Search Results for author:
Found 11 papers, 7 papers with code
Steering Deep Feature Learning with Backward Aligned Feature Updates
Deep learning succeeds by doing hierarchical feature learning, yet tuning Hyper-Parameters (HP) such as initialization scales, learning rates etc., only give indirect control over this behavior.
Computational Guarantees for Doubly Entropic Wasserstein Barycenters via Damped Sinkhorn Iterations
We study the computation of doubly regularized Wasserstein barycenters, a recently introduced family of entropic barycenters governed by inner and outer regularization strengths.
Local Convergence of Gradient Methods for Min-Max Games: Partial Curvature Generically Suffices
We show that these dynamics also converge as soon as $S$ is nonzero (partial curvature) and the eigenvectors of the antisymmetric part $A$ are in general position with respect to the kernel of $S$.
On the Effect of Initialization: The Scaling Path of 2-Layer Neural Networks
In supervised learning, the regularization path is sometimes used as a convenient theoretical proxy for the optimization path of gradient descent initialized from zero.
Doubly Regularized Entropic Wasserstein Barycenters
In particular, it can be estimated efficiently: given $n$ samples from each of the probability measures, it converges in relative entropy to the population barycenter at a rate $n^{-1/2}$.
Infinite-width limit of deep linear neural networks
We finally study the continuous-time limit obtained for infinitely wide linear neural networks and show that the linear predictors of the neural network converge at an exponential rate to the minimal $\ell_2$-norm minimizer of the risk.
An Exponentially Converging Particle Method for the Mixed Nash Equilibrium of Continuous Games
We consider the problem of computing mixed Nash equilibria of two-player zero-sum games with continuous sets of pure strategies and with first-order access to the payoff function.
Trajectory Inference via Mean-field Langevin in Path Space
Trajectory inference aims at recovering the dynamics of a population from snapshots of its temporal marginals.
Training Integrable Parameterizations of Deep Neural Networks in the Infinite-Width Limit
For two-layer neural networks, it has been understood via these asymptotics that the nature of the trained model radically changes depending on the scale of the initial random weights, ranging from a kernel regime (for large initial variance) to a feature learning regime (for small initial variance).
Statistical and Topological Properties of Sliced Probability Divergences
The idea of slicing divergences has been proven to be successful when comparing two probability measures in various machine learning applications including generative modeling, and consists in computing the expected value of a `base divergence' between one-dimensional random projections of the two measures.
HexaShrink, an exact scalable framework for hexahedral meshes with attributes and discontinuities: multiresolution rendering and storage of geoscience models
Efficient representations and storage are thus becoming "enabling technologies'' in HPC experimental and simulation science.
