Second-order optimisation strategies for neural network quantum states

• URL: http://arxiv.org/abs/2401.17550v1
• Date: Wed, 31 Jan 2024 02:34:14 GMT
• Title: Second-order optimisation strategies for neural network quantum states
• Authors: M. Drissi, J. W. T. Keeble, J. Rozal\'en Sarmiento, A. Rios
• Abstract summary: We revisit the Kronecker Factored Approximate Curvature, an optimiser that has been used extensively in a variety of simulations. We reformulate the Variational Monte Carlo approach in a game theory framework, to propose a novel optimiser based on decision geometry. We find that, on a practical test case for continuous systems, this new optimiser consistently outperforms any of the KFAC improvements in terms of stability, accuracy and speed of convergence.
• Score: 1.814143871199829
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The Variational Monte Carlo method has recently seen important advances through the use of neural network quantum states. While more and more sophisticated ans\"atze have been designed to tackle a wide variety of quantum many-body problems, modest progress has been made on the associated optimisation algorithms. In this work, we revisit the Kronecker Factored Approximate Curvature, an optimiser that has been used extensively in a variety of simulations. We suggest improvements on the scaling and the direction of this optimiser, and find that they substantially increase its performance at a negligible additional cost. We also reformulate the Variational Monte Carlo approach in a game theory framework, to propose a novel optimiser based on decision geometry. We find that, on a practical test case for continuous systems, this new optimiser consistently outperforms any of the KFAC improvements in terms of stability, accuracy and speed of convergence. Beyond Variational Monte Carlo, the versatility of this approach suggests that decision geometry could provide a solid foundation for accelerating a broad class of machine learning algorithms.

Related papers

• A Stochastic Approach to Bi-Level Optimization for Hyperparameter Optimization and Meta Learning [74.80956524812714]
  We tackle the general differentiable meta learning problem that is ubiquitous in modern deep learning. These problems are often formalized as Bi-Level optimizations (BLO) We introduce a novel perspective by turning a given BLO problem into a ii optimization, where the inner loss function becomes a smooth distribution, and the outer loss becomes an expected loss over the inner distribution.
  arXiv  Detail & Related papers  (2024-10-14T12:10:06Z)
• Analyzing and Enhancing the Backward-Pass Convergence of Unrolled Optimization [50.38518771642365]
  The integration of constrained optimization models as components in deep networks has led to promising advances on many specialized learning tasks. A central challenge in this setting is backpropagation through the solution of an optimization problem, which often lacks a closed form. This paper provides theoretical insights into the backward pass of unrolled optimization, showing that it is equivalent to the solution of a linear system by a particular iterative method. A system called Folded Optimization is proposed to construct more efficient backpropagation rules from unrolled solver implementations.
  arXiv  Detail & Related papers  (2023-12-28T23:15:18Z)
• Quantum algorithm for robust optimization via stochastic-gradient online learning [0.0]
  We consider the online robust optimization meta-algorithm by Ben-Tal et al. and show that for a large range of subgradients, this algorithm has the same guarantee as the original non-stochastic version. We develop a quantum version of this algorithm and show that an at most quadratic improvement in terms of the dimension can be achieved.
  arXiv  Detail & Related papers  (2023-04-05T07:25:07Z)
• Socio-cognitive Optimization of Time-delay Control Problems using Evolutionary Metaheuristics [89.24951036534168]
  Metaheuristics are universal optimization algorithms which should be used for solving difficult problems, unsolvable by classic approaches. In this paper we aim at constructing novel socio-cognitive metaheuristic based on castes, and apply several versions of this algorithm to optimization of time-delay system model.
  arXiv  Detail & Related papers  (2022-10-23T22:21:10Z)
• Markov Chain Monte-Carlo Enhanced Variational Quantum Algorithms [0.0]
  We introduce a variational quantum algorithm that uses Monte Carlo techniques to place analytic bounds on its time-complexity. We demonstrate both the effectiveness of our technique and the validity of our analysis through quantum circuit simulations for MaxCut instances.
  arXiv  Detail & Related papers  (2021-12-03T23:03:44Z)
• A theoretical and empirical study of new adaptive algorithms with additional momentum steps and shifted updates for stochastic non-convex optimization [0.0]
  It is thought that adaptive optimization algorithms represent the key pillar behind the of the Learning field. In this paper we introduce adaptive momentum techniques for different non-smooth objective problems.
  arXiv  Detail & Related papers  (2021-10-16T09:47:57Z)
• SUPER-ADAM: Faster and Universal Framework of Adaptive Gradients [99.13839450032408]
  It is desired to design a universal framework for adaptive algorithms to solve general problems. In particular, our novel framework provides adaptive methods under non convergence support for setting.
  arXiv  Detail & Related papers  (2021-06-15T15:16:28Z)
• Bayesian Optimisation for Constrained Problems [0.0]
  We propose a novel variant of the well-known Knowledge Gradient acquisition function that allows it to handle constraints. We empirically compare the new algorithm with four other state-of-the-art constrained Bayesian optimisation algorithms and demonstrate its superior performance.
  arXiv  Detail & Related papers  (2021-05-27T15:43:09Z)
• Quantum variational optimization: The role of entanglement and problem hardness [0.0]
  We study the role of entanglement, the structure of the variational quantum circuit, and the structure of the optimization problem. Our numerical results indicate an advantage in adapting the distribution of entangling gates to the problem's topology. We find evidence that applying conditional value at risk type cost functions improves the optimization, increasing the probability of overlap with the optimal solutions.
  arXiv  Detail & Related papers  (2021-03-26T14:06:54Z)
• Meta-Learning with Neural Tangent Kernels [58.06951624702086]
  We propose the first meta-learning paradigm in the Reproducing Kernel Hilbert Space (RKHS) induced by the meta-model's Neural Tangent Kernel (NTK) Within this paradigm, we introduce two meta-learning algorithms, which no longer need a sub-optimal iterative inner-loop adaptation as in the MAML framework. We achieve this goal by 1) replacing the adaptation with a fast-adaptive regularizer in the RKHS; and 2) solving the adaptation analytically based on the NTK theory.
  arXiv  Detail & Related papers  (2021-02-07T20:53:23Z)
• A Dynamical Systems Approach for Convergence of the Bayesian EM Algorithm [59.99439951055238]
  We show how (discrete-time) Lyapunov stability theory can serve as a powerful tool to aid, or even lead, in the analysis (and potential design) of optimization algorithms that are not necessarily gradient-based. The particular ML problem that this paper focuses on is that of parameter estimation in an incomplete-data Bayesian framework via the popular optimization algorithm known as maximum a posteriori expectation-maximization (MAP-EM) We show that fast convergence (linear or quadratic) is achieved, which could have been difficult to unveil without our adopted S&C approach.
  arXiv  Detail & Related papers  (2020-06-23T01:34:18Z)

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.