Stabilizes deep Bayesian neural networks with self-stabilizing priors.
problem Brittleness and difficulty in training deep Bayesian neural networks.
method Signal propagation theory, reformulated ELBO, self-stabilizing priors.
result Improved convergence and robustness in training deeper networks and noisier settings.
Paper tackles GAN instability in audio and speech signals using a new similarity metric.
problem Improving stability of LS-GANs for audio and speech signals.
method Proposes a new similarity metric in unitary space of Schur decomposition for 2D audio and speech representations.
result Enhanced stability in training with less mode collapse compared to baseline GANs.
Improves CNN stability by translating classical signal denoising methods.
problem Stability of CNNs is poorly understood.
method Interprets classical signal denoising methods as ResNet architectures.
result Translates diffusivities, shrinkage functions, and regularizers into CNN activation functions.
The paper analyzes deep convolutional representations and their properties.
problem Understanding the properties of deep convolutional architectures.
method Introducing a multilayer kernel based on convolutional kernel networks and studying the geometry induced by the kernel mapping.
result Characterization of the RKHS and its relation to model complexity and generalization.
We ensure the stability and uniqueness of sparse coding dictionaries in noisy signals.
problem Stability and uniqueness of sparse coding dictionaries in noisy signals.
method Very general conditions guaranteeing stability and uniqueness of sparse coding dictionaries in the presence of noise.
result Recoverability of original dictionary elements from noisy data.
Stabilizes linear models for clinical adoption by detecting feature correlations.
problem Instability of sparse high-dimensional models hinders clinical adoption.
method Regularizes latent correlation in features using an autoencoder network.
result Significant improvement in feature stability and model estimation stability.
Paper proposes a new framework to improve stability-based bounds in deep learning.
problem Explaining generalization in overparameterized neural networks.
method Decomposes excess risk dynamics into signal and noise components, applying stability-based bounds only to the noise.
result The decomposition framework improves stability-based bounds and explains generalization in neural networks.
A new geometry for comparing signals, overcoming traditional limitations.
problem Comparing and interpolating discontinuous and signed signals.
method Investigation of Riemannian geometry on signal space, introducing a metric that measures both horizontal and vertical deformations.
result Characterization of metric properties and establishment of geodesic regularity and stability.
Backpropagation-free RL method trains layers using local signals.
problem Vanishing or exploding gradients in backpropagation-based RL.
method Local pairwise distance matching for layer-wise training without backpropagation.
result Backpropagation-free method achieves competitive performance and stability.
ARMA graph filters approximate any graph frequency response and are stable in time-varying settings.
problem Designing efficient graph filters for signals on graphs.
method Autoregressive moving average (ARMA) recursions for graph filtering.
result ARMA graph filters can approximate any desired graph frequency response and are stable in time-varying settings.
New methods for signal reconstruction using guiding sets and frame-less pathways.
problem Signal reconstruction in Hilbert spaces with specified properties.
method Axiomatic approach involving sample consistent and guiding sets, with reconstruction set defined as a shortest pathway.
result Existence and uniqueness of reconstruction set in Hilbert space, with derived stability and error bounds.
We analyze why some models resist unlearning using linear stability theory.
problem Understanding and predicting when machine learning models resist unlearning.
method Linear stability theory applied to machine learning models, focusing on data coherence and optimization dynamics.
result Data coherence and signal-to-noise ratio (SNR) influence unlearning resistance; lower SNR makes unlearning easier.
Deep nets are vulnerable to tiny noise that can mislead them.
problem Vulnerability of deep learning models to adversarial noise.
method Sparse signal model analysis of CNNs and two pursuit algorithms.
result Layered Basis Pursuit is more robust to adversarial attacks.
Paper proves spectral filters can be transferred between graphs.
problem Proving spectral filters can be transferred between graphs.
method Introducing the Cayley smoothness space and proving filters in this space are linearly stable.
result Graph spectral filters are transferable if they are in the Cayley smoothness space.
GNNs improve graph signal discrimination by adding nonlinearities.
problem Improving graph signal discrimination in physical networks.
method Analyzing the discriminability of GNNs and their relation to graph filter banks.
result GNNs are at least as discriminative as linear graph filter banks.
Retraining stabilizes model influence on data.
problem Performativity in predictive models leads to feedback loops.
method Developed the stable signal principle to address retraining dynamics.
result Repeated risk minimization converges geometrically to stable signal direction.
New deformation stability for cartoon functions proved.
problem Deformation stability of deep CNNs for cartoon functions.
method Established bounds for cartoon functions.
result Deformation stability for cartoon functions proved.
The paper analyzes deep neural networks using rectified linear units.
problem Understanding the individual affine linear representations of deep neural networks.
method Signal processing perspective, atomic decompositions, Lipschitz regularity estimation.
result Conditions for stabilizing learning in deep neural networks without network depth constraints.
GNNs maintain stability under minor graph topology changes.
problem Stability of GNNs to small graph topology changes.
method Proved stability of GNNs with integral Lipschitz filters.
result GNNs output change is bounded by relative graph topology change.
The paper analyzes Laplacian pyramids for extending and denoising discrete functions.
problem Analyzing conditions for convergence and stability of Laplacian pyramids.
method Investigates Laplacian pyramids for extension and denoising, providing convergence conditions and stability bounds.
result Mild conditions are provided under which the Laplacian pyramids algorithm converges and stability bounds are proven.
New method uses generative models to improve phase retrieval stability.
problem Improving stability of solutions in phase retrieval problems.
method Unified reconstruction approach using generative models to mitigate overfitting.
result Mitigates overfitting to generative model for varying noise levels.
Model improves emotion recognition using multiple physiological signals.
problem Single physiological signal is insufficient for accurate emotion recognition.
method Fused multiple modal physiological signals (EEG, EMG, EOG) for emotion classification.
result Best classification accuracy of 94.42% on arousal and 94.02% on valence in two-class tasks.
Novel complex RNN improves stability and performance in sequence tasks.
problem Lack of complex representations in deep learning for sequence tasks.
method Developed a complex gated recurrent cell combining complex-valued and norm-preserving state transitions with a gating mechanism.
result Improves stability and convergence properties, performs competitively on various tasks.
New BMI interface stabilizes user experience over long periods.
problem Inconsistent neural signal data leads to interface recalibration.
method Adversarial Domain Adaptation Network to match residual distributions.
result Adversarial Domain Adaptation Network outperforms other methods.
GNMR controls runtime stability in low-precision language model training.
problem Efficient low-precision training faces numerical risks at specific operators.
method GNMR compares gradient norms to historical means, applying bounded recovery actions.
result GNMR preserves high-fidelity quality with sparse, budgeted recovery.
Study finds no statistically significant trading edge in MNQ futures signals from OHLCV data.
problem Testing intraday momentum signals from OHLCV data in MNQ futures under realistic execution constraints.
method 947 trading days of five-minute data, 14 signal families evaluated, strict institutional criteria applied.
result No signal satisfies all criteria simultaneously, gross edge insufficient to overcome costs.
Generative model for EEG signals using GANs.
problem Generating realistic EEG signals for research and applications.
method Modified Wasserstein GANs for time series generation, including up- and down-sampling.
result Generated naturalistic EEG signals with metrics like Inception score and Frechet inception distance.
Novel Bayesian meta-reinforcement learning framework improves traffic signal control robustness.
problem Lack of robustness and stability in adaptation for traffic signal control.
method Value-based Bayesian meta-reinforcement learning framework BM-DQN with fast-adaptation variation and DQN fast-update advantage.
result Framework adapts more quickly and robustly to new scenarios than previous methods.
Paper proposes a deep RL approach for traffic signal control balancing efficiency and equity.
problem Inefficient and inflexible traffic signal controllers.
method Deep reinforcement learning with a novel reward function combining efficiency and equity.
result The proposed algorithm achieves state-of-the-art performance on various traffic scenarios.
A popular approach within the signal processing and machine learning communities consists in modelling signals as sparse linear combinations of atoms selected from a learned dictionary. While this paradigm has led to numerous empirical successes in various fields ranging from image to audio processing, there have only …
New empirical index reveals wider validity of Echo State Property in input-driven reservoirs.
problem Lack of proper input consideration in Echo State Property conditions.
method Introduced an empirical Echo State Property index to analyze stability of reservoirs with input signals.
result The actual domain of Echo State Property validity is wider than literature conditions suggest.
Paper extends cepstral distance for stable, minimum-phase models.
problem Quantifying similarity between data objects in deterministic systems.
method Combines insights from systems theory and machine learning to extend weighted cepstral distance.
result Extended weighted cepstral distance can be interpreted in terms of poles and zeros of the model.
The paper introduces isotropy as a regularizer to enhance portfolio stability.
problem Model uncertainty and estimation errors in diversification strategies.
method Integrates isotropy as a geometric regularizer into mean-variance optimization.
result Isotropy constraint systematically induces negative average-signal exposure, providing a robust crash hedge.
Noise stability improves understanding of Transformer models.
problem Lack of robustness metrics for real-valued domains and junta-like input dependence in modern LLMs.
method Proposed noise stability as a new metric and developed a practical regularization method.
result Noise stability regularization method accelerates training by 35-75%.
Paper proposes a fast stability scanning method for future grid scenarios.
problem Capturing inter-seasonal variations in renewable generation.
method Novel feature selection algorithm and self-adaptive PSO-k-means clustering.
result Reduced computational burden up to ten times with acceptable accuracy.
Graph signal processing detects hallucinations in large language models.
problem Detecting factual reasoning from hallucinations in large language models.
method Modeling transformer layers as dynamic graphs, using spectral analysis to define diagnostics.
result Spectral signatures can distinguish different types of hallucinations and achieve high accuracy.
Kernel-guided training stabilizes GANs by controlling discrepancies.
problem Stability and interpretability issues in GANs.
method Kernel-based regularization to control discrepancies in GAN loss function.
result Theoretical guarantees on stability of the training dynamics.
Stable algebraic filters improve neural network performance.
problem Improving neural network stability to deformations.
method Analyzed stability of algebraic filters and neural networks under deformations of the homomorphism.
result Stable algebraic filters have frequency responses whose derivative is inversely proportional to frequency.
Kernel-guided training stabilizes GANs by controlling discrepancies.
problem Stability and interpretability issues in GANs.
method Kernel-based regularization to control discrepancies in GAN loss function.
result Theoretical guarantees on stability of the training dynamics.
LogSpecT learns graphs from stationary signals without infeasibility issues.
problem Infeasibility of SpecT model for graph learning from stationary signals.
method Design of LogSpecT and rLogSpecT models with recovery guarantees.
result rLogSpecT is always feasible and provides recovery guarantees.
GNNs generalize CNNs for graph data, showing equivariance and stability.
problem Processing signals on graphs.
method Graph convolutional filters, nonlinearities, stacked layers.
result GNNs converge to graphon neural networks under graph convergence.
New pursuit algorithm for ML-CSC model with improved stability and dictionary learning.
problem Lack of exact pursuit algorithms and conditions for non-empty model in ML-CSC.
method Projection approach for pursuit algorithm, stability bounds, practical alternatives, online dictionary learning.
result Sound pursuit algorithm and practical dictionary learning for ML-CSC model.
A method uses non-autonomous equations to classify time signals efficiently.
problem Time signal classification with minimal parameters and high accuracy.
method Develops a framework using non-autonomous dynamical equations to classify time signals.
result The method achieves comparable accuracy with fewer parameters than existing methods.
Unified model for market dynamics, linking price and order flow.
problem Modeling market dynamics and order flow in a unified framework.
method Markovian market model driven by a hidden Brownian efficient price, signal-driven and queue-reactive models.
result Stability of mid-price around efficient price at macroscopic scale, behavior as diffusion.
We solve demixing sparse signals from nonlinear observations efficiently.
problem Demixing sparse signals from noisy, nonlinear observations.
method Developed fast algorithms for two scenarios: unknown and known link function.
result Achieved stable recovery of constituent signals with nearly tight sample complexity bounds.
Unified framework for stable RL learning with theoretical guarantees.
problem Lack of systematic theoretical principles guiding RL post-training methods.
method Unified theoretical framework for policy-gradient estimators and optimization algorithms.
result Establishes unbiasedness, variance expressions, and convergence guarantees.
Oil prices affect Russian banks' stability, with negative impacts from decreases.
problem The impact of international oil prices on Russian public banks' financial stability.
method Data from 17 Russian public banks (2008-2016), Pool Mean Group (PMG) estimator.
result An increase in international oil prices and price to book value ratio positively affects Russian public banks' stability in the long run, while negative shocks have the opposite effect.
Paper learns dictionaries for sparse signal recovery using automatic differentiation.
problem Learning dictionaries for sparse signal recovery from noisy data.
method Approximates reconstructions using FB algorithm and learns dictionaries with projected gradient descent.
result Successfully learns 1D TV dictionary from piecewise constant signals.