arXiv Machine Learning
Zero-SNR Analyticity of the Scalar MMSE Is Equivalent to Gaussianity
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Sep 18
TAP Accuracy Below the Fluctuation Scale and Universal Posterior Geometry in Spherical Linear Models
arXiv:2609. 20577v1 Announce Type: cross Abstract: We study the Bayes-optimal spherical linear model as the ambient dimension and sample size grow proportionally, under a quantitative Marchenko--Pastur spectral-regularity condition on the design.
arXiv Machine Learning
Aug 11
Logarithmic-Free Moment and Generalization Bounds for Uniformly Stable Algorithms
arXiv:2608. 09870v1 Announce Type: cross Abstract: Uniform stability is a classical tool for controlling the generalization error of a learning algorithm.
arXiv Machine Learning
Sep 24
Exact Minimax One-Bit Unbiased Compression: Heavy-Tail Necessity and Finite-Randomness Approximation
arXiv:2609. 27860v1 Announce Type: new Abstract: A pointwise-unbiased one-bit compressor reconstructs every real input in expectation while transmitting one bit.
arXiv Machine Learning
Jun 2
How Accurately Can a Gaussian Approximate Stochastic Approximation Iterates?
arXiv:2602. 13906v2 Announce Type: replace-cross Abstract: Stochastic approximation (SA) is a method for finding the root of an operator perturbed by noise.
arXiv Machine Learning
Jul 21
Scaling Limits of Constant-Stepsize SGD at Flat Minima
arXiv:2607. 16384v1 Announce Type: new Abstract: For stochastic gradient descent (SGD) with a constant stepsize $\alpha$, the invariant law of the iterates, centered at a minimizer, describes the behavior of the algorithm over long time horizons.
arXiv Machine Learning
Aug 14
Identifiability and Stability of Generative Drifting in the Companion-Elliptic Kernel Family
arXiv:2604. 24196v4 Announce Type: replace-cross Abstract: A drifting model is a one-step generator trained by moving each sample along a field of kernel-weighted attraction toward data samples and repulsion between model samples; training halts once this field vanishes.