arXiv Machine Learning

Perfect reconstruction of sparse signals using nonconvexity control and one-step RSB message passing

arXiv:2512. 17426v2 Announce Type: replace-cross Abstract: We consider sparse signal reconstruction via minimization of the smoothly clipped absolute deviation (SCAD) penalty, and develop one-step replica-symmetry-breaking (1RSB) extensions of approximate message passing (AMP), termed 1RSB-AMP.

arXiv Machine Learning
Jul 14

Demixing Sparse Signals from Nonlinear Observations using Generalized Non-convex Regularization

arXiv:2607. 10618v1 Announce Type: cross Abstract: We consider the recovery of a pair of sparse vectors from a limited number of nonlinear observations of their superposition: $y_i=g(\inner{\ba_i}{\bPhi\bw^\ast+\bPsi\bz^\ast})+e_i$, $i=1,\dots,m$, with $m\ll n$, incoherent orthonormal bases $\bPhi,\bPsi$, a scalar link $g$, and noise $e_i$ that may be heavy-tailed or contaminated.

By Raziyeh Takbiri
arXiv Machine Learning
1d ago

Reference-free logged energy-oracle recovery for neural approximations of symmetric coercive variational problems: conforming Riesz reconstruction and archive-level selection

arXiv:2608. 16473v1 Announce Type: new Abstract: Neural PDE training yields a finite checkpoint archive, yet its logged energy errors are inaccessible without the exact solution, while loss-based selection does not necessarily recover the logged energy oracle.

By Karim Bounja, Lahcen Laayouni, Boujemaa Achchab, Abdeljalil Sakat
arXiv Machine Learning
Jul 31

RIPPLE: Generating Multi-Channel Phase, Not Recovering It

arXiv:2607. 27775v1 Announce Type: new Abstract: Generative models synthesize magnitude spectra with high fidelity, while phase is delegated to a recovery module---Griffin--Lim, a vocoder, or a latent decoder---applied independently to each channel.

By Jaehyuk Lee, Yeajin Lee, Dayeon Shin, Donghun Lee
arXiv Machine Learning
Jun 15

Nonlinear Two-Time-Scale Stochastic Approximation: A Sharp Phase Transition and How to Beat It

arXiv:2606. 14488v1 Announce Type: cross Abstract: Recent finite-time analyses of nonlinear two-time-scale stochastic approximation show that under contractive assumptions the slow iterate $Y_k$ with stepsizes $\beta_k=\Theta(k^{-1})$ and $\alpha_k=\Theta(k^{-a})$, $a\in(1/2,1)$, generally satisfies a mean-square rate of order $k^{-a}$; decoupled $k^{-1}$ rates require strong local linearity.

By Dhruv Sarkar, Vaneet Aggarwal
arXiv Machine Learning
Jul 30

On the robustness of noisy solutions in non-convex neural networks

arXiv:2607. 27000v1 Announce Type: cross Abstract: Optimization in non-convex neural network models is strongly influenced by the geometry of the solution space: sparse, isolated, point-like clusters are typically algorithmically inaccessible, whereas wide and flat regions can be found efficiently despite being relatively rare.

By Enrico M. Malatesta, Alessandra Passalacqua, Riccardo Zecchina