Differential privacy mechanism design has traditionally been tailored for a scalar-valued query function. Although many mechanisms such as the Laplace and Gaussian mechanisms can be extended to a matrix-valued query function by adding i.i.d. noise to each element of the matrix, this method is often suboptimal as it for…
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
48 results for “Matrix Mechanism”
We propose a new input perturbation mechanism for publishing a covariance matrix to achieve -differential privacy. Our mechanism uses a Wishart distribution to generate matrix noise. In particular, We apply this mechanism to principal component analysis. Our mechanism is able to keep the positive semi-definitene…
Study asymptotics of unitary matrix elements in quantum mechanics.
problem Asymptotic behavior of unitary matrix elements in quantum mechanics.
method Uses Berezin-Toeplitz quantization and symplectic geometry.
result Recover asymptotics of Wigner's d-matrix elements for spin representations.
Matrix completion is a modern missing data problem where both the missing structure and the underlying parameter are high dimensional. Although missing structure is a key component to any missing data problems, existing matrix completion methods often assume a simple uniform missing mechanism. In this work, we study ma…
New method for efficient matrix completion with nonignorable missing data.
problem Nonignorable missing data in matrix completion.
method Nuclear norm regularized U-statistic loss function and accelerated proximal gradient algorithm.
result Near minimax optimal statistical convergence rate for nonignorable missing data.
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.
PACE-GGM uses Gaussian mechanism for private covariance estimation.
problem Private estimation of covariance matrices in high dimensions.
method Data-adaptive selection of entries, Gaussian mechanism, maximum-entropy reconstruction.
result Consistent improvements in estimation error compared to Gaussian mechanism and baselines.
New method for privacy amplification without sampling for matrix factorization.
problem Privacy amplification for differentially private model training with matrix factorization.
method Sampling-free bounds based on Rényi divergence and conditional composition.
result Stronger privacy guarantees for small ε, applicable to various matrices.
JME continually estimates data moments privately and accurately.
problem Private and accurate continual estimation of data moments.
method Uses matrix mechanism and joint sensitivity analysis.
result Improves accuracy in estimating mean and covariance with reduced noise.
We propose a version of the non-relativistic quantum mechanics in which the pure states of a quantum system are described as sections of a Hilbert (generally infinitely-dimensional) fibre bundle over the space-time. There evolution is governed via (a kind of) a parallel transport in this bundle. Some problems concernin…
Proposes a privacy-preserving recommendation system using matrix factorization and differential privacy.
problem Privacy leakage in recommendation systems when anonymizing user data is not sufficient.
method Uses matrix factorization and differential privacy via the Gaussian mechanism.
result Demonstrates excellent utility for privacy-preserving recommendation systems.
The paper discusses a pooling mechanism to induce subsampling in graph structured data and introduces it as a component of a graph convolutional neural network. The pooling mechanism builds on the Non-Negative Matrix Factorization (NMF) of a matrix representing node adjacency and node similarity as adaptively obtained …
New bounds for private matrix approximation using Gaussian noise and Dyson Brownian Motion.
problem Private approximation of symmetric matrices with Gaussian noise.
method Viewing Gaussian noise as Dyson Brownian Motion to track eigenvalue and eigenvector evolution.
result Improved bounds on Frobenius-distance utility for private matrix approximation.
Missing values challenge data analysis because many supervised and unsupervised learning methods cannot be applied directly to incomplete data. Matrix completion based on low-rank assumptions are very powerful solution for dealing with missing values. However, existing methods do not consider the case of informative mi…
Interactive privacy mechanisms improve spectral density estimation under local differential privacy.
problem Estimating spectral density of Gaussian time series with local differential privacy constraints.
method Two-stage process: Laplace mechanism followed by privatized sample analysis.
result Interactive mechanisms achieve faster rates for spectral density estimation.
Study shows attention-style models learn pairwise interactions efficiently.
problem Learning pairwise interactions in attention-style models.
method Proved minimax rate of convergence for learning pairwise interactions.
result Minimax rate is independent of embedding dimension and token number.
Decision Machines embeds decision trees into vector spaces for improved optimization.
problem Overfitting and difficulty in finding optimal decision tree structure.
method Embedding Boolean tests into a binary vector space and representing tree structure as matrices.
result Optimized decision trees with enhanced predictive power.
DMFAW improves multi-view clustering with adaptive weights and feature selection.
problem Lack of effective feature selection and empirical hyperparameter selection in existing deep matrix factorization methods.
method Introduces Deep Matrix Factorization with Adaptive Weights (DMFAW) for multi-view clustering, incorporating feature selection and dynamically updating weights using Control Theory.
result DMFAW outperforms state-of-the-art methods in clustering performance.
LoRA and privacy: Random projections help but not always.
problem Ensuring differential privacy in LoRA fine-tuning.
method Wishart projection mechanism and noisy variants.
result LoRA is not inherently private, but low-rank fine-tuning can be more private.
Kernel PCA explains self-attention mechanisms in deep learning models.
problem Understanding and explaining self-attention mechanisms in deep learning models.
method Deriving self-attention from kernel principal component analysis (kernel PCA).
result RPC-Attention, a robust attention mechanism, outperforms softmax attention in various tasks.
Several important applications, such as streaming PCA and semidefinite programming, involve a large-scale positive-semidefinite (psd) matrix that is presented as a sequence of linear updates. Because of storage limitations, it may only be possible to retain a sketch of the psd matrix. This paper develops a new algorith…
It is postulated that quantum gravity is a sum over causal structures coupled to matter via scale evolution. Quantized causal structures can be described by studying simple matrix models where matrices are replaced by an algebra of quantum mechanical observables. In particular, previous studies constructed quantum grav…
New Performer model tackles long-sequence protein modeling.
problem Challenges of training complex Transformer models for long sequences.
method Linearly scalable long-context Transformer architecture, Performer.
result Performer provides strong theoretical guarantees and is effective for protein sequence modeling.
AIM models explain deep learning in attention layers, offering solvable insights.
problem Understanding how deep learning models learn in attention layers.
method Statistical mechanics and random matrix theory.
result Closed-form predictions for Bayes-optimal generalization error and gradient descent performance.
A Convex Relaxation Approach to Generalization Analysis for Parallel Positively Homogeneous Networkscs.LG
We develop a convex relaxation method for analyzing neural network generalization.
problem Analyzing the generalization of parallel positively homogeneous networks.
method Linking non-convex ERM to a convex optimization problem over prediction functions.
result Achieved generalization bounds with almost linear sample complexity in network width.
The Social Internet of Things (SIoT), integration of the Internet of Things and Social Networks paradigms, has been introduced to build a network of smart nodes that are capable of establishing social links. In order to deal with misbehaving service provider nodes, service requestor nodes must evaluate their trustworth…
The completion of low rank matrices from few entries is a task with many practical applications. We consider here two aspects of this problem: detectability, i.e. the ability to estimate the rank reliably from the fewest possible random entries, and performance in achieving small reconstruction error. We propose a …
We present a general framework, the coupled compound Poisson factorization (CCPF), to capture the missing-data mechanism in extremely sparse data sets by coupling a hierarchical Poisson factorization with an arbitrary data-generating model. We derive a stochastic variational inference algorithm for the resulting model …
Muon optimizer simplifies matrix optimization with spectral orthogonalization.
problem Matrix optimization challenges, especially with large condition numbers.
method Simplified Muon optimizer using spectral orthogonalization of gradients.
result Simplified Muon converges linearly with independent scalar sequences, outperforming gradient descent and Adam.
Statistical Inference for Matching Decisions via Matrix Completion under Dependent Missingnessstat.ME
The paper addresses statistical inference in matching markets with dependent missingness.
problem Statistical inference for two-sided matching markets with matching-induced dependence.
method Non-convex algorithm based on Grassmannian gradient descent, debiasing and projection framework.
result Near-optimal entrywise convergence rates for various matching mechanisms.
PAN uses path integrals for graph convolution and pooling, improving GNN performance.
problem Designing efficient graph convolution and pooling for graph neural networks.
method Path integral based graph convolution and pooling using learnable weights for path lengths.
result PAN achieves state-of-the-art performance on various graph classification/regression tasks.
Constant Curvature Coefficients and Exact Solutions in Fractional Gravity and Geometric Mechanicsmath-ph
We study fractional configurations in gravity theories and Lagrange mechanics. The approach is based on Caputo fractional derivative which gives zero for actions on constants. We elaborate fractional geometric models of physical interactions and we formulate a method of nonholonomic deformations to other types of fract…
New framework explains why nonconvex methods work well in low-rank matrix estimation.
problem Nonconvex low-rank matrix estimation problems in machine learning.
method Developed a theoretical framework revealing a benign regularizer.
result Nonconvex procedures can behave well due to a disguised convexity.
Method completes mixed matrix from complex surveys with heterogeneous missingness.
problem Recovering a mixed dataframe matrix from complex survey sampling with different missingness patterns.
method Two-stage procedure: logistic regression for missingness modeling, and weighted log-likelihood maximization with low-rank constraint.
result The proposed method achieves sublinear convergence and shows superior performance compared to existing methods.
We consider cones over manifolds admitting real Killing spinors and instanton equations on connections on vector bundles over these manifolds. Such cones are manifolds with special (reduced) holonomy. We generalize the scalar ansatz for a connection proposed by Harland and Nolle in such a way that instantons are parame…
Linformer reduces transformer complexity to linear, improving efficiency.
problem High cost of training and deploying large transformer models for long sequences.
method Approximates self-attention with low-rank matrix, proposing Linformer with complexity.
result Linformer performs similarly to standard transformers but is more memory- and time-efficient.
The paper uses a Hamiltonian method to price barrier options under Vasicek interest rate model.
problem Option pricing under Vasicek interest rate model with time-varying interest rates.
method Splitting time to maturity into infinite steps and using quantum mechanics methods for matrix elements, derived pricing kernel and integral expression.
result Numerical results of option prices as functions of underlying asset price, floating rate, and regression rate.
Attention improves edge prediction in e-commerce graphs.
problem Predicting edges in graphs from node attributes in e-commerce.
method Used attention mechanism in simple feedforward networks, derived analytically tractable model AttEST.
result Attention network outperforms LSTM architectures by over 20% on F-1 score.
New neural model processes 2D data with long-range dependencies efficiently.
problem Limited receptive field of convolutions for complex 2D tasks.
method Proposes Matrix Shuffle-Exchange network with layers and complexity.
result Exceeds convolutional and graph neural network baselines in long-range dependency modeling.
The correlation matrix is the key element in optimal portfolio allocation and risk management. In particular, the eigenvectors of the correlation matrix corresponding to large eigenvalues can be used to identify the market mode, sectors and style factors. We investigate how these eigenvalues depend on the time scale of…
This work proposes a new method for simultaneous probabilistic identification and control of an observable, fully-actuated mechanical system. Identification is achieved by conditioning stochastic process priors on observations of configurations and noisy estimates of configuration derivatives. In contrast to previous w…
Matrix Factorization for Practical Continual Mean Estimation Under User-Level Differential Privacycs.LG
Novel mean estimation method under user-level differential privacy reduces noise in continual mean estimates.
problem Maintaining accurate running mean estimates under user-level differential privacy.
method Developed a novel mean estimation specific factorization under approximate differential privacy.
result Achieved asymptotically lower mean-squared error bounds in continual mean estimation.
Study uses ML techniques to reveal quantum-like features in classical systems.
problem Understanding the intuition behind unsupervised ML in physical systems.
method Three ML techniques applied to adjacency matrices of 2D particulate systems.
result ML techniques reveal quantum-like features in classical systems.
Framework for robust matrix estimation with side information.
problem High-dimensional matrix estimation with restrictive structure.
method Flexible framework decomposing matrix into four components: interaction, row, column, and residual.
result Improved imputation accuracy and treatment-effect estimation with side information.
In this paper we propose a look at the capital risk problem inspired by deterministic, known from classical mechanics, problem of juggling. We propose capital equivalents to the Newton's laws of motion and on this basis we determine the most secure form of credit repayment with regard to maximisation of profit. Then we…
Method detects neural network equivalence via matrix ensembles and spectral analysis.
problem Detecting equivalence among different deep learning architectures.
method Generating Mixed Matrix Ensembles (MMEs) and matching to conjugate circular ensembles.
result Empirical evidence shows vanishing differences in spectral densities with long tail decay rates.
The paper investigates polynomial alternatives to softmax in transformer models.
problem The effectiveness of softmax attention in transformers is questioned.
method The authors explore polynomial activations as alternatives to softmax, focusing on their ability to regularize the attention matrix.
result Certain polynomials can serve as effective substitutes for softmax in transformer applications, achieving strong performance.
Consistent estimator derived for confounding strength in observational data.
problem Estimating confounding strength in observational data is challenging due to unobserved confounders.
method Derived and adapted a consistent estimator using tools from random matrix theory.
result The original estimator is not consistent, but an adapted one is.