Towards Optimally Efficient Tree Search with Deep Learning

• URL: http://arxiv.org/abs/2101.02420v4
• Date: Mon, 15 Mar 2021 08:26:14 GMT
• Title: Towards Optimally Efficient Tree Search with Deep Learning
• Authors: Le He, Ke He, Lisheng Fan, Xianfu Lei, Arumugam Nallanathan and George K. Karagiannidis
• Abstract summary: This paper investigates the classical integer least-squares problem which estimates signals integer from linear models. The problem is NP-hard and often arises in diverse applications such as signal processing, bioinformatics, communications and machine learning. We propose a general hyper-accelerated tree search (HATS) algorithm by employing a deep neural network to estimate the optimal estimation for the underlying simplified memory-bounded A* algorithm.
• Score: 76.64632985696237
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper investigates the classical integer least-squares problem which estimates integer signals from linear models. The problem is NP-hard and often arises in diverse applications such as signal processing, bioinformatics, communications and machine learning, to name a few. Since the existing optimal search strategies involve prohibitive complexities, they are hard to be adopted in large-scale problems. To address this issue, we propose a general hyper-accelerated tree search (HATS) algorithm by employing a deep neural network to estimate the optimal heuristic for the underlying simplified memory-bounded A* algorithm, and the proposed algorithm can be easily generalized with other heuristic search algorithms. Inspired by the temporal difference learning, we further propose a training strategy which enables the network to approach the optimal heuristic precisely and consistently, thus the proposed algorithm can reach nearly the optimal efficiency when the estimation error is small enough. Experiments show that the proposed algorithm can reach almost the optimal maximum likelihood estimate performance in large-scale problems, with a very low complexity in both time and space. The code of this paper is avaliable at https://github.com/skypitcher/hats.

Related papers

• Quality-Diversity Algorithms Can Provably Be Helpful for Optimization [24.694984679399315]
  Quality-Diversity (QD) algorithms aim to find a set of high-performing, yet diverse solutions. This paper tries to shed some light on the optimization ability of QD algorithms via rigorous running time analysis.
  arXiv  Detail & Related papers  (2024-01-19T07:40:24Z)
• Neural Algorithmic Reasoning for Combinatorial Optimisation [20.36694807847833]
  We propose leveraging recent advancements in neural reasoning to improve the learning of CO problems. We suggest pre-training our neural model on relevant algorithms before training it on CO instances. Our results demonstrate that by using this learning setup, we achieve superior performance compared to non-algorithmically informed deep learning models.
  arXiv  Detail & Related papers  (2023-05-18T13:59:02Z)
• Dual Algorithmic Reasoning [9.701208207491879]
  We propose to learn algorithms by exploiting duality of the underlying algorithmic problem. We demonstrate that simultaneously learning the dual definition of these optimisation problems in algorithmic learning allows for better learning. We then validate the real-world utility of our dual algorithmic reasoner by deploying it on a challenging brain vessel classification task.
  arXiv  Detail & Related papers  (2023-02-09T08:46:23Z)
• Provably Faster Algorithms for Bilevel Optimization [54.83583213812667]
  Bilevel optimization has been widely applied in many important machine learning applications. We propose two new algorithms for bilevel optimization. We show that both algorithms achieve the complexity of $mathcalO(epsilon-1.5)$, which outperforms all existing algorithms by the order of magnitude.
  arXiv  Detail & Related papers  (2021-06-08T21:05:30Z)
• A bi-level encoding scheme for the clustered shortest-path tree problem in multifactorial optimization [1.471992435706872]
  The Clustered Shortest-Path Tree Problem (CluSPT) plays an important role in various types of optimization problems in real-life. Recently, some Multifactorial Evolutionary Algorithm (MFEA) have been introduced to deal with the CluSPT. This paper describes a MFEA-based approach to solve the CluSPT.
  arXiv  Detail & Related papers  (2021-02-12T13:36:07Z)
• Community detection using fast low-cardinality semidefinite programming [94.4878715085334]
  We propose a new low-cardinality algorithm that generalizes the local update to maximize a semidefinite relaxation derived from Leiden-k-cut. This proposed algorithm is scalable, outperforms state-of-the-art algorithms, and outperforms in real-world time with little additional cost.
  arXiv  Detail & Related papers  (2020-12-04T15:46:30Z)
• Online Model Selection for Reinforcement Learning with Function Approximation [50.008542459050155]
  We present a meta-algorithm that adapts to the optimal complexity with $tildeO(L5/6 T2/3)$ regret. We also show that the meta-algorithm automatically admits significantly improved instance-dependent regret bounds.
  arXiv  Detail & Related papers  (2020-11-19T10:00:54Z)
• Efficient Computation of Expectations under Spanning Tree Distributions [67.71280539312536]
  We propose unified algorithms for the important cases of first-order expectations and second-order expectations in edge-factored, non-projective spanning-tree models. Our algorithms exploit a fundamental connection between gradients and expectations, which allows us to derive efficient algorithms.
  arXiv  Detail & Related papers  (2020-08-29T14:58:26Z)
• Learning to Accelerate Heuristic Searching for Large-Scale Maximum Weighted b-Matching Problems in Online Advertising [51.97494906131859]
  Bipartite b-matching is fundamental in algorithm design, and has been widely applied into economic markets, labor markets, etc. Existing exact and approximate algorithms usually fail in such settings due to either requiring intolerable running time or too much computation resource. We propose textttNeuSearcher which leverages the knowledge learned from previously instances to solve new problem instances.
  arXiv  Detail & Related papers  (2020-05-09T02:48:23Z)

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.