Search Results for author: Florian Schäfer

Found 8 papers, 7 papers with code

Polymatrix Competitive Gradient Descent

no code implementations16 Nov 2021 Jeffrey Ma, Alistair Letcher, Florian Schäfer, Yuanyuan Shi, Anima Anandkumar

In this work we propose polymatrix competitive gradient descent (PCGD) as a method for solving general sum competitive optimization involving arbitrary numbers of agents.

Multi-agent Reinforcement Learning

ZerO Initialization: Initializing Residual Networks with only Zeros and Ones

1 code implementation25 Oct 2021 Jiawei Zhao, Florian Schäfer, Anima Anandkumar

Deep neural networks are usually initialized with random weights, with adequately selected initial variance to ensure stable signal propagation during training.

Image Classification

Competitive Mirror Descent

3 code implementations17 Jun 2020 Florian Schäfer, Anima Anandkumar, Houman Owhadi

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

1 code implementation29 Apr 2020 Florian Schäfer, Matthias Katzfuss, Houman Owhadi

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

2 code implementations ICML 2020 Florian Schäfer, Hongkai Zheng, Anima Anandkumar

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.

Image Generation

Competitive Gradient Descent

7 code implementations NeurIPS 2019 Florian Schäfer, Anima Anandkumar

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

3 code implementations20 Sep 2017 Leon Thurner, Alexander Scheidler, Florian Schäfer, Jan-Hendrik Menke, Julian Dollichon, Friederike Meier, Steffen Meinecke, Martin Braun

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

1 code implementation7 Jun 2017 Florian Schäfer, T. J. Sullivan, Houman Owhadi

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

Cannot find the paper you are looking for? You can Submit a new open access paper.