Momentum Accelerates Evolutionary Dynamics

• URL: http://arxiv.org/abs/2007.02449v1
• Date: Sun, 5 Jul 2020 21:09:30 GMT
• Title: Momentum Accelerates Evolutionary Dynamics
• Authors: Marc Harper and Joshua Safyan
• Abstract summary: We show that momentum accelerates the convergence of evolutionary dynamics including the replicator equation and Euclidean gradient descent on populations. We also show that momentum can alter the convergence properties of these dynamics, for example by breaking the cycling associated to the rock-paper-scissors landscape.
• Score: 4.061135251278187
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We combine momentum from machine learning with evolutionary dynamics, where momentum can be viewed as a simple mechanism of intergenerational memory. Using information divergences as Lyapunov functions, we show that momentum accelerates the convergence of evolutionary dynamics including the replicator equation and Euclidean gradient descent on populations. When evolutionarily stable states are present, these methods prove convergence for small learning rates or small momentum, and yield an analytic determination of the relative decrease in time to converge that agrees well with computations. The main results apply even when the evolutionary dynamic is not a gradient flow. We also show that momentum can alter the convergence properties of these dynamics, for example by breaking the cycling associated to the rock-paper-scissors landscape, leading to either convergence to the ordinarily non-absorbing equilibrium, or divergence, depending on the value and mechanism of momentum.

Related papers

• Artificial Kuramoto Oscillatory Neurons [65.16453738828672]
  We introduce Artificial Kuramotoy Neurons (AKOrN) as a dynamical alternative to threshold units. We show that this idea provides performance improvements across a wide spectrum of tasks. We believe that these empirical results show the importance of our assumptions at the most basic neuronal level of neural representation.
  arXiv  Detail & Related papers  (2024-10-17T17:47:54Z)
• Nested replicator dynamics, nested logit choice, and similarity-based learning [56.98352103321524]
  We consider a model of learning and evolution in games with action sets endowed with a partition-based similarity structure. In this model, revising agents have a higher probability of comparing their current strategy with other strategies that they deem similar. Because of this implicit bias toward similar strategies, the resulting dynamics do not satisfy any of the standard monotonicity rationalitys for imitative game dynamics.
  arXiv  Detail & Related papers  (2024-07-25T07:09:53Z)
• Dynamics of inhomogeneous spin ensembles with all-to-all interactions: breaking permutational invariance [49.1574468325115]
  We investigate the consequences of introducing non-uniform initial conditions in the dynamics of spin ensembles characterized by all-to-all interactions. We find that the dynamics of the spin ensemble now spans a more expansive effective Hilbert space.
  arXiv  Detail & Related papers  (2023-09-19T16:44:14Z)
• Speed limits to fluctuation dynamics [0.0]
  Fluctuation dynamics of an experimentally measured observable offer a primary signal for nonequilibrium systems. We develop a theory concerning rigorous limits to the rate of fluctuation growth. Our results open an avenue toward a quantitative theory of fluctuation dynamics in various non-equilibrium systems.
  arXiv  Detail & Related papers  (2023-09-13T20:49:48Z)
• Hyper-acceleration of quantum thermalization dynamics by bypassing long-lived coherences: An analytical treatment [0.0]
  We develop a perturbative technique for solving Markovian quantum dissipative dynamics. We show how to bypass a long-lived coherent dynamics and accelerate the relaxation to thermal equilibration in a hyper-exponential manner.
  arXiv  Detail & Related papers  (2023-01-15T16:34:02Z)
• Feedback-induced interactive dynamics: unitary but dissipative evolution [0.0]
  We show that measurement feedback and temporal discretization can give rise to a new type of quantum dynamics characterized by unitary but dissipative evolution. A nonequilibrium steady state with spontaneous symmetry breaking is revealed in a zero-dimensional (single-qubit) system.
  arXiv  Detail & Related papers  (2022-11-17T02:05:10Z)
• Entanglement and correlations in fast collective neutrino flavor oscillations [68.8204255655161]
  Collective neutrino oscillations play a crucial role in transporting lepton flavor in astrophysical settings. We study the full out-of-equilibrium flavor dynamics in simple multi-angle geometries displaying fast oscillations. We present evidence that these fast collective modes are generated by the same dynamical phase transition.
  arXiv  Detail & Related papers  (2022-03-05T17:00:06Z)
• Discovering Latent Causal Variables via Mechanism Sparsity: A New Principle for Nonlinear ICA [81.4991350761909]
  Independent component analysis (ICA) refers to an ensemble of methods which formalize this goal and provide estimation procedure for practical application. We show that the latent variables can be recovered up to a permutation if one regularizes the latent mechanisms to be sparse.
  arXiv  Detail & Related papers  (2021-07-21T14:22:14Z)
• Engineered dissipation induced entanglement transition in quantum spin chains: from logarithmic growth to area law [0.0]
  Recent theoretical work has shown that the competition between coherent unitary dynamics and measurements can give rise to transitions in the entanglement scaling. We consider an engineered dissipation, which stabilizes an entangled phase of a quantum spin$-1/2$ chain. We find that the system undergoes an entanglement transition from a logarithmic growth to an area law when the competition ratio between the unitary evolution and the non-unitary dynamics increases.
  arXiv  Detail & Related papers  (2021-06-18T12:41:01Z)
• Exponentially accelerated approach to stationarity in Markovian open quantum systems through the Mpemba effect [0.0]
  We show that the relaxation dynamics of Markovian open quantum systems can be accelerated exponentially by devising an optimal unitary transformation. This initial "rotation" is engineered in such a way that the state of the quantum system becomes to the slowest decaying dynamical mode. We illustrate our idea by showing how to achieve an exponential speed-up in the convergence to stationarity in Dicke models.
  arXiv  Detail & Related papers  (2021-03-08T19:02:31Z)
• Gradient Starvation: A Learning Proclivity in Neural Networks [97.02382916372594]
  Gradient Starvation arises when cross-entropy loss is minimized by capturing only a subset of features relevant for the task. This work provides a theoretical explanation for the emergence of such feature imbalance in neural networks.
  arXiv  Detail & Related papers  (2020-11-18T18:52:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.