation shows FRD is effective and performance depends on proxy memory structure.
Study proves stability and uniqueness for a specific type of flow.
problem Volume-preserving mean curvature flow stability and uniqueness.
method New gradient flow calibrations for volume preservation, stability estimate in distributional solutions.
result Strong solutions are calibrated and stable under certain conditions.
Bi-Lipschitz Autoencoder ensures robust manifold preservation.
problem Non-injective autoencoders lead to poor convergence and distorted latent representations.
method Injective regularization and bi-Lipschitz relaxation.
result BLAE consistently outperforms existing methods in manifold preservation.
Diagonal transformations preserve independence structures in non-Gaussian distributions.
problem Preserving independence structures in non-Gaussian distributions.
method Diagonal nonlinear transformations of multivariate normal variables.
result Independence structures are preserved in non-Gaussian distributions under diagonal transformations.
Paper presents a new method for privacy-preserving GLMs on vertically partitioned data.
problem Privacy concerns and data sharing restrictions in collaborative data mining.
method Distributed block coordinate descent algorithm for generalized linear models.
result The method achieves accurate standard errors without additional communication cost.
This paper develops embeddings that preserve likelihood-based statistical inference.
problem Modern machine learning embeddings destroy the geometric structure required for likelihood-based inference.
method Developed a rigorous theory of likelihood-preserving embeddings and introduced the Likelihood-Ratio Distortion metric.
result Controlling the distortion Δn is necessary and sufficient for preserving inference. Survey of privacy-preserving distributed deep learning methods.
problem Protecting confidential patterns in data during distributed deep learning.
method Comparison of federated learning, split learning, large batch SGD, and privacy-preserving techniques.
result Trade-offs between computational resources, data leakage, and communication efficiency.
CoreFlow models matrix-valued distributions efficiently, preserving shared low-rank structure.
problem Learning matrix-valued distributions from high-dimensional and incomplete data.
method Low-rank flow model that learns shared row/column subspaces and trains a normalizing flow on the core.
result CoreFlow improves generation quality in few-sample regimes and remains competitive in data-rich settings.
Efficiently speeds up privacy-preserving logistic regression.
problem Privacy-preserving machine learning in collaborative studies.
method Customized numerical optimization for secure computing.
result Significant acceleration of logistic regression up to 8.1x.
This paper tackles scale-free networks by preserving their heavy-tailed vertex degree distribution.
problem Preserving the scale-free property in network embeddings.
method Proposes a 'degree penalty' principle to design algorithms that preserve the heavy-tailed degree distribution of scale-free networks.
result Our algorithms reconstruct the heavy-tailed degree distribution and outperform state-of-the-art models in network mining tasks.
FLAMECHE solves the CFL trilemma by enabling encryption-compatible metadata-based clustering.
problem The CFL trilemma: improving two dimensions of privacy, communication, and computation comes at the expense of the third.
method FLAMECHE reformulates metadata-based CFL as a distributed EM procedure, allowing compatibility with secure FL schemes.
result FLAMECHE improves the effectiveness of client models and enables encryption-compatible clustering.
SecVM preserves user privacy in training SVMs for classification tasks.
problem Training supervised classifiers on sensitive user data while maintaining privacy.
method A novel secret vector machine (SecVM) framework for training linear SVMs in a distributed, privacy-preserving manner.
result SecVM outperforms baselines in a large-scale online evaluation, preserving user privacy and classification accuracy.
Paper proposes a privacy-preserving DML framework using local randomization and ADMM perturbation.
problem Privacy concerns in distributed machine learning with sensitive user data.
method Local randomization and ADMM perturbation to provide differential privacy and heterogeneous privacy levels.
result The framework minimizes privacy losses and maintains model generalization.
Proposes a method to analyze distributed datasets without sharing original data.
problem Difficulty in centralizing large, distributed datasets due to size and privacy concerns.
method Centralizes intermediate representations instead of original datasets.
result Achieves higher prediction performance compared to individual analyses.
Privacy-preserving inference for clinical trials using differential privacy.
problem Balancing knowledge sharing and privacy in healthcare data.
method Differential privacy (DP) applied to log-linear belief updates in distributed settings.
result Differentially private, distributed inference methods outperform existing techniques.
Paper studies optimal federated learning for nonparametric regression with privacy constraints.
problem Federated learning for nonparametric regression with heterogeneous differential privacy constraints.
method Proposes distributed privacy-preserving estimators and investigates their risk properties.
result Establishes matching minimax lower bounds for global and pointwise estimation.
We examine the total mixed scalar curvature of a fixed distribution as a functional of a pseudo-Riemannian metric. We develop variational formulas for quantities of extrinsic geometry of the distribution to find the critical points of this action. Together with the arbitrary variations of the metric, we consider also v…
FedSLIM optimizes compact pattern models across distributed databases without sharing raw data.
problem Privacy-preserving federated descriptive analytics for data silos.
method Federated MDL-based framework using SLIM principle.
result FedSLIM variants preserve high-quality compression structure and recover globally informative patterns.
We study tilting subweibull distributions and their tail behavior.
problem Understanding tail behavior of subweibull distributions.
method Alternative characterizations and conditions for tail behavior preservation.
result Conditions for tail behavior preservation after exponential tilting.
InstaHide encrypts images for privacy in distributed learning.
problem Private training of deep neural networks on distributed data.
method Encryption of training images with one-time secret keys and pixel-wise masks.
result Preserves privacy with minor accuracy loss, secure against known attacks.
In this paper, we propose a geometric integrator for nonholonomic mechanical systems. It can be applied to discrete Lagrangian systems specified through a discrete Lagrangian defined on QxQ, where Q is the configuration manifold, and a (generally nonintegrable) distribution in TQ. In the proposed method, a discretizati…
This work investigates the properties of Gaussian-smoothed sliced divergences for comparing distributions.
problem Comparing probability distributions while preserving privacy.
method Investigates the theoretical properties of Gaussian-smoothed sliced Wasserstein distance and generalized versions.
result Gaussian smoothed sliced Wasserstein distance converges with a rate of \(O(n^{-1/2})\).
LEASGD improves privacy-preserving decentralized learning with lower communication costs.
problem Achieving efficient and private decentralized learning.
method Proposes LEASGD, a Leader-Follower Elastic Averaging Stochastic Gradient Descent algorithm.
result LEASGD outperforms state-of-the-art algorithms in terms of lower loss and reduced communication costs.
New method learns disentangled representations using Gromov-Monge maps.
problem Learning disentangled representations from unlabelled data.
method Introduces a novel approach based on Gromov-Monge maps to preserve geometric features while aligning data distributions.
result Demonstrates effectiveness on four benchmarks, outperforming other methods.
Proposes MRF for consistency and privacy in RF.
problem Insufficient theoretical understanding of RF's consistency and privacy.
method Introduces MRF with multinomial distributions for feature and value selection.
result Proves MRF's consistency and analyzes its privacy within differential privacy.
The paper addresses distribution mismatch in latent space operations of generative models.
problem Distribution mismatch in latent space operations of generative models.
method Distribution matching transport maps to preserve the prior distribution.
result Proposed operations give higher quality samples compared to original operations.
A statistical framework for removing unwanted data domains in machine learning.
problem Removing unwanted data domains in machine learning while preserving desired performance.
method Modeling domains as probability distributions and using hypothesis testing to select samples to remove.
result Characterization of allowable edited data distributions and removal-preservation Pareto frontiers for various distribution families.
Paper introduces algorithms for private decision tree learning.
problem Private decision tree learning in distributed settings.
method Proposes DP-TopDown, NoisyCounts, and LocalRNM.
result First utility guarantees for private decision tree learning.