Skip to search formSkip to main contentSkip to account menu
SEISMIC: A Self-Exciting Point Process Model for Predicting Tweet Popularity
TLDR
This paper builds on the theory of self-exciting point processes to develop a statistical model that allows for accurate predictions of the final number of reshares of a given post, and demonstrates a strong improvement in predictive accuracy over existing approaches.
View on ACM
Convergence rates of sub-sampled Newton methods
TLDR
This paper uses sub-sampling techniques together with low-rank approximation to design a new randomized batch algorithm which possesses comparable convergence rate to Newton's method, yet has much smaller per-iteration cost.
View PDF on arXiv
Generalization of Two-layer Neural Networks: An Asymptotic Viewpoint
TLDR
The exact population risk of the unregularized least squares regression problem with two-layer neural networks when either the first or the second layer is trained using a gradient flow under different initialization setups is derived.
View Paper
Global Non-convex Optimization with Discretized Diffusions
TLDR
This non-asymptotic analysis delivers computable optimization and integration error bounds based on easily accessed properties of the objective and chosen diffusion and complements these results with improved optimization guarantees for targets other than the standard Gibbs measure.
View PDF on arXiv
Estimating LASSO Risk and Noise Level
TLDR
To the best of the knowledge, this result is the first that provides an asymptotically consistent risk estimator for the LASSO solely based on data and it is demonstrated through simulations that the variance estimation outperforms several existing methods in the literature.
View Paper
Accelerating SVRG via second-order information
TLDR
This paper proposes to improve the performance of SVRG by incorporating approximate curvature information while maintaining a per-iteration complexity that is linear in the dimension.
On the Convergence of Langevin Monte Carlo: The Interplay between Tail Growth and Smoothness
TLDR
It is shown that the same rate is achievable for a wider class of potentials that are degenerately convex at infinity, and any order of smoothness ${\beta\in(0,1]}$; consequently, the results are applicable to a wide class of non-convex potentialS that are weakly smooth and exhibit at least linear tail growth.
View PDF on arXiv
Maximum Likelihood for Variance Estimation in High-Dimensional Linear Models
We study maximum likelihood estimators (MLEs) for the residual variance, the signalto-noise ratio, and other variance parameters in high-dimensional linear models. These parameters are essential in…
View Paper
Stochastic Runge-Kutta Accelerates Langevin Monte Carlo and Beyond
TLDR
The convergence rate of sampling algorithms obtained by discretizing smooth Ito diffusions exhibiting fast Wasserstein-$2$ contraction is established, based on local deviation properties of the integration scheme.
View PDF on arXiv
Robust Estimation of Neural Signals in Calcium Imaging
TLDR
This work uses the proposed robust loss in a matrix factorization framework to extract the neurons and their temporal activity in calcium imaging datasets and demonstrates the superiority of the robust estimation approach over existing methods on both simulated and real datasets.
View Paper
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License