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.

168,742 papers · 148 categories

Trend · papers per month

371013 · Jun 202019922001200920172026
48 results for Rényi DP

A(DP)2^2SGD improves federated learning privacy and efficiency.

problem Privacy and efficiency in federated learning with asynchronous decentralized parallel SGD.
method Differentially private asynchronous decentralized parallel SGD (A(DP)2^2SGD) using R{é}nyi differential privacy.
result Achieves optimal convergence rate and comparable model accuracy to SSGD but faster.

In this work we consider the gravitating vortex equations. These equations couple a metric over a compact Riemann surface with a hermitian metric over a holomorphic line bundle equipped with a fixed global section --- the Higgs field ---, and have a symplectic interpretation as moment-map equations. As a particular cas…

2016-06-24abs ↗pdf ↗

We obtain all possible solutions of a 1/4 Bogomol'nyi-Prasad-Sommerfield equation exactly, containing configurations made of walls, vortices and monopoles in the Higgs phase. We use supersymmetric U(N_C) gauge theories with eight supercharges with N_F fundamental hypermultiplets in the strong coupling limit. The moduli…

2004-05-14abs ↗pdf ↗

A new GAN loss function based on cumulant generating functions improves stability and robustness.

problem Improving the stability and performance of GANs.
method Cumulant GAN loss function based on variational R{é}nyi divergence.
result Cumulant GAN achieves linear convergence to Nash equilibrium and superior performance in image generation.

Existence and uniqueness of gravitating vortices on Riemann surfaces with specific properties.

problem Existence and uniqueness of gravitating vortices on compact Riemann surfaces.
method Existence via solving a continuity path, proving existence of singular gravitating vortices, and establishing existence of singular Einstein-Bogomol'nyi equations.
result Existence and uniqueness of gravitating vortices on Riemann surfaces with suitable properties.

The paper finds shape modes for vortices in a specific sigma model.

problem Existence of internal modes in CP1\mathbb{C}P^1 vortices.
method Developed a geometric formalism based on the Bogomol'nyi decomposition of the energy functional.
result Proved the existence of at least one shape mode for a general CP1\mathbb{C}P^1 vortex solution.

New DP-CD method outperforms DP-SGD in solving composite DP-ERM problems.

problem Privacy-preserving machine learning with differential privacy.
method Differentially Private proximal Coordinate Descent (DP-CD) for composite Empirical Risk Minimization (ERM).
result DP-CD outperforms DP-SGD due to larger step sizes and better gradient exploitation.

DOPPLER optimizes DP training with low-pass filtering, improving model accuracy.

problem Privacy concerns in deep learning models and performance degradation of DP optimizers.
method Developed DOPPLER, a low-pass filter for DP optimizers, to reduce privacy noise and enhance model quality.
result DOPPLER optimizers outperform non-DOPPLER counterparts by 3%-10% in test accuracy.

Proactive DP optimizes privacy and utility in DP-SGD with a fixed privacy budget.

problem Balancing privacy and utility in differential privacy for machine learning.
method Proposes a pro-active DP framework that allows a-priori selection of DP-SGD parameters to maximize test accuracy.
result Proactive DP can optimize utility of DP-SGD with a fixed privacy budget (ε, δ).

Framework purifies approximate differential privacy to pure differential privacy.

problem Achieving pure differential privacy from approximate differential privacy.
method Randomized post-processing with calibrated noise to eliminate δ parameter.
result First statistically and computationally efficient reduction from approximate DP to pure DP.

We consider a general 4n-dimensional quaternionic Kahler geometry with a free action of the torus T^(n+1). The toric action lifts onto the Swann bundle of the quaternionic Kahler space to a tri-holomorphic action that commutes with the standard H* action on the bundle. By matching Pedersen and Poon's generalized Gibbon…

2008-11-23abs ↗pdf ↗

This paper improves privacy accounting in decentralized FL using f-Differential Privacy.

problem Challenges in accurately quantifying privacy budget in decentralized FL.
method Develops two new f-DP-based accounting methods for decentralized FL.
result Yields tighter (ε,δ) bounds and improved utility compared to existing methods.

DP-Net uses dynamic programming for efficient deep neural network compression.

problem Efficiently compressing deep neural networks while maintaining accuracy.
method Dynamic Programming for optimal weight quantization and clustering-friendly training.
result Achieves up to 77X compression ratio on Wide ResNet with minimal accuracy loss.

We present a systematic method to construct exactly all Bogomol'nyi-Prasad-Sommerfield (BPS) multi-wall solutions in supersymmetric (SUSY) U(N_C) gauge theories in five dimensions with N_F hypermultiplets in the fundamental representation for infinite gauge coupling. The moduli space of these non-Abelian walls is found…

2004-04-26abs ↗pdf ↗

This paper improves privacy bounds for DP algorithms using ff-DP.

problem Difficulty in analyzing randomness in DP algorithms due to mixture distributions.
method Derives a closed-form expression for trade-off functions and analyzes ff-DP.
result Enhances privacy of DP-GD with random initialization and shuffling models.

New DP bootstrap method for statistical inference with improved privacy and accuracy.

problem Lack of general techniques for conducting statistical inference under differential privacy.
method DP bootstrap procedure to infer sampling distribution and construct confidence intervals.
result DP bootstrap estimates provide consistent point estimates and asymptotically valid standard CIs.

A new DP algorithm improves privacy in hashing and sampling for search and learning.

problem Improving privacy in hashing and sampling for large-scale applications.
method Combines differential privacy with one permutation hashing and bin-wise consistent weighted sampling.
result Proposes DP-OPH and DP-BCWS algorithms that enhance privacy while maintaining utility.

Gaussian DP improves reporting of ML algorithms' differential privacy guarantees.

problem Incomplete and misleading DP guarantees for ML algorithms.
method Using non-asymptotic Gaussian Differential Privacy (GDP) to provide accurate bounds on privacy profiles of ML algorithms.
result GDP captures the entire privacy profile of DP-SGD and related algorithms with virtually no error.

The paper introduces DP algorithms using random projections and sign random projections for improved privacy in machine learning.

problem Improving differential privacy in machine learning applications.
method Developed algorithms based on random projections and sign random projections, focusing on individual differential privacy (iDP) and standard differential privacy (DP).
result DP-SignOPORP and iDP-SignRP achieve superior performance in differential privacy, especially for small epsilon values.

Recent developments in differentially private (DP) machine learning and DP Bayesian learning have enabled learning under strong privacy guarantees for the training data subjects. In this paper, we further extend the applicability of DP Bayesian learning by presenting the first general DP Markov chain Monte Carlo (MCMC)…

2019-01-29abs ↗pdf ↗

Paper constructs motifs from planar tilings for DP weaves and polycatenanes.

problem Creating complex entangled structures from periodic tilings.
method Combinatorial methodology using polygonal link transformations.
result Predicting the type of motif from a given tiling and polygonal link method.

Improved regret bounds for DP-KLUCB and DP-IMED in Bernoulli bandits.

problem Minimizing regret in stochastic bandits under ε-global Differential Privacy.
method Developed DP versions of KLUCB and IMED, proving tighter lower bounds and matching upper bounds.
result DP-KLUCB and DP-IMED achieve asymptotically optimal regret under ε-global DP.

Differential privacy (DP) is a popular mechanism for training machine learning models with bounded leakage about the presence of specific points in the training data. The cost of differential privacy is a reduction in the model's accuracy. We demonstrate that in the neural networks trained using differentially private …

2019-05-28abs ↗pdf ↗

Framework evaluates privacy cost of non-private pre-processing in DP pipelines.

problem Privacy cost of non-private data-dependent pre-processing in DP machine learning pipelines.
method Establishes upper bounds on overall privacy guarantees using Smooth DP and bounded sensitivity.
result Explicit overall privacy guarantees for various pre-processing algorithms.

New DP mechanisms improve ML privacy-utility-computational tradeoffs.

problem Improving privacy in machine learning with multiple passes over data.
method Formalized DP for adaptive streams, extended matrix factorization techniques, Fourier-transform-based mechanism.
result Substantial improvements in privacy-utility-computational tradeoffs over previous methods.

A gas of NN Bogomol'nyi vortices in the Abelian Higgs model is studied on a compact Riemann surface of genus gg and area AA. The volume of the moduli space is computed and found to depend on N,gN, g and AA, but not on other details of the shape of the surface. The volume is then used to find the thermodynamic partit…

1998-07-02abs ↗pdf ↗

New DP algorithms with margin guarantees for various hypothesis sets.

problem Differential privacy in machine learning with margin guarantees.
method Developed pure and efficient DP learning algorithms for linear, kernel-based, and neural network hypotheses.
result Margin guarantees are independent of input dimension and hypothesis type.

This guide simplifies applying differential privacy to machine learning models.

problem Limited practical guidance for achieving good privacy-utility-computations in ML models.
method Comprehensive self-contained guide covering theory and practical implementation.
result Achieves best possible DP ML model with rigorous privacy guarantees.

This paper provides a method for noise-calibrated inference from DP synthetic data.

problem Inference from DP synthetic data is often miscalibrated and lacks principled uncertainty quantification.
method Release DP sufficient statistics, perform noise-calibrated likelihood-based inference, and optional synthetic data generation.
result Asymptotic normality and valid confidence intervals for the plug-in DP MLE.

Improved DP-SGD on large models achieves high accuracy on image classification tasks.

problem Differentially private image classification often degrades performance.
method Careful hyper-parameter tuning and signal propagation techniques.
result Achieved 81.4% top-1 accuracy on CIFAR-10 under (8, 10^{-5})-DP.

Differential privacy has seen remarkable success as a rigorous and practical formalization of data privacy in the past decade. This privacy definition and its divergence based relaxations, however, have several acknowledged weaknesses, either in handling composition of private algorithms or in analyzing important primi…

2019-05-07abs ↗pdf ↗

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.

DP-SGD provides privacy guarantees for all data points, but we propose output-specific DP to better account for individual examples.

problem Accounting for individual privacy guarantees in DP-SGD.
method Output-specific (ε,δ)(\varepsilon,δ)-DP and an efficient algorithm to investigate individual privacy across datasets.
result Most examples enjoy stronger privacy guarantees than the worst-case bound, and there is a correlation between training loss and privacy parameter.