Search Results for author:
Found 10 papers, 2 papers with code
An Improved Analysis of Langevin Algorithms with Prior Diffusion for Non-Log-Concave Sampling
Along this line, Freund et al. (2022) suggest that the modified Langevin algorithm with prior diffusion is able to converge dimension independently for strongly log-concave target distributions.
Faster Sampling without Isoperimetry via Diffusion-based Monte Carlo
Specifically, DMC follows the reverse SDE of a diffusion process that transforms the target distribution to the standard Gaussian, utilizing a non-parametric score estimation.
Mean-Field Analysis of Two-Layer Neural Networks: Global Optimality with Linear Convergence Rates
We consider optimizing two-layer neural networks in the mean-field regime where the learning dynamics of network weights can be approximated by the evolution in the space of probability measures over the weight parameters associated with the neurons.
Adaptive Gradient Methods Can Be Provably Faster than SGD with Random Shuffling
Adaptive gradient methods have been shown to outperform SGD in many tasks of training neural networks.
ACMo: Angle-Calibrated Moment Methods for Stochastic Optimization
Due to its simplicity and outstanding ability to generalize, stochastic gradient descent (SGD) is still the most widely used optimization method despite its slow convergence.
Adaptive Gradient Methods Can Be Provably Faster than SGD after Finite Epochs
Adaptive gradient methods have attracted much attention of machine learning communities due to the high efficiency.
SPAN: A Stochastic Projected Approximate Newton Method
SPAN computes the inverse of the Hessian matrix via low-rank approximation and stochastic Hessian-vector products.
Acutum: When Generalization Meets Adaptability
To the best of our knowledge, Acutum is the first adaptive gradient method without second moments.
Enhancing Network Embedding with Auxiliary Information: An Explicit Matrix Factorization Perspective
In this paper, we take a matrix factorization perspective of network embedding, and incorporate structure, content and label information of the network simultaneously.
