arXiv research

A new geometry for comparing signals, overcoming traditional limitations.

We prove the correspondence between the information geometry of a signal filter and a Kähler manifold. The information geometry of a minimum-phase linear system with a finite complex cepstrum norm is a Kähler manifold. The square of the complex cepstrum norm of the signal filter corresponds to the Kähler potential. The…

Kähler information manifolds for signal filters in weighted Hardy spaces are explored.

Wi-GATr learns to simulate wireless signals with high accuracy and speed.

This paper considers the classification of linear subspaces with mismatched classifiers. In particular, we assume a model where one observes signals in the presence of isotropic Gaussian noise and the distribution of the signals conditioned on a given class is Gaussian with a zero mean and a low-rank covariance matrix.…

Paper explores Elliptical Wishart distributions in signal processing and machine learning.

A new distance metric derived from information theory and estimation theory.

Paper reviews multi-way graph signal processing for tensor data.

Riemannian geometry has been applied to Brain Computer Interface (BCI) for brain signals classification yielding promising results. Studying electroencephalographic (EEG) signals from their associated covariance matrices allows a mitigation of common sources of variability (electronic, electrical, biological) by constr…

Proposes integrating global and local entropy for more reliable LLMs.

This paper reconstructs complex graph signals using kernel methods on manifolds.

We implement methods from computational homology to obtain a topological signal of singularity formation in a selection of geometries evolved numerically by Ricci flow. Our approach, based on persistent homology, produces precise, quantitative measures describing the behavior of an entire collection of data across a di…

We present a novel condition, which we term the net- work nullspace property, which ensures accurate recovery of graph signals representing massive network-structured datasets from few signal values. The network nullspace property couples the cluster structure of the underlying network-structure with the geometry of th…

Proposes a new Sliced-Wasserstein distance for covariance matrices in M/EEG signals.

New framework uses geometry of embeddings to predict robustness.

We consider globally hyperbolic flat spacetimes in 2+1 and 3+1 dimensions, in which a uniform light signal is emitted on the $r$-level surface of the cosmological time for $r\to 0$. We show that the frequency of this signal, as perceived by a fixed observer, is a well-defined, bounded function which is generally not co…

We construct geometric shrinkage priors for Kählerian signal filters. Based on the characteristics of Kähler manifolds, an efficient and robust algorithm for finding superharmonic priors which outperform the Jeffreys prior is introduced. Several ansätze for the Bayesian predictive priors are also suggested. In particul…

Paper revisits five IF paradoxes using differential geometry.

Proposes a new complex Gaussian distribution for better modeling of complex-valued signals.

New method separates graph structure from node attributes to recover lost signal.

We study the classification performance of Kronecker-structured models in two asymptotic regimes and developed an algorithm for separable, fast and compact K-S dictionary learning for better classification and representation of multidimensional signals by exploiting the structure in the signal. First, we study the clas…

This paper offers a characterization of fundamental limits on the classification and reconstruction of high-dimensional signals from low-dimensional features, in the presence of side information. We consider a scenario where a decoder has access both to linear features of the signal of interest and to linear features o…

A method for predicting signals on graphs using Gaussian processes and optimal transport.

Characterizing the phase transitions of convex optimizations in recovering structured signals or data is of central importance in compressed sensing, machine learning and statistics. The phase transitions of many convex optimization signal recovery methods such as $\ell_1$ minimization and nuclear norm minimization are…

Graph signal processing detects hallucinations in large language models.

A new framework enhances binaural audio for moving talkers.

We review the information geometry of linear systems and its application to Bayesian inference, and the simplification available in the Kähler manifold case. We find conditions for the information geometry of linear systems to be Kähler, and the relation of the Kähler potential to information geometric quantities such …

Information geometry offers new tools for statistical analysis.

Local minimax analysis for Poisson deconvolution of discrete signals.

DPI quantifies phase differences in 1D and multidimensional signals using Riesz transform.

This paper extends compositional data analysis using graph signal processing.

Estimates signals from a continuous dictionary with sparse mixtures using optimization.

In this paper, we study a polynomial decomposition model that arises in problems of system identification, signal processing and machine learning. We show that this decomposition is a special case of the X-rank decomposition --- a powerful novel concept in algebraic geometry that generalizes the tensor CP decomposition…

The paper shows that random frames have full spark with high probability.

This paper studies the effect of discretizing the parametrization of a dictionary used for Matching Pursuit decompositions of signals. Our approach relies on viewing the continuously parametrized dictionary as an embedded manifold in the signal space on which the tools of differential (Riemannian) geometry can be appli…

We analyzed the performance of a biologically inspired algorithm called the Corrected Projections Algorithm (CPA) when a sparseness constraint is required to unambiguously reconstruct an observed signal using atoms from an overcomplete dictionary. By changing the geometry of the estimation problem, CPA gives an analyti…

The paper introduces novel Gaussian process models for vector-valued signals on manifolds.

This report concerns the problem of dimensionality reduction through information geometric methods on statistical manifolds. While there has been considerable work recently presented regarding dimensionality reduction for the purposes of learning tasks such as classification, clustering, and visualization, these method…

This paper proposes a geometry-aware active learning framework for spatiotemporal dynamic systems.

A bridge between continuous signals and discrete Ising spins for associative memory.

Maximizing the speed and precision of communication while minimizing power dissipation is a fundamental engineering design goal. Also, biological systems achieve remarkable speed, precision and power efficiency using poorly understood physical design principles. Powerful theories like information theory and thermodynam…

FedSPDnet improves federated learning for SPD matrices, outperforming existing methods.

Subspace models play an important role in a wide range of signal processing tasks, and this paper explores how the pairwise geometry of subspaces influences the probability of misclassification. When the mismatch between the signal and the model is vanishingly small, the probability of misclassification is determined b…

Statistical neurodynamics studies macroscopic behaviors of randomly connected neural networks. We consider a deep layered feedforward network where input signals are processed layer by layer. The manifold of input signals is embedded in a higher dimensional manifold of the next layer as a curved submanifold, provided t…

Unified study of principal component analysis under various structured signal models.

Study on detecting and recovering hidden dense cycles in random graphs.

The paper shows that causal identification is not essential for efficient portfolios, focusing on geometric sufficiency conditions.

Unified framework for Riemannian deep learning across manifold-valued representations.