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

86171257342 · Jun 202019922001200920172026
48 results for Gaussian noise injections

GNIs induce a regulariser that penalizes high-frequency components in neural network activations.

problem Understanding the regularizing effect of Gaussian noise injections on neural network activations.
method Deriving the explicit regularizer by marginalizing out injected noise and analyzing its effect in the Fourier domain.
result GNIs induce a regularizer that produces calibrated classifiers with large margins.

GNIs induce asymmetric heavy-tailed noise in SGD, affecting network performance.

problem The effect of Gaussian noise injections on SGD dynamics and network performance.
method Developed a Langevin-like SDE driven by asymmetric heavy-tailed noise to model the modified SGD dynamics.
result GNIs induce an implicit bias that varies with noise heaviness and asymmetry, affecting network performance.

This paper connects noise injection to Bayesian inference for neural networks, improving model uncertainty.

problem Improving the reliability and confidence of neural network predictions through uncertainty quantification.
method Introducing noise into neural network parameters during training and inference to estimate prediction uncertainty.
result The MCNI method outperforms baseline models in regression and classification tasks.

We present a noise-injected version of the Expectation-Maximization (EM) algorithm: the Noisy Expectation Maximization (NEM) algorithm. The NEM algorithm uses noise to speed up the convergence of the EM algorithm. The NEM theorem shows that injected noise speeds up the average convergence of the EM algorithm to a local…

2018-01-12abs ↗pdf ↗

Enhances deep learning robustness to noise without sacrificing clean data accuracy.

problem Robustness of deep neural networks to input noise.
method Discriminative loss at penultimate layer and class-wise feature alignment with Gaussian noise.
result Improves robustness to various perturbations without degrading clean data accuracy.

Colored noise improves neural network robustness against adversarial attacks.

problem Vulnerability of neural networks to adversarial perturbations.
method Injection of colored noise into network weights and activations during adversarial training.
result Our approach outperforms previous methods in terms of adversarial accuracy on CIFAR-10 and CIFAR-100 datasets.

Proposes a differentially private bandit algorithm reducing noise over time.

problem Privacy concerns in interactive recommendation systems.
method Tree-based mechanism to add Laplace or Gaussian noise to model parameters, focusing on dynamic global sensitivity.
result Demonstrates (ε,δ)(ε, δ)-differential privacy with reduced noise and improved regret.

Noise injection regularizes Hessian, improving neural network training and generalization.

problem Regularizing over-parameterized neural networks with nonconvex and nonlinear geometry.
method Injecting isotropic Gaussian noise into weight matrices and designing a two-point estimate of the Hessian penalty.
result Effective regularization of Hessian improves generalization, achieving up to 2.4% test accuracy increase.

Neural Ordinary Differential Equation (Neural ODE) has been proposed as a continuous approximation to the ResNet architecture. Some commonly used regularization mechanisms in discrete neural networks (e.g. dropout, Gaussian noise) are missing in current Neural ODE networks. In this paper, we propose a new continuous ne…

2019-06-05abs ↗pdf ↗

Geometry-aware noise improves model generalization on complex manifolds.

problem Improving model generalization on highly curved data manifolds.
method Add geometry-aware noise to input space, projecting Gaussian noise onto tangent space of manifold and mapping it via geodesic curve.
result Geometry-aware noise leads to improved generalization and robustness on highly curved manifolds.

Privacy-preserving SGD with heavy-tailed noise achieves differential privacy guarantees.

problem Privacy preservation in noisy SGD with heavy-tailed noise.
method Differential privacy guarantees for SGD with heavy-tailed noise.
result SGD with heavy-tailed perturbations achieves (0,O(1/n))(0, O(1/n))-DP.

It has been shown that injecting noise into the neural network weights during the training process leads to a better generalization of the resulting model. Noise injection in the distributed setup is a straightforward technique and it represents a promising approach to improve the locally trained models. We investigate…

2018-09-27abs ↗pdf ↗

FCNv2 robustness tested under noise and random initial conditions.

problem Assessing AI weather forecasting model robustness to input noise.
method Two experiments with varying noise levels and random initial conditions.
result FCNv2 preserves hurricane features under low to moderate noise, but underestimates intensity and persistence.

Privacy-preserving crypto exchanges adjust prices based on Gaussian noise.

problem Ensuring fair pricing in privacy-preserving cryptocurrency exchanges.
method Derive Kyle equilibrium with Gaussian noise perturbation, rescaling price-impact and strategy factors.
result Identify a privacy subsidy as a transfer from LP pool to traders, invariant to noise.

Noise injection before gradient steps helps in regularization for neural networks.

problem Improving generalization in overparametrized neural networks.
method Injecting small noise perturbations before computing gradient steps, especially in layer-wise fashion.
result Small noise perturbations can explicitly regularize neural networks without variance explosion.

S-SGD adds symmetrical noise to weights to avoid sharp minima in deep learning.

problem SGD does not always converge to a flat minimum, leading to poor generalization.
method Symmetrical weight noise injection in SGD.
result S-SGD outperforms conventional SGD and weight-noise injection methods in large batch training.

DLPM replaces Gaussian noise with α-stable noise in DDPM, improving data distribution coverage and robustness.

problem Handling mode collapse and class imbalance in datasets with heavy-tailed noise.
method Extending DDPM to use α-stable noise, simplifying the process with elementary proof techniques.
result DLPM yields better coverage of data distribution tails, improved robustness to unbalanced datasets, and faster computation times.

Noise injection (NI) is an efficient technique to mitigate over-fitting in neural networks (NNs). The Bernoulli NI procedure as implemented in dropout and shakeout has connections with l1l_1 and l2l_2 regularization for the NN model parameters. We propose whiteout, a family NI regularization techniques (NIRT) through i…

2016-12-05abs ↗pdf ↗

Noise injection improves inference privacy in DNN models.

problem Malicious servers can infer sensitive attributes from input data.
method Adaptive Noise Injection (ANI) using a lightweight DNN on the client.
result Significant improvement in privacy (up to 48.5% degradation in sensitive-task accuracy with <1% degradation in primary accuracy).

Improves generative models by adding jump-diffusion noise.

problem Limited performance of diffusion models in generating samples from unknown distributions.
method Generalizes diffusion processes to include jump-diffusion noise, deriving closed-form generalized score functions.
result Jump-diffusion models outperform Gaussian models in specific parameter regimes.

Noise in RNNs promotes flatter minima and more stable dynamics.

problem Understanding and optimizing the training of RNNs with noise.
method Formalizing RNNs as stochastic differential equations and analyzing the effect of noise in the hidden states.
result Noise injection in RNNs leads to flatter minima, more stable dynamics, and improved robustness.

Stochastic Gradient Hamiltonian Monte Carlo (SGHMC) is a momentum version of stochastic gradient descent with properly injected Gaussian noise to find a global minimum. In this paper, non-asymptotic convergence analysis of SGHMC is given in the context of non-convex optimization, where subsampling techniques are used o…

2019-03-25abs ↗pdf ↗

Efficiently calculates privacy guarantees for 2020 Census data.

problem Evaluate privacy guarantees for 2020 U.S. Census data releases.
method Sieve-accelerated quadrature method to evaluate tail probabilities of high-dimensional convolutions.
result Achieves 1,824-fold speedup over prior methods while maintaining error tolerances.

Paper develops robust neural network sensors for fuel injection quantities.

problem Adversarial noise increases error in standard neural network models for fuel injection measurements.
method Apply provable robust network learning and verification methods to fuel injection measurements.
result Provable robust model reduces mean relative error to 16.5% under sensor noise.

Stochastic Gradient Langevin Dynamics (SGLD) is a sampling scheme for Bayesian modeling adapted to large datasets and models. SGLD relies on the injection of Gaussian Noise at each step of a Stochastic Gradient Descent (SGD) update. In this scheme, every component in the noise vector is independent and has the same sca…

2018-06-07abs ↗pdf ↗

Proposes a method to generate private synthetic data in a decentralized setting using correlated noise.

problem Challenges of generating private synthetic data in a decentralized setting with limited client data.
method Integrates CAPE protocol into federated DP-CDA framework to generate anti-correlated noise.
result Improves privacy-utility trade-off in federated setting compared to centralized approach.

New method for certified unlearning reduces noise injection.

problem Achieving formal unlearning guarantees with adaptive noise calibration.
method Adaptive per-instance noise calibration based on individual data point sensitivities.
result Derivation of high-probability per-instance sensitivity bounds for ridge regression.

This paper examines the assumptions of the derived equivalence between dropout noise injection and L2L_2 regularisation for logistic regression with negative log loss. We show that the approximation method is based on a divergent Taylor expansion, making, subsequent work using this approximation to compare the dropout …

2019-05-27abs ↗pdf ↗

A new method for feature selection robust to noise and design variability.

problem Feature selection in high-dimensional regression under sampling variability and measurement error.
method Injects controlled additive noise into the design matrix, fits a base selector, and aggregates selection frequencies.
result Improved robustness compared to Stability Selection and standard base selectors.

Self-supervised method enhances ultrasound images without needing clean targets.

problem Multiplicative speckle, acquisition blur, and scanner artifacts hamper ultrasound interpretation.
method Physics-guided degradation model trained on rotated/cropped patches with synthesized inputs.
result Achieves highest PSNR/SSIM across Gaussian and speckle noise levels, with significant improvements in heavy noise conditions.

Latent Noise Injection improves synthetic data generation for privacy and statistical alignment.

problem Slow convergence of generative models in high-dimensional settings.
method Latent Noise Injection using Masked Autoregressive Flows (MAF).
result Synthetic data closely reflects the underlying distribution, especially in high-dimensional settings.

SymNoise improves language model fine-tuning by 6.7% over NEFTune, using symmetric noise.

problem Improving performance of language models through noise-based fine-tuning.
method Introducing SymNoise, a new fine-tuning method using symmetric noise in embeddings.
result SymNoise increases model performance by 69.04% on AlpacaEval compared to NEFTune's 64.69%.

Study on Langevin dynamics for recovering planted signals in spiked matrix models.

problem Recovering a planted signal in spiked matrix models.
method Path-wise characterization of overlap using integro-differential equations and explicit formula derivation.
result Sharp phase transition in limiting overlap: positive in one regime, zero in another due to injected noise.

The paper studies ray transforms on surfaces with negative curvature, proving injectivity and determining connections and Higgs fields.

problem Injectivity of ray transforms on surfaces with negative curvature and determination of connections and Higgs fields.
method Analysis of Gaussian thermostats on compact Riemannian surfaces with negative curvature, proving injectivity and determining connections and Higgs fields.
result Injectivity of the thermostat ray transform and determination of connections and Higgs fields.

Enhances DIM to match learned representations to a specific distribution.

problem Learning representations conforming to a specific distribution.
method Injecting noise into normalized outputs of the encoder while keeping the InfoMax training objective.
result Learning uniformly and normally distributed representations, as well as representations of other absolutely continuous distributions.