Results 51 to 60 of about 527,249 (162)

Eigenvalue Corrected Noisy Natural Gradient

, 2018
Variational Bayesian neural networks combine the flexibility of deep learning with Bayesian uncertainty estimation. However, inference procedures for flexible variational posteriors are computationally expensive. A recently proposed method, noisy natural gradient, is a surprisingly simple method to fit expressive posteriors by adding weight noise to ...
Bae, Juhan, Zhang, Guodong, Grosse, Roger   +2 more
openaire   +2 more sources

Quantum natural gradient without monotonicity

Quantum natural gradient without monotonicity
The natural gradient (NG) is an information-geometric optimization method that plays a crucial role, especially in the estimation of parameters for machine learning models like neural networks. To apply NG to quantum systems, the quantum natural gradient (QNG) was introduced and utilized for noisy intermediate-scale devices.
Toi Sasaki, Hideyuki Miyahara
openaire   +3 more sources

Bayesian Online Natural Gradient (BONG)

Advances in Neural Information Processing Systems 37
Final NeurIPS version, updated in response to reviews.
Jones, Matt, Chang, Peter, Murphy, Kevin
openaire   +2 more sources

Acropora tenuis energy acquisition along a natural turbidity gradient

Frontiers in Marine Science
Predicted future increases in both local and global stressors are expected to lead to elevated turbidity levels and an expansion of the geographical range of turbid coral reefs.
Adi Zweifler, Adi Zweifler, Nicola K. Browne, Oren Levy, Renae Hovey, Renae Hovey, Mick O’Leary, Mick O’Leary   +7 more
doaj   +1 more source

Modified conjugate quantum natural gradient

EPJ Quantum Technology
Abstract 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.
openaire   +2 more sources

Natural Gradient Descent for Control

ASME Letters in Dynamic Systems and Control
Abstract This article bridges optimization and control and presents a novel closed-loop control framework based on natural gradient descent, offering a trajectory-oriented alternative to traditional cost-function tuning. We leverage the Fisher information matrix to formulate a preconditioned gradient descent update that offers ...
Esmzad, Ramin, Yaghmaie, Farnaz Adib, Modares, Hamidreza   +2 more
openaire   +2 more sources

Thermodynamic Natural Gradient Descent

Second-order training methods have better convergence properties than gradient descent but are rarely used in practice for large-scale training due to their computational overhead. This can be viewed as a hardware limitation (imposed by digital computers).
Donatella, Kaelan, Duffield, Samuel, Aifer, Maxwell, Melanson, Denis, Crooks, Gavin, Coles, Patrick J.   +5 more
openaire   +2 more sources

Natural gradient ascent in evolutionary games

Biosystems
We study evolutionary games with a continuous trait space in which replicator dynamics are restricted to the manifold of multidimensional Gaussian distributions. We demonstrate that the replicator equations are natural gradient flow for maximization of the mean fitness.
openaire   +3 more sources

On Quantum Natural Policy Gradients

IEEE Transactions on Quantum Engineering
This research delves into the role of the quantum Fisher Information Matrix (FIM) in enhancing the performance of Parameterized Quantum Circuit (PQC)-based reinforcement learning agents. While previous studies have highlighted the effectiveness of PQC-based policies preconditioned with the quantum FIM in contextual bandits, its impact in broader ...
André Sequeira, Luis Paulo Santos, Luis Soares Barbosa   +2 more
openaire   +3 more sources

Efficient quantum circuits based on the quantum natural gradient

Physical Review Research
Efficient preparation of arbitrary entangled quantum states is crucial for quantum computation. This is particularly important for noisy intermediate-scale quantum simulators relying on variational hybrid quantum-classical algorithms.
Ananda Roy, Sameer Erramilli, Robert M. Konik   +2 more
doaj   +1 more source