Recent years have witnessed substantial progress in understanding the behavior of EM for mixture models that are correctly specified.

We first modify the algorithm of Chekuri et al. (2010) to achieve a(1 1/e) approximation for m=o( klog3k),with 0ask .

For large-scale databases the sequential scan with theO(nd) complexity is not feasible, and the efficient approximate methods arerequired.

The sparse generalized eigenvalue problem (SGEP) aims to find the leading eigenvector with sparsity structure. SGEP plays an important role in statistical learning and has wide applications including, but not limited to, sparse principal component analysis, sparse canonical correlation analysis and sparse Fisher discriminant analysis, etc. Due to the sparsity constraint, the solution of SGEP entails interesting properties from both numerical and statistical perspectives. In this paper, we provide a detailed sensitivity analysis for SGEP and establish the rate-optimal perturbation bound under the sparse setting. Specifically, we show that the bound is related to the perturbation/noise level and the recovery of the true support of the leading eigenvector as well. We also investigate the estimator of SGEP via imposing a non-convex regularization. Such estimator can achieve the optimal error rate and can recover the sparsity structure as well. Extensive numerical experiments corroborate our theoretical findings via using alternating direction method of multipliers (ADMM)-based computational method.

A.1 Remarks on executed benchmarks We executed all benchmarks faithfully and to the best of our knowledge. In particular, with regards to the multi-modal transformer scaling behavior, as there are in fact no such studies for AR models yet to compare to. The integration of Chefer was straightforward. We did not further investigate or fine-tune evaluations to any method. In Figure 1 we ran Chefer with a full backward pass.

The global dimensionality of a neural representation manifold provides rich insight into the computational process underlying both artificial and biological neural networks. However, all existing measures of global dimensionality are sensitive to the number of samples, i.e., the number of rows and columns of the sample matrix. We show that, in particular, the participation ratio of eigenvalues, a popular measure of global dimensionality, is highly biased with small sample sizes, and propose a bias-corrected estimator that is more accurate with finite samples and with noise. On synthetic data examples, we demonstrate that our estimator can recover the true known dimensionality. We apply our estimator to neural brain recordings, including calcium imaging, electrophysiological recordings, and fMRI data, and to the neural activations in a large language model and show our estimator is invariant to the sample size. Finally, our estimators can additionally be used to measure the local dimensionalities of curved neural manifolds by weighting the finite samples appropriately.

We consider inferring the causal effect of a treatment (intervention) on an outcome of interest in situations where there is potentially an unobserved confounder influencing both the treatment and the outcome. This is achievable by assuming access to two separate sets of control (proxy) measurements associated with treatment and outcomes, which are used to estimate treatment effects through a function termed the em causal bridge (CB). We present a new theoretical perspective, associated assumptions for when estimating treatment effects with the CB is feasible, and a bound on the average error of the treatment effect when the CB assumptions are violated. From this new perspective, we then demonstrate how coupling the CB with an autoencoder architecture allows for the sharing of statistical strength between observed quantities (proxies, treatment, and outcomes), thus improving the quality of the CB estimates. Experiments on synthetic and real-world data demonstrate the effectiveness of the proposed approach in relation to the state-of-the-art methodology for proxy measurements.

Tensors, as higher-order generalizations of matrices, have emerged as powerful tools for representing and analyzing multi-dimensional data. They naturally arise in diverse applications such as multi-relational networks, spatiotemporal measurements, neuroimaging, and latent variable models. Unlike matrices, which capture only pairwise relationships, tensors encode multi-way interactions, offering richer structural insights. Among the various tensor models, orthogonally decomposable (odeco) tensors play a special role. Their decomposition structure parallels the eigendecomposi-tion of matrices, but with important advantages in both statistical robustness and computational tractability. In particular, odeco tensors arise in the method of moments for latent variable models.