Results 11 to 20 of about 6,455,829 (284)
QuantumHybrid quantum-classical algorithms appear to be the most promising approach for near-term quantum applications. An important bottleneck is the classical optimization loop, where the multiple local minima and the emergence of barren plateaux make these ...
Ioannis Kolotouros, Petros Wallden
doaj +5 more sources
Compatible natural gradient policy search [PDF]
Machine Learning, 2019 Trust-region methods have yielded state-of-the-art results in policy search. A common approach is to use KL-divergence to bound the region of trust resulting in a natural gradient policy update. We show that the natural gradient and trust region optimization are equivalent if we use the natural parameterization of a standard exponential policy ...
Joni Pajarinen +4 more
core +11 more sources
A Simplified Natural Gradient LearningAlgorithm [PDF]
Advances in Artificial Neural Systems, 2011 Adaptive natural gradient learning avoids singularities in the parameter space of multilayer perceptrons. However, it requires a larger number of additional parameters than ordinary backpropagation in the form of the Fisher information matrix. This paper describes a new approach to natural gradient learning that uses a smaller Fisher information matrix.
Michael R. Bastian +2 more
openaire +3 more sources
Kernelized Wasserstein Natural Gradient
CoRR, 2019 Many machine learning problems can be expressed as the optimization of some cost functional over a parametric family of probability distributions. It is often beneficial to solve such optimization problems using natural gradient methods. These methods are invariant to the parametrization of the family, and thus can yield more effective optimization ...
Michael Arbel +3 more
core +7 more sources
Natural gradient matrix momentum [PDF]
, 1999 Natural gradient learning is an efficient and principled method for improving on-line learning. In practical applications there will be an increased cost required in estimating and inverting the Fisher information matrix.
Rattray, Magnus +2 more
core +9 more sources
Modified conjugate quantum natural gradient
EPJ Quantum TechnologyAbstract The efficient optimization of variational quantum algorithms (VQAs) is critical for their successful application in quantum computing. The Quantum Natural Gradient (QNG) method, which leverages the geometry of quantum state space, has demonstrated improved convergence compared to standard gradient descent (Stokes et al.
Halla, Mourad
core +6 more sources
A Natural Policy Gradient. [PDF]
, 2001 We provide a natural gradient method that represents the steepest descent direction based on the underlying structure of the parameter space. Although gradient methods cannot make large changes in the values of the parameters, we show that the natural gradient is moving toward choosing a greedy optimal action rather than just a better action.
Kakade, Sham M
openaire +3 more sources
Natural Gradient Shared Control [PDF]
2020 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), 2020 We propose a formalism for shared control, which is the problem of defining a policy that blends user control and autonomous control. The challenge posed by the shared autonomy system is to maintain user control authority while allowing the robot to support the user. This can be done by enforcing constraints or acting optimally when the intent is clear.
Yoojin Oh +3 more
openaire +3 more sources
Dual Stochastic Natural Gradient Descent
CoRR, 2020 [EN] Although theoretically appealing, Stochastic Natural Gradient Descent (SNGD) is computationally expensive, it has been shown to be highly sensitive to the learning rate, and it is not guaranteed to be convergent. Convergent Stochastic Natural Gradient Descent (CSNGD) aims at solving the last two problems.
Sánchez-López, Borja +1 more
openaire +3 more sources
On the Natural Gradient of the Evidence Lower Bound
J. Mach. Learn. Res., 2023 This article studies the Fisher-Rao gradient, also referred to as the natural gradient, of the evidence lower bound (ELBO) which plays a central role in generative machine learning. It reveals that the gap between the evidence and its lower bound, the ELBO, has essentially a vanishing natural gradient within unconstrained optimization.
Ay, Nihat +2 more
openaire +3 more sources