Self-training with noisy student-teacher boosts keyword spotting accuracy.
problem Robust keyword spotting in challenging conditions.
method Aggressive data augmentation and self-training with noisy student-teacher approach.
result Significant accuracy improvement in difficult conditions, up to 60%.
New framework explains diverse impacts of data augmentation.
problem Understanding the varied effects of data augmentation on model performance.
method Developed a theoretical framework to characterize DA's impact on linear models.
result Data augmentation induces implicit spectral regularization through two effects.
Paper constructs a spectral sequence linking annular Khovanov homology to reduced Khovanov homology.
problem Classifying links with minimal annular Khovanov homology rank.
method Constructs a spectral sequence converging from annular Khovanov homology to reduced Khovanov homology.
result Classifies links with minimal rank of annular Khovanov homology.
Deep learning method clusters multi-view data matrices.
problem Clustering heterogeneous relational data matrices.
method Deep collective matrix tri-factorization (DCMTF).
result Discover latent clusters across input matrices and their associations.
A new method learns outcome-aware spectral features for causal effect estimation.
problem Estimation of causal effects in the presence of hidden confounders.
method Augmented Spectral Feature Learning framework that minimizes a contrastive loss derived from an augmented operator incorporating outcome information.
result Our method remains effective even under spectral misalignment.
Proves accuracy guarantees for self-supervised learning with correlated positive pairs.
problem Lack of theoretical guarantees for self-supervised learning with correlated positive pairs.
method Novel augmentation graph concept and spectral decomposition loss.
result Provably accurate features under linear probe evaluation.
The paper develops spectral networks in symplectic topology and their relation to Lagrangian fillings.
problem Understanding spectral networks in symplectic topology and their role in Lagrangian fillings.
method Analytic results on adiabatic degeneration of Floer trajectories and explicit computation of continuation strips.
result Established equivalence between Family Floer functor and non-abelianization functor for Lagrangian fillings with spectral networks.
MASC balances dataset representation using affinity clustering and distribution discrepancies.
problem Representation bias in datasets due to group imbalance.
method MASC uses affinity clustering and pairwise distribution discrepancies to balance non-protected and protected groups.
result MASC effectively debiases target datasets, comparable to existing methods.
WF distance measures time series similarity via spectral density displacement.
problem Measuring similarity between time series.
method Wasserstein-Fourier distance between normalised power spectral densities.
result WF establishes as a general-purpose metric for time series.
Generative Adversarial Networks (GANs) are known to be difficult to train, despite considerable research effort. Several regularization techniques for stabilizing training have been proposed, but they introduce non-trivial computational overheads and interact poorly with existing techniques like spectral normalization.…
RKD improves clustering in semi-supervised learning with limited labels.
problem Improving clustering accuracy in semi-supervised learning with few labeled examples.
method RKD as spectral clustering on a teacher model's graph, with clustering error quantification.
result RKD provably leads to low clustering error in semi-supervised classification problems.
Paper improves MVSC using tensor low-rank modeling.
problem Improving multi-view spectral clustering.
method Structured tensor low-rank norm for MVSC optimization.
result Proposed method outperforms state-of-the-art methods.
New method optimizes portfolios for non-stationary markets.
problem Inadequate classical portfolio optimization for non-stationary markets.
method Reformulate portfolio optimization in spectral domain, using complex statistics.
result Time-varying optimal capital allocations for non-stationary markets.
A new model reduces noise and speeds up subspace segmentation.
problem Subspace segmentation from noisy data.
method Group norm regularized factorization model (GNRFM) with AALM algorithm.
result The method is faster and more robust to noise.
GCNNs gain rotation invariance with more training augmentation, making SVD-Universal more effective.
problem Improving robustness of GCNNs to adversarial attacks.
method SVD-Universal technique applied to GCNNs trained with larger rotations.
result SVD-Universal becomes more effective as GCNNs gain rotation invariance.
New framework explains neural network bias in solving differential equations.
problem Understanding and controlling the bias in PINNs for differential equations.
method Deriving an integro-differential equation from PINNs and GPR equivalence.
result PINN predictions are influenced by a kernel term reflecting architecture choices.
Augments GNNs with diversification to preserve node identity.
problem Current GNNs filter node information, potentially losing node identity.
method Integrates diversification operators with aggregation to enrich node representations.
result Significant performance boost on 9 node classification tasks.
Novel bio-inspired masking for robust speech emotion recognition.
problem Noise degradation in speech emotion recognition.
method Cochlear cepstrogram-based contrastive learning with temporal and frequency masking.
result Improved speech emotion recognition performance on K-EmoCon benchmark.
Data vectors are obtained from multiple domains. They are feature vectors of images or vector representations of words. Domains may have different numbers of data vectors with different dimensions. These data vectors from multiple domains are projected to a common space by linear transformations in order to search clos…
Introduces data augmentation for graph convolutional networks, proposing Monte Carlo Graph Learning.
problem Lack of transparency in graph convolutional networks.
method Data augmentation through graph structure, training traditional classifiers on expanded training set.
result MCGL shows better tolerance to graph structure noise than GCN on noisy graphs.
Study reveals class disparities in balanced datasets through spectral imbalance.
problem Class disparities in balanced datasets are overlooked despite model performance gaps.
method Developed a theoretical framework and studied 11 encoders to diagnose spectral imbalance.
result Identified spectral imbalance as a source of class disparities in balanced datasets.
Method estimates number of clusters in Block Markov Chain trajectories.
problem Challenges in choosing number of clusters for sequential data.
method Spectral embedding and density-based clustering.
result Asymptotically consistent method for estimating clusters.
New model learns graph spectra accurately, outperforming existing methods.
problem Graph diffusion models struggle to distinguish certain graph families and their spectra.
method Leveraged random matrix theory to analytically extract spectral properties, introducing Dyson Diffusion Model.
result Dyson Diffusion Model learns graph spectra accurately and outperforms existing models.
Exploring adversarial attack vectors and studying their effects on machine learning algorithms has been of interest to researchers. Deep neural networks working with time series data have received lesser interest compared to their image counterparts in this context. In a recent finding, it has been revealed that curren…
The increasing access to brain signal data using electroencephalography creates new opportunities to study electrophysiological brain activity and perform ambulatory diagnoses of neuronal diseases. This work proposes a pairwise distance learning approach for Schizophrenia classification relying on the spectral properti…
Positive weights improve kernel quadrature's accuracy.
problem Improving kernel quadrature weights to be positive and stable.
method Using convex geometry to approximate the kernel mean embedding with positive weights.
result Positive weights lead to improved kernel quadrature bounds with Monte-Carlo-beating rates.
Detects corruption in agentic models during execution.
problem Inconsistent context, retrieval errors, or adversarial inputs corrupt intermediate steps of reasoning chains.
method Analyzes token graphs induced by attention and computes spectral statistics to emit accept/reject signals.
result A single threshold on the high frequency energy ratio optimally detects context inconsistency in agentic models.
Discrete return (DR) Laser Detection and Ranging (Ladar) systems provide a series of echoes that reflect from objects in a scene. These can be first, last or multi-echo returns. In contrast, Full-Waveform (FW)-Ladar systems measure the intensity of light reflected from objects continuously over a period of time. In a c…
Study optimal spectral estimator for semi-supervised node classification.
problem Semi-supervised node classification on CSBM with limited labels.
method Spectral estimator inspired by PCA, graph ridge regression, GCN.
result Achieves information-theoretical threshold for exact recovery.
The paper proves geometric and spectral alignment for deep neural networks.
problem Understanding the singular spectra of deep neural network layers.
method Proves deterministic quotient-geometric estimates for singular spectra of Frobenius-normalized layer factors.
result Exact power-law spectra form a trace-normalized Cartan orbit under Frobenius normalization.
New defence against data-poisoning attacks in neural networks.
problem Data-poisoning attacks can evade existing defences and increase model efficacy.
method Proved geometric mechanism and identified near clone regime in input space.
result Regularisation and data augmentation reduce data fitting capacity and prevent poisoning.
Unconstrained models learn physical symmetries effectively with simple data augmentation.
problem Ensuring physical symmetries in machine learning models.
method Rigorous metrics to measure symmetry content, data augmentation strategy, architectural analysis.
result Unconstrained models can learn approximate equivariant behavior with simple data augmentation.
Hyperspectral remote sensing images (HSIs) are characterized by having a low spatial resolution and a high spectral resolution, whereas multispectral images (MSIs) are characterized by low spectral and high spatial resolutions. These complementary characteristics have stimulated active research in the inference of imag…
We study the spectral sequence associated to the filtration by powers of the augmentation ideal on the (twisted) equivariant chain complex of the universal cover of a connected CW-complex X. In the process, we identify the d^1 differential in terms of the coalgebra structure of H_*(X,\k), and the \kπ_1(X)-module struct…
ACFS optimizes spectral risk under decision-dependent uncertainty using adaptive forest sampling.
problem Minimizing spectral risk with decision-dependent uncertainty.
method ACFS integrates Generalised Random Forests, CEM-guided exploration, rank-weighted augmentation, and multi-start refinement.
result ACFS achieves lowest median oracle spectral risk on both benchmarks.
Hyperspectral remote sensing images (HSIs) usually have high spectral resolution and low spatial resolution. Conversely, multispectral images (MSIs) usually have low spectral and high spatial resolutions. The problem of inferring images which combine the high spectral and high spatial resolutions of HSIs and MSIs, resp…
Sharp distance estimates for compact spin manifolds using Dirac operator.
problem Metric inequalities for compact spin manifolds with lower bounds on scalar and mean curvatures.
method Using the Dirac operator technique with spectral estimates and local boundary conditions.
result Optimal estimates for Riemannian bands and long neck problem solutions.
Unified analysis of kernel-based and locally adaptive bandit optimization methods.
problem Performance of bandit optimization algorithms in RKHS functions.
method Investigates the relationship between kernel regularity and algorithmic performance, characterizing spectral properties of various kernels.
result Unified framework for analyzing kernel-based and locally adaptive bandit algorithms, deriving explicit regret bounds.
Using the duality between Wilson loop expectation values of SU(N) Chern-Simons theory on S3 and topological open-string amplitudes on the local mirror of the resolved conifold, we study knots on S3 and their invariants encoded in colored HOMFLY polynomials by means of topological recursion. In the context of the …
KOMET identifies Koopman operators from model parameter trajectories to adapt to evolving data distributions.
problem Adaptation of parametric models to non-stationary environments.
method Data-driven framework using Koopman operator identification and Extended Dynamic Mode Decomposition (EDMD).
result KOMET achieves high autonomous-rollout accuracies of 0.981 to 1.000 over 100 time steps on various drifting datasets.
Study examines how data augmentation impacts optimization in linear regression.
problem Understanding how data augmentation schedules affect optimization in linear regression.
method Analyzed the effect of augmentation on optimization in linear regression with MSE loss, using classical convex optimization and recent work on implicit bias.
result Proved that under certain joint schedules for learning rate and augmentation scheme, augmented gradient descent converges and characterized the resulting minimum.
Data augmentation doesn't improve robustness, contrary to belief.
problem The effectiveness of data augmentation in improving model robustness is questioned.
method Taking a Domain Generalization viewpoint, the study examines the robustness of augmented representations.
result Augmented representations are not robust to distortions used during training.
This paper improves auto-augment efficiency by sharing augmentation weights.
problem Efficient evaluation of augmentation policies for model training.
method Augmentation-Wise Weight Sharing (AWS) to create a fast yet accurate proxy task.
result Augmentation policies found achieve superior accuracies compared to existing methods.
Simple policy search outperforms advanced learnable test-time augmentation techniques.
problem Improving predictive performance through test-time data augmentation.
method Greedy policy search (GPS) for learning test-time augmentation policies.
result Augmentation policies learned with GPS achieve superior predictive performance and robustness.
New measures quantify how data augmentation improves model performance.
problem Understanding the effectiveness of data augmentation in deep learning.
method Introduced Affinity and Diversity measures to quantify augmentation performance.
result Augmentation performance is best achieved by optimizing both Affinity and Diversity.
CNNs encode data augmentation transformations, especially in early layers.
problem Whether neural network features encode data augmentation transformations.
method Systematic approach using pre-trained vision models to predict augmentation transformations.
result Neural network features encode data augmentation transformations, especially in early layers.
WeMix improves data augmentation by correcting bias in deep learning.
problem Data augmentation's effectiveness is limited by data bias.
method Developed AugDrop and MixLoss algorithms to correct data bias.
result WeMix improves data augmentation performance through bias correction.
A study on optimizing data augmentation weights for improved test-time predictions.
problem Improving robustness of predictions during testing with data augmentation methods.
method A weighted Test-Time Augmentation (TTA) approach based on variational Bayesian framework to optimize weights.
result Optimizing weights suppresses unwanted data augmentations and improves prediction performance.