Complex Momentum for Optimization in Games

2021-02-16 · Jonathan Lorraine, David Acuna, Paul Vicol, David Duvenaud

We generalize gradient descent with momentum for optimization in differentiable games to have complex-valued momentum. We give theoretical motivation for our method by proving convergence on bilinear zero-sum games for simultaneous and alternating updates. Our method gives real-valued parameter updates, making it a drop-in replacement for standard optimizers. We empirically demonstrate that complex-valued momentum can improve convergence in realistic adversarial games - like generative adversarial networks - by showing we can find better solutions with an almost identical computational cost. We also show a practical generalization to a complex-valued Adam variant, which we use to train BigGAN to better inception scores on CIFAR-10.

📄 PDF Abstract BibTeX arXiv:2102.08431

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Six Ways To Communicate To Someone At Expedia Via Phone And Email's. To communicate or get human at Expedia, the quickest option is typically to call their customer service at ＋１－８８８－８２９－０８８１　ｏｒ　＋１（８０５）　３３０　（４０５６）. You can also use the live chat…

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

((Reservation@Faqs))How do I cancel a reservation on Expedia? How do I cancel a reservation on Expedia? +1^888^829^0881° oR +1^888^829^0881 – Need to cancel your Expedia reservation quickly and without hassle? This step-by-step guide…

Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…

Residual Connection 설명 없음

Non-Local Operation A Non-Local Operation is a component for capturing long-range dependencies with deep neural networks. It is a generalization of the classical non-local mean operation in…

GAN Hinge Loss The GAN Hinge Loss is a hinge loss based loss function for [generative adversarial…

Negative Momentum for Improved Game Dynamics

2018-07-12 · Gauthier Gidel, Reyhane Askari Hemmat, Mohammad Pezeshki, Remi Lepriol 외

Games generalize the single-objective optimization paradigm by introducing different objective functions for different players. Differentiable games often proceed by simultaneous or alternating gradient updates. In machi…

On the Suboptimality of Negative Momentum for Minimax Optimization

2020-08-17 · Guodong Zhang, Yuanhao Wang

Smooth game optimization has recently attracted great interest in machine learning as it generalizes the single-objective optimization paradigm. However, game dynamics is more complex due to the interaction between diffe…

When is Momentum Extragradient Optimal? A Polynomial-Based Analysis

2022-11-09 · Junhyung Lyle Kim, Gauthier Gidel, Anastasios Kyrillidis, Fabian Pedregosa

The extragradient method has gained popularity due to its robust convergence properties for differentiable games. Unlike single-objective optimization, game dynamics involve complex interactions reflected by the eigenval…

Momentum in Reinforcement Learning

2019-10-21 · Nino Vieillard, Bruno Scherrer, Olivier Pietquin, Matthieu Geist

We adapt the optimization's concept of momentum to reinforcement learning. Seeing the state-action value functions as an analog to the gradients in optimization, we interpret momentum as an average of consecutive $q$-fun…

Atari Games reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Accelerating Smooth Games by Manipulating Spectral Shapes

2020-01-02 · Waïss Azizian, Damien Scieur, Ioannis Mitliagkas, Simon Lacoste-Julien 외

We use matrix iteration theory to characterize acceleration in smooth games. We define the spectral shape of a family of games as the set containing all eigenvalues of the Jacobians of standard gradient dynamics in the f…