arXiv:2604. 03634v5 Announce Type: replace Abstract: We establish that temporal averaging over multiple observations is the degenerate case of algebraic group action with the trivial group $G=\{e\}$.
DANCo (Dimensionality from Angle and Norm Concentration) jointly calibrates nearest-neighbor distance and angular statistics and consistently reaches state-of-the-art accuracy on clean intrinsic-dimen...
arXiv:2609.37114v1 Announce Type: new Abstract: DANCo (Dimensionality from Angle and Norm Concentration) jointly calibrates nearest-neighbor distance and angular statistics and consistently reaches s...
arXiv:2606. 24418v1 Announce Type: new Abstract: Data augmentation is a simple and model-agnostic approach for exploiting known invariances in learning problems.
arXiv:2608. 11954v1 Announce Type: cross Abstract: Structured potential outcomes such as microscopy images may be recorded after an unknown, unit-specific transformation.
The paper surveys the use of linear, function‑preserving transforms in 4‑bit large‑language‑model (LLM) quantization, formalizing the underlying principle as the "Great Inversion"—the trade‑off between energy concentration favored by allocation‑flexible coding and within‑group flattening favored by grouped shared‑scale quantization. It reviews 200 works, classifies 43 transform methods by structure, data‑awareness, construction approach, and runtime cost, and examines how they interact with GPTQ rounding. The study also explores how different number formats (FP4, MXFP4, NVFP4) influence the optimal transform choice and outlines open research problems. "whyItMatters":"The survey clarifies the conflicting objectives in transform‑based LLM quantization and provides a practical guide for selecting transforms based on deployment regime, thereby informing future research and deployment strategies."
arXiv:2511.22435v2 Announce Type: replace Abstract: Invariant learning on graphs aims to build predictors that rely on causal substructures rather than on environment-specific shortcuts. Current meth...
The paper tackles two key gaps in streaming PCA using Oja's algorithm: it establishes sharp operator‑norm convergence for general‑rank subspaces under sub‑Gaussian data, and it provides distributional inference for the resulting subspace estimator. The authors remove non‑vanishing remainder terms from existing analyses, achieving rates that match minimax bounds in both dense‑tail and sparse‑tail regimes. They further develop a linearization of Oja’s iterates, enabling high‑dimensional Gaussian approximations and an online multiplier bootstrap for practical inference.
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.
arXiv:2606. 01443v1 Announce Type: cross Abstract: A central difficulty in training Joint-Embedding Predictive Architectures (JEPAs) is preventing representation collapse.
arXiv:2609.08133v1 Announce Type: cross Abstract: In nonconvex optimization problems arising in geometric machine learning, data augmentation is commonly used to promote invariance by averaging empir...
arXiv:2609.08759v1 Announce Type: cross Abstract: Quantization schemes based on randomized rotations have recently received renewed attention, including the roles of MMSE and unbiased reconstruction...
arXiv:2608.30374v1 Announce Type: cross Abstract: We study null-space estimation from a noisy matrix. For a simple left null space, we first derive an exact compact expression for the error of the sm...