47 articles mentioning Sharp-MiniCPM5-2B-GGUF
arXiv:2610.26976v1 Announce Type: new Abstract: We establish sharp degree bounds for Putinar sum-of-squares (SOS) certificates in terms of the positivity margin $\delta$. For any fixed Archimedean quadratic module with prescribed generators and any fixed bound on the degree of the objective, we prov
arXiv:2610.27398v1 Announce Type: new Abstract: Probabilities of causation (PoCs) have developed steadily, from the binary measures first introduced by Pearl to the non-binary setting recently studied by Shu et al. As the theory has matured, PoCs have found applications in a growing range of areas,
arXiv:2610.10080v3 Announce Type: replace-cross Abstract: Gaussian processes (GPs) are widely used across machine learning, spatial statistics, time-series analysis, optimization, Bayesian statistics, and scientific applications. A central component of a GP model is its kernel, which is typically sp
arXiv:2610.21567v1 Announce Type: new Abstract: Query-conditioned probabilistic predictors answer logically related questions one at a time, and labels to check their calibration are often missing. For each restriction on what a bettor's stakes may use, a minimax theorem identifies, for finitely sup
arXiv:2603.23305v2 Announce Type: replace-cross Abstract: We investigate the problem of matching networks where both edge weights and node features are correlated following a specific node correspondence. While prior work has established sharp thresholds for matching either graphs or features indivi
arXiv:2610.16084v1 Announce Type: new Abstract: Activation steering adds a vector to a language model's internal representations at inference time. It is a lightweight alternative to fine-tuning for behavioral control. The standard construction, contrastive activation addition (CAA), is fragile, as
arXiv:2510.12451v3 Announce Type: replace-cross Abstract: Flat minima are strongly associated with improved generalisation in deep neural networks. However, this connection has proven nuanced in recent studies, with both theoretical counterexamples and empirical exceptions emerging in the literature
arXiv:2610.13207v1 Announce Type: new Abstract: Fake news detection under low resource conditions is challenged by the scarcity of labeled data and the difficulty of capturing subtle deceptive patterns. In this work, we focus on low resource fake news detection, where only a small labeled set is ava
arXiv:2604.25984v2 Announce Type: replace-cross Abstract: The marginal likelihood, also known as the evidence, is regarded as a mathematical embodiment of Occam's razor, enabling hyperparameter selection that avoids overfitting. The evidence lower bound (ELBO) objective from variational inference ha
arXiv:2610.12052v1 Announce Type: cross Abstract: Despite their empirical success, why diffusion models overcome the bottlenecks of classical score-based samplers remains unclear. In this work, we leverage Gaussian distributions to isolate this phenomenon. We establish 2-Wasserstein convergence boun
arXiv:2610.12358v1 Announce Type: cross Abstract: We study Gaussian regression under squared population $L_2$ loss in a known $m$-dimensional subspace of degree-at-most-$k$ functions on the $d$-dimensional Boolean cube. Random inputs can undersample regions essential for prediction, delaying the par
arXiv:2610.09827v1 Announce Type: new Abstract: Long inputs and extended generation increase the storage and access costs of the key-value (KV) cache. Low-bit quantization reduces storage and memory traffic, while query-channel pruning can further reduce key-cache reads. Rotation-based quantization
arXiv:2605.06866v3 Announce Type: replace Abstract: We study finite-iteration behavior of asynchronous categorical distributional temporal-difference methods, covering scalar categorical TD (CTD) in the Cram\'er geometry and multivariate signed-categorical TD (MTD) in the maximum mean discrepancy (M
arXiv:2610.07721v1 Announce Type: cross Abstract: We study ridge regression from exactly $s$ distinct rows of a fixed design. Responses are fixed, and only the subset is random. The determinant law and selected ridge fit share one positive definite penalty. Established mean identities and exponentia
arXiv:2610.00101v1 Announce Type: cross Abstract: How much risk does a small reweighted training support retain? For finite weighted least squares with the minimum-norm learner, we prove the exact law $\Gamma_d(n)=3-n/d$ throughout $\lceil3d/2\rceil\leq n\leq2d-1$. The guarantee covers every observe
arXiv:2610.01951v1 Announce Type: new Abstract: Top-two algorithms are simple and effective for fixed-confidence best-arm identification, but their sharp non-asymptotic behavior is still not well understood. We study this problem for Bernoulli bandits through $\beta$-EB-TCI, the empirical-best top-t
arXiv:2610.00254v1 Announce Type: new Abstract: We characterize the regret attainable in online convex optimization when access to the feasible set is limited to an exact linear optimization oracle. The learner is given an inscribed ball and a diameter bound and must remain feasible on every consist
arXiv:2609.38161v1 Announce Type: new Abstract: Evaluations of graph reconstruction by language models typically report a single aggregate distance between the original and the reconstructed graph. We prove that for the Wasserstein distance between Laplacian spectra such a summary is bracketed by tw
arXiv:2609.37344v1 Announce Type: new Abstract: Data reconstruction attacks have empirically been successful in recovering training samples from learned models, raising privacy concerns and motivating defenses with guarantees that remain valid against future threats. While differential privacy (DP)
arXiv:2609.36568v1 Announce Type: new Abstract: Diffusion models have emerged as state-of-the-art generative models, with recent extensions from Euclidean spaces to Riemannian manifolds. However, existing convergence guarantees for Riemannian diffusion models typically require $\tilde{O}(\mathrm{pol
arXiv:2604.01525v2 Announce Type: replace-cross Abstract: We give a short linear-algebraic proof of the inequality $$ \|x\|_1\,\|x\|_\infty \le \frac{1+\sqrt{n}}{2}\,\|x\|_2^2, $$ valid for every $x\in\mathbb{R}^n$. This inequality relates three fundamental norms on finite-dimensional spaces and has
arXiv:2605.19823v2 Announce Type: replace-cross Abstract: Neural operators have achieved strong performance in learning solution operators of partial differential equations (PDEs), but their inherently continuous representations struggle to capture discontinuities and sharp transitions. Existing app
arXiv:2609.29140v1 Announce Type: new Abstract: Repeated evaluation can estimate a benchmark score accurately while still requiring replication to certify narrow uncertainty. We characterize that requirement on a fixed grid of $M$ tasks with $L$ binary paths per task under the hard budget $(M+t)K$,
arXiv:2608.24098v2 Announce Type: replace Abstract: Uniform stability controls how much one training example can change the loss at any test point. A new logarithmic-free upper bound shows that a $\gamma$-uniformly stable algorithm with loss in $[0,L]$ has generalization gap at most $O \left(\gamma\
arXiv:2609.27008v1 Announce Type: cross Abstract: We study the long-time behavior of Wasserstein gradient flows for interaction energies \[ \mathsf E[\mu] = \frac12\iint_{M\times M}K(x,y)\,\mathrm d\mu(x)\,\mathrm d\mu(y) \] on a closed manifold $M$. For kernels diagonal in a Laplace eigenbasis with
arXiv:2608.01069v2 Announce Type: replace Abstract: Bandit algorithms generate data for downstream inference, but adaptive sampling biases post-bandit sample means. We analyze this bias for stable index algorithms, including UCB1 and its generalizations, and derive sharp leading-order expressions fo
arXiv:2606.05438v2 Announce Type: replace Abstract: We study the deterministic first-order oracle complexity of finding \(\epsilon\)-stationary points in smooth nonconvex optimization when the objective satisfies higher-order smoothness assumptions. While the classical \(\epsilon^{-2}\) rate is opti
arXiv:2609.20333v1 Announce Type: new Abstract: We study reconstruction in autoencoders that apply the same forward map before and after setting the observed coordinates to zero. For equal odd input and hidden dimensions $d\geq 3$, among orientation-preserving diffeomorphisms whose Jacobian singular
arXiv:2609.17845v1 Announce Type: cross Abstract: Let the exact homogeneous hard-margin support vector machine be trained on \(m\) independent observations from a Borel probability law on a real Hilbert space. We prove that, with score zero counted as an error, there is a universal numerical constan
arXiv:2609.18782v1 Announce Type: new Abstract: We establish convergence bounds for deep $V$-learning with horizon $H$. The algorithm fits a scalar value function to targets from executed transitions and selects actions using a predictive model and the value function. For current observed-successor
arXiv:2609.15825v1 Announce Type: new Abstract: A self-supervised encoder is trained once, frozen, and reused through lightweight probes on tasks nobody named at training time; the practitioner's question is when the off-the-shelf features are good enough and when they need fixing. Canonical correla
arXiv:2608.26515v2 Announce Type: replace-cross Abstract: We determine the minimax cumulative log-loss regret of a finite-alphabet, exogenously driven source with genuinely infinite input memory: independent Rademacher inputs $(U_t)$ are observed sequentially and the next binary mark has logit $\sum
arXiv:2609.07997v1 Announce Type: new Abstract: We characterize the sharp structure-agnostic minimax risk for coefficient estimation in the partial linear model when the outcome and treatment nuisances are learned by two distinct black-box learners, which resolves the open problem in double machine
arXiv:2609.04578v1 Announce Type: cross Abstract: We study stochastic gradient descent with random reshuffling for finite sums \[ F(x)=\frac1n\sum_{i=1}^n f_i(x). \] For fresh reshuffling with a constant component stepsize, if each $f_i$ has an $L$-Lipschitz gradient and the average $F$ is $\mu$-str
arXiv:2609.03973v1 Announce Type: new Abstract: An image editor may satisfy every regional plausibility constraint separately even when no single latent explanation fits the complete output. We formalize this local-to-global failure using a common witness grade and witness nerve. The framework separ
arXiv:2609.00872v1 Announce Type: cross Abstract: We establish sharp mixed spectral Barron regularity for eigenfunctions of molecular Coulomb Hamiltonians. The mixed norm is a Fourier $L^1$ norm with one isotropic weight and coordinate-product weights, and therefore detects regularity invisible to t
arXiv:2608.29018v1 Announce Type: cross Abstract: We determine the sharp restricted isometry threshold for recovery at global minima of the rank-restricted matrix LASSO. For target rank $r_{\star}$, if the rank-$k$ RIP constant satisfies $\delta<\delta_{\mathrm{sharp}}(k/r_{\star})$, where $\delta_{
arXiv:2608.31157v1 Announce Type: new Abstract: Many parameter-efficient methods generate the parameters of a large neural network from a low-dimensional latent representation. Given an architecture $\Phi$ with $P_\Phi$ parameter slots, we write $\boldsymbol{\theta}_f=\mathcal{G}(\boldsymbol{\xi}_f)
arXiv:2608.28564v1 Announce Type: cross Abstract: We study kernel ridge regression under anisotropic Gaussian data, where the input covariance decays as a power law with exponent $\alpha\geq 0$ for polynomial inner-product kernels. We derive asymptotically sharp expressions for the kernel spectrum a
arXiv:2608.28150v1 Announce Type: new Abstract: Which geometry controls the rank complexity of normalized softmax attention? We study maximum-row-$\ell_1$ approximation rank, exactly the least unrestricted rank preserving every bounded vector-valued output. Two sharp worst-case laws isolate support
arXiv:2608.27372v1 Announce Type: cross Abstract: We establish a sharp phase transition for fitting random vectors by an ellipsoid. The random vectors have independent subgaussian coordinates with mean zero, variance one, and a common fourth moment, and the number of vectors is proportional to the s
arXiv:2608.26877v1 Announce Type: new Abstract: Prior analyses by Derezinski and Warmuth established all-size sampling identities, selected-OLS unbiasedness, and inverse moments for ordinary volume sampling, while their exact arbitrary-fixed-response loss and prediction-covariance formulas are at th
arXiv:2607.23679v1 Announce Type: new Abstract: Recent years have witnessed increasing interests in tackling heteroscedastic noise in bandits and reinforcement learning. In these works, the cumulative variance of the noise $\Lambda = \sum_{t=1}^T \sigma_t^2$, where $\sigma_t^2$ is the variance of th
arXiv:2607.21673v1 Announce Type: new Abstract: Test-time adaptive out-of-distribution (OOD) detectors update a memory bank from the unlabelled stream. We show this adaptation obeys a provable dynamical law. Modelling bank impurity as a generalized P\'olya urn, we prove almost-sure convergence to a
arXiv:2607.19042v1 Announce Type: cross Abstract: Neural hypergraphs are a natural generalization of neural networks, the reference models in modern machine learning. Yet, their deployment has proven demanding: the number of weighted hyperedges required leads to an intractable parameter explosion. H
arXiv:2606.26009v2 Announce Type: replace Abstract: Variational Monte Carlo (VMC) is a central algorithm in electronic structure theory and has gained renewed importance through modern neural-network ans\"atze such as FermiNet. At its core, VMC seeks ground states by minimizing the Rayleigh quotient
arXiv:2607.14576v1 Announce Type: new Abstract: We propose \emph{the sublinear-growth principle} for deep residual architectures -- a sharp stability threshold on the input-magnitude exponent of every residual block's velocity field: $$\|v(x, t)\| \leq c\,\|x\|^q + b, \qquad q \in [0, 1].$$ The thre