Abstract:Fixed-point iterations are at the heart of numerical computing and are often a computational bottleneck in real-time applications that typically need a fast solution of moderate accuracy. We present neural fixed-point acceleration which combines ideas from meta-learning and classical acceleration methods to automatically learn to accelerate fixed-point problems that are drawn from a distribution. We apply our framework to SCS, the state-of-the-art solver for convex cone programming, and design models and loss … Show more
“…In addition to the development of the methodologies, another trend is to explore new applications in wireless networks. Besides the optimization problems mentioned before, learning to optimize techniques are expected to solve other problems involved in wireless communication for future research directions, including multi-object optimization problems [245], bi-level optimization problems [246], conic programming [247], maximum-likelihood estimation problems [248], etc, in various emerging applications.…”
Section: ) Advanced Methodologies and Extended Applications Of Moasmentioning
The sixth generation (6G) wireless systems are envisioned to enable the paradigm shift from "connected things" to "connected intelligence", featured by ultra high density, largescale, dynamic heterogeneity, diversified functional requirements and machine learning capabilities, which leads to a growing need for highly efficient intelligent algorithms. The classic optimization-based algorithms usually require highly precise mathematical model of data links and suffer from poor performance with high computational cost in realistic 6G applications. Based on domain knowledge (e.g., optimization models and theoretical tools), machine learning (ML) stands out as a promising and viable methodology for many complex large-scale optimization problems in 6G, due to its superior performance, generalizability, computational efficiency and robustness. In this paper, we systematically review the most representative "learning to optimize" techniques in diverse domains of 6G wireless networks by identifying the inherent feature of the underlying optimization problem and investigating the specifically designed ML frameworks from the perspective of optimization. In particular, we will cover algorithm unrolling, learning to branch-andbound, graph neural network for structured optimization, deep reinforcement learning for stochastic optimization, as well as endto-end learning for semantic optimization, for solving challenging large-scale optimization problems arising from various important wireless applications. To enable ML implementation in distributed wireless networks across massive number of end devices, federated learning for distributed optimization will further be presented. Through the in-depth discussion, we shed light on the excellent performance of ML-based optimization algorithms with respect to the classical methods, and provide insightful guidance to develop advanced ML techniques in 6G networks. Neural network design, theoretical tools of different ML methods,
“…In addition to the development of the methodologies, another trend is to explore new applications in wireless networks. Besides the optimization problems mentioned before, learning to optimize techniques are expected to solve other problems involved in wireless communication for future research directions, including multi-object optimization problems [245], bi-level optimization problems [246], conic programming [247], maximum-likelihood estimation problems [248], etc, in various emerging applications.…”
Section: ) Advanced Methodologies and Extended Applications Of Moasmentioning
The sixth generation (6G) wireless systems are envisioned to enable the paradigm shift from "connected things" to "connected intelligence", featured by ultra high density, largescale, dynamic heterogeneity, diversified functional requirements and machine learning capabilities, which leads to a growing need for highly efficient intelligent algorithms. The classic optimization-based algorithms usually require highly precise mathematical model of data links and suffer from poor performance with high computational cost in realistic 6G applications. Based on domain knowledge (e.g., optimization models and theoretical tools), machine learning (ML) stands out as a promising and viable methodology for many complex large-scale optimization problems in 6G, due to its superior performance, generalizability, computational efficiency and robustness. In this paper, we systematically review the most representative "learning to optimize" techniques in diverse domains of 6G wireless networks by identifying the inherent feature of the underlying optimization problem and investigating the specifically designed ML frameworks from the perspective of optimization. In particular, we will cover algorithm unrolling, learning to branch-andbound, graph neural network for structured optimization, deep reinforcement learning for stochastic optimization, as well as endto-end learning for semantic optimization, for solving challenging large-scale optimization problems arising from various important wireless applications. To enable ML implementation in distributed wireless networks across massive number of end devices, federated learning for distributed optimization will further be presented. Through the in-depth discussion, we shed light on the excellent performance of ML-based optimization algorithms with respect to the classical methods, and provide insightful guidance to develop advanced ML techniques in 6G networks. Neural network design, theoretical tools of different ML methods,
“…• Section 6.4.1 discusses models that integrate fixed-point computations into semiamortized models. Venkataraman and Amos (2021) amortize convex cone programs by differentiating through the splitting cone solver (O'donoghue et al, 2016) and Bai et al (2022) amortize deep equilibrium models (Bai et al, 2019(Bai et al, , 2020.…”
Section: Semi-amortized Modelsmentioning
confidence: 99%
“…Neural fixed-point acceleration (Venkataraman and Amos, 2021) proposes a semi-amortized method for computing fixed-points and use it for convex cone programming. Representing a latent state at time t with ĥt , they parameterize the initial iterate ŷ0 , ĥ0 = init θ (x) with an initialization model init θ and perform the fixed-point computations…”
Section: Neural Fixed-point Acceleration (Neuralfp) and Conic Optimiz...mentioning
confidence: 99%
“…NeuralSCS (Venkataraman and Amos, 2021) applies this neural fixed-point acceleration to solve constrained convex cone programs solved by the splitting cone solver (SCS) (O'donoghue et al, 2016) of the form…”
Section: Neural Fixed-point Acceleration (Neuralfp) and Conic Optimiz...mentioning
Optimization is a ubiquitous modeling tool and is often deployed in settings which repeatedly solve similar instances of the same problem. Amortized optimization methods use learning to predict the solutions to problems in these settings. This leverages the shared structure between similar problem instances. In this tutorial, we will discuss the key design choices behind amortized optimization, roughly categorizing 1) models into fully-amortized and semi-amortized approaches, and 2) learning methods into regression-based and objectivebased. We then view existing applications through these foundations to draw connections between them, including for manifold optimization, variational inference, sparse coding, meta-learning, control, reinforcement learning, convex optimization, and deep equilibrium networks. This framing enables us easily see, for example, that the amortized inference in variational autoencoders is conceptually identical to value gradients in control and reinforcement learning as they both use fully-amortized models with an objective-based loss.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.