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.

168,695 papers · 148 categories

Trend · papers per month

98196293391 · Jun 202019922001200920172026
48 results for gradient degradation

Combines Integrated Gradients and PatternAttribution into PGIG, outperforming alternatives.

problem Improving neural network explainability methods.
method Combines Integrated Gradients and PatternAttribution into Pattern-Guided Integrated Gradients (PGIG).
result PGIG outperforms other explainability methods in a large-scale image degradation experiment.

This paper improves federated learning for industrial predictive analytics by accommodating client heterogeneity.

problem Traditional federated models assume homogeneity in degradation processes, which doesn't apply to industrial settings.
method Personalized federated prognostic model using proximal gradient descent algorithm for joint parameter estimation.
result The proposed model enhances performance and provides comprehensive failure time distributions.

DGPs with variational inference suffer from SNR issues that degrade gradient estimates, leading to unreliable training.

problem SNR issues in gradient estimates for DGPs with variational inference.
method Adapted doubly reparameterized gradient estimators for DGP training.
result Fix improves predictive performance of DGP models.

New algorithm improves multitask learning across diverse agents.

problem Performance degradation in decentralized learning with heterogeneous objectives.
method Developed an exact subspace diffusion algorithm for multitask learning over networks.
result The algorithm outperforms alternatives in noisy gradient approximations.

This paper improves deep learning models' accuracy with differential privacy using gradient encoding and denoising.

problem Deep learning models leak sensitive information about their training datasets.
method Gradient encoding to map gradients to a smaller vector space, and denoising for post-processing.
result Our technique achieves better model accuracy with differential privacy guarantees compared to state-of-the-art methods.

Develops new bounds for deterministic samplers in diffusion models.

problem Analyzing deterministic samplers in diffusion generative models.
method Operational interpretation of deterministic sampling; restoration and degradation steps.
result First polynomial convergence bounds for DDIM-type samplers.

AdaScale SGD adapts learning rates for large-batch training efficiently.

problem Adapting learning rates for large-batch training to balance speed-ups and model quality.
method Adaptive learning rate adaptation based on gradient variance.
result AdaScale achieves reliable speed-ups for a wide range of batch sizes without degrading model quality.

Study finds non-IID data causes FL performance issues.

problem Reduced performance in federated learning due to non-IID data.
method Investigated from IID to non-IID settings, categorized methods into two strategies.
result Inconsistencies in client loss landscapes are the primary cause of performance degradation.

Gradient coding is a technique for straggler mitigation in distributed learning. In this paper we design novel gradient codes using tools from classical coding theory, namely, cyclic MDS codes, which compare favorably with existing solutions, both in the applicable range of parameters and in the complexity of the invol…

2017-07-12abs ↗pdf ↗

Develops a nonlocal PINN framework using PDDO for better solution of PDEs with sharp gradients.

problem Dealing with sharp gradients in solutions of PDEs using traditional PINN approaches.
method Integrates long-range interactions (nonlocality) into PINN using Peridynamic Differential Operator (PDDO).
result Nonlocal PINN approach improves solution accuracy and parameter inference for problems with sharp gradients.

Optimal gradient quantization reduces communication costs in distributed deep learning.

problem High communication costs in distributed training of deep neural networks.
method Deduced optimal gradient quantization conditions for binary and multi-level quantization, developed novel schemes for dynamic quantization levels.
result Demonstrated superior performance of proposed quantization schemes on CIFAR and ImageNet datasets.

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.

Artificial neural network (ANN) provides superior accuracy for nonlinear alternating current (AC) state estimation (SE) in smart grid over traditional methods. However, research has discovered that ANN could be easily fooled by adversarial examples. In this paper, we initiate a new study of adversarial false data injec…

2019-06-26abs ↗pdf ↗

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.

SpecGD mitigates misalignment in phase retrieval models with anisotropic inputs.

problem Misalignment during gradient descent in phase retrieval models with anisotropic inputs.
method Spectral gradient descent modifies gradient updates to preserve directional information and remove spike amplification.
result SpecGD removes spike amplification, leading to stable alignment and accelerated noise contraction.

BinaryDuo improves BNNs by coupling binary activations, outperforming state-of-the-art models.

problem Gradient mismatch in BNNs due to binarizing activations.
method Using gradient of smoothed loss function to estimate gradient mismatch, proposing BinaryDuo scheme with coupled ternary activations.
result BinaryDuo outperforms state-of-the-art BNNs on various benchmarks.

Unified framework reduces NFEs for inverse problems.

problem High computational costs and degraded reconstruction quality in existing LDM-based inverse solvers.
method Consistency Regularised Gradient Flows for posterior sampling and prompt optimization.
result Significantly reduced computational cost with state-of-the-art performance.

New algorithm maintains privacy while improving model performance in selective release.

problem Privacy degradation and slow convergence in DPSGD.
method Differentially Private Selective Release based on Clipped Gradients (DPSR-CG).
result Maintains strict privacy guarantees while achieving exceptional model performance.

Develops a new method to improve performance in multi-objective learning problems.

problem Gradient bias in multi-objective learning leading to degraded performance.
method Stochastic Multi-objective gradient Correction (MoCo) method that guarantees convergence without increasing batch size.
result Demonstrates effectiveness of MoCo method in simulations on multi-task learning.

Statistical test detects model degradations in optimized language models.

problem Detecting model degradations in optimized language models.
method Statistical hypothesis testing framework based on McNemar's test.
result Even small accuracy degradations (0.3%) can be attributed to actual degradations, not noise.

BNCR-GAN improves GANs to generate clean images from degraded inputs.

problem Generating clean images from blurred, noisy, and compressed degraded inputs.
method Multiple-generator model with image, blur-kernel, noise, and quality-factor generators, using masking architectures and adaptive consistency losses.
result BNCR-GAN effectively learns clean image generators from degraded images without degradation parameters.

In this work we study generalization of neural networks in gradient-based meta-learning by analyzing various properties of the objective landscapes. We experimentally demonstrate that as meta-training progresses, the meta-test solutions, obtained after adapting the meta-train solution of the model, to new tasks via few…

2019-07-16abs ↗pdf ↗

Boosted GFlowNets improve exploration by sequentially training GFlowNets with residual rewards.

problem GFlowNets struggle to evenly explore reward landscapes, leading to poor coverage of high-reward areas.
method Sequential training of an ensemble of GFlowNets, each optimizing a residual reward.
result Boosted GFlowNets achieve better exploration and sample diversity on multimodal benchmarks and peptide design tasks.

TSSM splits neural networks for parallel training with minimal accuracy loss.

problem Accuracy degradation in parallel training of deep neural networks.
method TSSM reformulates alternating minimization to achieve parallelism with minimal accuracy loss.
result TSSM achieves significant speedup without accuracy loss on multiple datasets.

While training error of most deep neural networks degrades as the depth of the network increases, residual networks appear to be an exception. We show that the main reason for this is the Lyapunov stability of the gradient descent algorithm: for an arbitrarily chosen step size, the equilibria of the gradient descent ar…

2018-03-22abs ↗pdf ↗

We examine the role of memorization in deep learning, drawing connections to capacity, generalization, and adversarial robustness. While deep networks are capable of memorizing noise data, our results suggest that they tend to prioritize learning simple patterns first. In our experiments, we expose qualitative differen…

2017-06-16abs ↗pdf ↗

Framework optimizes battery storage for markets by separating long-term degradation from short-term market dynamics.

problem Intractable computation due to timescale mismatch between battery degradation and market dynamics.
method Approximate dynamic programming with value function approximation and pseudo-time encoding.
result Policy outperforms benchmarks in real-time market scenarios.

New analysis reveals batch size effects on stochastic conditional gradient methods.

problem Understanding the role of batch size in stochastic conditional gradient methods.
method Deriving a new analysis focusing on momentum-based stochastic conditional gradient algorithms (e.g., Scion).
result Increasing batch size initially improves optimization accuracy but can degrade performance beyond a critical threshold.

AdaDPIGU improves privacy in deep learning by adaptively clipping and pruning gradients.

problem Privacy in deep learning models, especially in high-dimensional settings.
method Importance-based gradient updates, adaptive clipping, differentially private SGD.
result AdaDPIGU achieves high accuracy while maintaining privacy, outperforming non-private models.

New algorithm eliminates sign function in PGD attacks, improving performance.

problem Improving robustness of neural networks against adversarial attacks.
method Proposes a new raw gradient descent (RGD) algorithm that eliminates the sign function in PGD attacks.
result The RGD algorithm outperforms PGD and other competitors in various settings.

Paper develops a hybrid DNN approach for RUL prediction with adaptive drift.

problem RUL estimation challenges in practice, especially online update and uncertainty quantification.
method Hybrid DNN approach with Wiener-based-degradation model and adaptive drift. LSTM-CNN for trajectory prediction and Bayesian inference for adaptive drift.
result Superior accuracy in RUL prediction demonstrated on turbofan engines data.