arXiv Statistics ML
Tensor-normal maximum likelihood estimation at the operator-norm sample threshold
Read the original on arXiv Statistics ML →The Flow has not summarised this story yet — read it at arXiv Statistics ML.
Related stories
arXiv Statistics ML
2d ago
Information-Theoretic Bounds for Sparse Covariance Estimation in the Vertical-Split Distributed Model
arXiv:2606.07124v2 Announce Type: replace-cross Abstract: We study the minimax estimation error for distributed covariance matrix estimation in the vertical-split (feature-split) setting, where two a...
arXiv Machine Learning
1d ago
Accurate Trace Estimation with Fewer Random Bits via Recursive TensorSketch
arXiv:2609.18577v1 Announce Type: new Abstract: We consider the problem of estimating the trace of an implicit matrix $\mathbf{A} \in \mathbb{R}^{d^p\times d^p}$ that can only be accessed through mat...
arXiv Machine Learning
Sep 7
Centered Permutation Prefixes for SGD with Random Reshuffling: Sharp Rates, H\"older Geometry, and Composite Proximal Extensions
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).
arXiv Machine Learning
Aug 14
Minimax and Adaptive Covariance Matrix Estimation under Differential Privacy
arXiv:2603. 19703v2 Announce Type: replace-cross Abstract: Estimating covariance matrices is fundamental to a wide range of statistical applications.
arXiv Machine Learning
Aug 14
Active-Trace Complexity Bounds for Moreau--Yosida Unadjusted Langevin Sampling
arXiv:2608. 13467v1 Announce Type: new Abstract: We study the Moreau--Yosida unadjusted Langevin algorithm (MYULA) for the nonsmooth composite target \[ \pi(dx)\propto \exp\{-f(x)-g(x)\}\,dx, \qquad x\in\mathbb R^d, \] where \(f\) is \(m\)-strongly convex with \(L_f\)-Lipschitz gradient and \(g\) is convex and \(G\)-Lipschitz.
Hugging Face Trending Papers
Aug 5
The Sample Complexity of Distributionally Robust PAC Learning under Cressie--Read Divergences
We study distributionally robust PAC learning for the $0$--$1$-loss, where adversarial perturbations of the data distribution are constrained by a Cressie--Read divergence of order $k>1$ and radius $ρ\geq 0$. For hypothesis classes with VC dimension $d$, we establish realizable and agnostic sample-complexity bounds tight up to constant and logarithmic factors, respectively; ordinary empirical risk minimization attains both rates up to logarithmic factors.