
-
SGD in the Large: Average-case Analysis, Asymptotics, and Stepsize Criticality
We propose a new framework, inspired by random matrix theory, for analyz...
read it
-
Average-case Acceleration for Bilinear Games and Normal Matrices
Advances in generative modeling and adversarial learning have given rise...
read it
-
Halting Time is Predictable for Large Models: A Universality Property and Average-case Analysis
Average-case analysis computes the complexity of an algorithm averaged o...
read it
-
Average-case Acceleration Through Spectral Density Estimation
We develop a framework for designing optimal quadratic optimization meth...
read it
-
A Test for Shared Patterns in Cross-modal Brain Activation Analysis
Determining the extent to which different cognitive modalities (understo...
read it
-
SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
SciPy is an open source scientific computing library for the Python prog...
read it
-
The Difficulty of Training Sparse Neural Networks
We investigate the difficulties of training sparse neural networks and m...
read it
-
Information matrices and generalization
This work revisits the use of information criteria to characterize the g...
read it
-
Frank-Wolfe Splitting via Augmented Lagrangian Method
Minimizing a function over an intersection of convex sets is an importan...
read it
-
Adaptive Three Operator Splitting
We propose and analyze a novel adaptive step size variant of the Davis-Y...
read it
-
Frank-Wolfe with Subsampling Oracle
We analyze two novel randomized variants of the Frank-Wolfe (FW) or cond...
read it
-
Breaking the Nonsmooth Barrier: A Scalable Parallel Method for Composite Optimization
Due to their simplicity and excellent performance, parallel asynchronous...
read it
-
On the convergence rate of the three operator splitting scheme
The three operator splitting scheme was recently proposed by [Davis and ...
read it
-
ASAGA: Asynchronous Parallel SAGA
We describe ASAGA, an asynchronous parallel version of the incremental g...
read it
-
Hyperparameter optimization with approximate gradient
Most models in machine learning contain at least one hyperparameter to c...
read it
-
Machine Learning for Neuroimaging with Scikit-Learn
Statistical machine learning methods are increasingly used for neuroimag...
read it
-
Second order scattering descriptors predict fMRI activity due to visual textures
Second layer scattering descriptors are known to provide good classifica...
read it
-
Learning to rank from medical imaging data
Medical images can be used to predict a clinical score coding for the se...
read it
-
Improved brain pattern recovery through ranking approaches
Inferring the functional specificity of brain regions from functional Ma...
read it