Search Results for author:
Found 11 papers, 10 papers with code
InRank: Incremental Low-Rank Learning
To remedy this, we design a new training algorithm Incremental Low-Rank Learning (InRank), which explicitly expresses cumulative weight updates as low-rank matrices while incrementally augmenting their ranks during training.
Sparse Cholesky Factorization for Solving Nonlinear PDEs via Gaussian Processes
The primary goal of this paper is to provide a near-linear complexity algorithm for working with such kernel matrices.
Competitive Physics Informed Networks
Neural networks can be trained to solve partial differential equations (PDEs) by using the PDE residual as the loss function.
Polymatrix Competitive Gradient Descent
In this work we propose polymatrix competitive gradient descent (PCGD) as a method for solving general sum competitive optimization involving arbitrary numbers of agents.
ZerO Initialization: Initializing Neural Networks with only Zeros and Ones
Deep neural networks are usually initialized with random weights, with adequately selected initial variance to ensure stable signal propagation during training.
Competitive Mirror Descent
Finally, we obtain the next iterate by following this direction according to the dual geometry induced by the Bregman potential.
Sparse Cholesky factorization by Kullback-Leibler minimization
We propose to compute a sparse approximate inverse Cholesky factor $L$ of a dense covariance matrix $\Theta$ by minimizing the Kullback-Leibler divergence between the Gaussian distributions $\mathcal{N}(0, \Theta)$ and $\mathcal{N}(0, L^{-\top} L^{-1})$, subject to a sparsity constraint.
Numerical Analysis Numerical Analysis Optimization and Control Statistics Theory Computation Statistics Theory
Implicit competitive regularization in GANs
We show that opponent-aware modelling of generator and discriminator, as present in competitive gradient descent (CGD), can significantly strengthen ICR and thus stabilize GAN training without explicit regularization.
Competitive Gradient Descent
We introduce a new algorithm for the numerical computation of Nash equilibria of competitive two-player games.
pandapower - an Open Source Python Tool for Convenient Modeling, Analysis and Optimization of Electric Power Systems
pandapower is a Python based, BSD-licensed power system analysis tool aimed at automation of static and quasi-static analysis and optimization of balanced power systems.
Computational Engineering, Finance, and Science
Compression, inversion, and approximate PCA of dense kernel matrices at near-linear computational complexity
This block-factorisation can provably be obtained in complexity $\mathcal{O} ( N \log( N ) \log^{d}( N /\epsilon) )$ in space and $\mathcal{O} ( N \log^{2}( N ) \log^{2d}( N /\epsilon) )$ in time.
Numerical Analysis Computational Complexity Data Structures and Algorithms Probability 65F30, 42C40, 65F50, 65N55, 65N75, 60G42, 68Q25, 68W40
