New coherence parameter for GNNs with Fourier measurements improves signal recovery.
problem Characterizing generative compressed sensing with Fourier measurements.
method Subspace counting arguments and high-dimensional probability theory.
result First known restricted isometry guarantee for generative compressed sensing with subsampled isometries.
Improved sampling strategy reduces Fourier measurements for neural network signals.
problem Efficiently sampling signals from neural networks with random Fourier matrices.
method Model-adapted sampling strategy with improved sample complexity.
result Reduced sample complexity from O(kdnα∞²) to O(kdα²₂) measurements.
This paper proposes a novel framework to regularize the highly ill-posed and non-linear Fourier ptychography problem using generative models. We demonstrate experimentally that our proposed algorithm, Deep Ptych, outperforms the existing Fourier ptychography techniques, in terms of quality of reconstruction and robustn…
In this paper, we study random subsampling of Gaussian process regression, one of the simplest approximation baselines, from a theoretical perspective. Although subsampling discards a large part of training data, we show provable guarantees on the accuracy of the predictive mean/variance and its generalization ability.…
State-of-the-art methods for Convolutional Sparse Coding usually employ Fourier-domain solvers in order to speed up the convolution operators. However, this approach is not without shortcomings. For example, Fourier-domain representations implicitly assume circular boundary conditions and make it hard to fully exploit …
The problem of recovering a structured signal x∈Cp from a set of dimensionality-reduced linear measurements b=Ax arises in a variety of applications, such as medical imaging, spectroscopy, Fourier optics, and computerized tomography. Due to computational and sto…
A new method detects hallucinations in medical image restoration using Fourier Ring Correlation.
problem Detecting hallucinations in DL outputs for medical image restoration.
method sFRC (s(c)can FRC) over small patches of DL outputs and reference images.
result sFRC effectively detects hallucinations in CT and MRI restoration problems.
Enhanced privacy, utility, and efficiency through MUST subsampling.
problem Balancing privacy, utility, and computational efficiency in data analysis.
method MUltistage Sampling Technique (MUST) for privacy amplification in differential privacy.
result MUST offers stronger privacy guarantees (ϵ) than one-stage subsampling methods while maintaining similar utility and computational efficiency. The paper improves privacy accounting for discrete-valued mechanisms and the subsampled Gaussian mechanism.
problem Improving the accuracy and efficiency of differential privacy accounting for discrete outputs.
method Uses fast Fourier transform (FFT) for rigorous error analysis and accounting of privacy loss.
result Provides strict lower and upper bounds for (ε,δ)-values, demonstrating up to 75% reduction in noise variance. Enhances financial optimization under model uncertainty using subsampling.
problem Model uncertainty in financial decision-making from limited data.
method Superimposes uncertainty measure on model space, uses subsampling for model distribution approximation, adapts SGD for efficiency.
result Uncertainty measures outperform traditional methods and achieve comparable performance to Bayesian methods.
This paper presents a deep learning method for faster magnetic resonance imaging (MRI) by reducing k-space data with sub-Nyquist sampling strategies and provides a rationale for why the proposed approach works well. Uniform subsampling is used in the time-consuming phase-encoding direction to capture high-resolution im…
Improved kernel quadrature with convex weights using subsampling.
problem Constructing quadrature rules with small worst-case error.
method Combining spectral properties of the kernel with recombination results.
result Effective algorithms for constructing convex quadrature rules with i.i.d. samples.
A new model-free subsampling method using uniform designs is proposed.
problem Model-based subsampling methods are often dependent on model assumptions.
method Developed a criterion (GEFD) and a model-free subsampling method based on uniform designs.
result The proposed method outperforms random sampling and is robust under diverse model specifications.
Establish a unified framework for negative results in Fourier analysis.
problem Fourier restriction, Lp-improving, and Fourier decay problems method Quantitative understanding of geometric properties of measures
result Explicit obstructions to measure satisfying Fourier restriction, Lp-improving, or Fourier decay estimates New discrepancy function compares discrete probability measures considering space geometry.
problem Comparing discrete probability measures in a geometrically meaningful way.
method Proposes the Fourier Discrepancy Function, proving convexity, differentiability, and providing gradient formula.
result Proves the Fourier Discrepancy is convex, twice differentiable, and provides an explicit gradient formula.
Enhances privacy in federated learning with Laplacian smoothing.
problem Protecting data privacy in federated learning while maintaining model accuracy.
method Laplacian smoothing for differentially private federated learning (DP-Fed-LS).
result Improves model accuracy with differential privacy guarantee and membership privacy.
Study proposes an active subsampling method for estimating individualized thresholds in high-dimensional data.
problem Estimating optimal individualized thresholds in high-dimensional data with limited labeled samples.
method Developed a K-step active subsampling algorithm to iteratively select and label the most informative data points.
result Revealed a phase transition phenomenon in the estimation of θ with respect to the smoothness of the conditional density. New Fourier analysis method for non-uniform Boolean hypercube.
problem Non-uniform probability measures on the Boolean hypercube.
method ANOVA-based decomposition, explicit basis, least squares problem.
result Generalization of Fourier analysis for arbitrary probability measures.
Improved DNN estimator with scalable subsampling for efficient inference.
problem Efficient inference for deep neural networks (DNNs).
method Non-random subsampling technique (scalable subsampling) applied to DNNs.
result Subagged DNN estimator offers computational efficiency and accurate point estimation/prediction intervals.
Develops a faster model selection method using influence functions.
problem Time-consuming and computationally inefficient model selection.
method Model-specific data subsampling guided by influence functions.
result Empirically shows improved selection of high-quality models.
New calibration measure SSCE ensures truthful prediction, unlike existing measures.
problem Ensuring truthful calibration measures in sequential prediction.
method Introduced a new calibration measure, Subsampled Smooth Calibration Error (SSCE).
result SSCE ensures truthful prediction, while existing measures are far from truthful.
New risk measure uses Fourier analysis of stock prices.
problem Identifying speculative behavior in financial products.
method Fourier analysis applied to stock price changes.
result Speculative behavior indicated by disproportionate price changes within one week.
Random Fourier features model reconstructs wind fields from sparse measurements.
problem Reconstructing wind fields from limited data.
method Random Fourier features approximating velocity field with adaptive sampling.
result Random Fourier features model outperforms benchmarks.
Proposes a new method for nonlinear Bayesian updates using ensemble kernel regression.
problem Nonlinear and non-Gaussian Bayesian updates for complex systems.
method Combines Kalman filtering for observed components and kernel density estimation for unobserved components, with subsampling and clustering.
result Reduces estimation errors in highly nonlinear scenarios compared to standard linear updates.
Fourier representation improves KSD for infinite-dimensional data.
problem Applying KSD to infinite-dimensional data.
method Combining measure equations with kernel methods for a Fourier representation of KSD.
result KSD can separate measures in infinite-dimensional Hilbert spaces.
New Fourier features improve high-precision approximation in large-scale problems.
problem Designing scalable, high-precision Fourier features for large-scale kernel methods.
method Introducing a new family of quadrature rules that accurately approximate the Gaussian measure in higher dimensions.
result Improved approximation bounds with new Fourier features.
The paper provides theoretical guarantees for optimized sampling in compressed sensing, showing error vanishes with more measurements.
problem Theoretical and practical improvements in compressed sensing with optimized sampling schemes.
method Theoretical analysis and empirical experiments with optimized sampling schemes for subsampled unitary matrices.
result The error caused by measurement noise vanishes with an increasing number of measurements for optimized sampling schemes, assuming Gaussian noise.
New algorithm for estimating multivariate quantiles using stochastic optimal transport.
problem Estimating multivariate quantiles from data.
method Stochastic algorithm for entropic optimal transport in Banach spaces, using Fourier coefficients.
result Almost sure convergence of the stochastic algorithm in infinite-dimensional Banach spaces.
New Fourier metrics equivalent to Wasserstein distances in image processing.
problem Equivalence of Fourier-based and Wasserstein metrics in imaging problems.
method Extensions of Fourier-based metrics to handle different centers of mass and discrete measures, showing equivalence to Wasserstein distances.
result New Fourier metrics are equivalent to Wasserstein distances with explicit constants, improving runtime in image processing.
A new method selects a representative subsample for efficient kernel density estimation.
problem Selecting a representative subsample without model assumptions.
method Optimal transport techniques for model-free subsampling with an efficient algorithm.
result The selected subsample can be used for efficient density estimation with derived convergence rates and optimal bandwidth.
In this paper we demonstrate that tempering Markov chain Monte Carlo samplers for Bayesian models by recursively subsampling observations without replacement can improve the performance of baseline samplers in terms of effective sample size per computation. We present two tempering by subsampling algorithms, subsampled…
New PDMP samplers improve BNN inference with accelerated computation.
problem Inference on Bayesian Neural Networks violates independence and posterior assumptions.
method Piecewise Deterministic Markov Process (PDMP) with adaptive thinning for inhomogenous Poisson Process (IPPs) sampling.
result PDMP samplers accelerate inference in BNNs, improving accuracy and mixing performance.
This paper optimizes subsampling for large datasets using Poisson distribution.
problem Efficiently subsample large datasets for quasi-likelihood estimation.
method Derives optimal Poisson subsampling probabilities and develops a distributed subsampling framework.
result Consistent and asymptotically normal estimators are obtained.
A two-stage GPR framework with automatic kernel search and subsampling improves prediction accuracy and efficiency.
problem Inaccurate predictions due to misspecified mean and kernel functions in Gaussian Process Regression.
method Two-stage GPR, automatic kernel search, subsampling for hyperparameter initialization.
result Competitive or better performance compared to full dataset training, robust on real-world datasets.
The restricted isometry property (RIP) is a universal tool for data recovery. We explore the implication of the RIP in the framework of generalized sparsity and group measurements introduced in the Part I paper. It turns out that for a given measurement instrument the number of measurements for RIP can be improved by o…
Large sample size brings the computation bottleneck for modern data analysis. Subsampling is one of efficient strategies to handle this problem. In previous studies, researchers make more fo- cus on subsampling with replacement (SSR) than on subsampling without replacement (SSWR). In this paper we investigate a kind of…
Quantum ELMs use a quantum reservoir to learn from data, with limits on expressivity and scalability.
problem Understanding the limits of quantum ELMs for machine learning tasks.
method Decomposed QELM predictions into Fourier series to analyze expressivity and scalability.
result Expressivity of QELMs is limited by the number of Fourier frequencies and observables, and scalability is hindered by hardware noise and entanglement.
We introduce the formalism of generalized Fourier transforms in the context of risk management. We develop a general framework to efficiently compute the most popular risk measures, Value-at-Risk and Expected Shortfall (also known as Conditional Value-at-Risk). The only ingredient required by our approach is the knowle…
A significant hurdle for analyzing large sample data is the lack of effective statistical computing and inference methods. An emerging powerful approach for analyzing large sample data is subsampling, by which one takes a random subsample from the original full sample and uses it as a surrogate for subsequent computati…
We study the problem of subsampling in differential privacy (DP), a question that is the centerpiece behind many successful differentially private machine learning algorithms. Specifically, we provide a tight upper bound on the Rényi Differential Privacy (RDP) (Mironov, 2017) parameters for algorithms that: (1) subsamp…
A new method tests independence for causal discovery on discrete data.
problem Inferring causal directions on discrete and categorical data.
method Subsampling-based method to test independence between cause and mechanism.
result Our method works for both discrete and categorical data without functional model assumptions.
In this paper, we prove that we can recover the genus of a closed compact surface S in R3 from the restriction to a generic line of the Fourier transform of the canonical measure carried by S. We also show that the restriction on some line in Minkowski space of the solution of a linear wave equation who…
We consider the class of risk measures associated with optimized certainty equivalents. This class includes several popular examples, such as CV@R and monotone mean-variance. Numerical schemes are developed for the computation of these risk measures using Fourier transform methods. This leads, in particular, to a very …
Modern computer vision algorithms often rely on very large training datasets. However, it is conceivable that a carefully selected subsample of the dataset is sufficient for training. In this paper, we propose a gradient-based importance measure that we use to empirically analyze relative importance of training images …
Approaches for approximating persistent homology for large datasets.
problem Inability to compute persistent homology for large datasets.
method Multiple subsampling framework for statistical approximation of persistent homology.
result Derivation of finite sample convergence rates for empirical means of persistent homology.
New algorithm recovers sparse measures in polynomial time.
problem Recovering sparse measures from Fourier moments.
method Polynomial-time recovery method inspired by mean-field theory.
result Improves upon convex relaxation methods in specific parameter regime.
New method circumvents curse of dimensionality in Laplacian estimation.
problem High-dimensional data challenges spectral clustering and diffusion maps.
method Kernelized Laplacian estimation via reproducing kernel Hilbert space.
result Non-asymptotic statistical rates show improved performance in high dimensions.
A new method reduces variance in SGMCMC by preferentially subsampling data.
problem High variance in stochastic gradient estimates impacts sampler performance.
method Use a non-uniform probability distribution to preferentially subsample data points and adaptively adjust subsample size.
result Maintains accuracy while substantially reducing average subsample size.