Towards Optimally Efficient Tree Search with Deep Temporal Difference Learning

01/07/2021
by   Ke He, et al.
13

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.

READ FULL TEXT

page 3

page 4

page 6

page 8

page 9

page 10

page 12

page 13

research
05/19/2020

Dynamic Partial Removal: A Neural Network Heuristic for Large Neighborhood Search

This paper presents a novel neural network design that learns the heuris...
research
09/07/2022

The (Un)Scalability of Heuristic Approximators for NP-Hard Search Problems

The A* algorithm is commonly used to solve NP-hard combinatorial optimiz...
research
12/27/2022

A Kernel Search Algorithm for Virtual Machine Consolidation Problem

Virtual machine consolidation describes the process of reallocation of v...
research
01/10/2013

Maximum Likelihood Bounded Tree-Width Markov Networks

Chow and Liu (1968) studied the problem of learning a maximumlikelihood ...
research
11/06/2020

A dynamic programming approach for generalized nearly isotonic optimization

Shape restricted statistical estimation problems have been extensively s...
research
11/29/2018

Solving group Steiner problems as Steiner problems: the rigorous proof

The Steiner tree problems are well-known NP-hard problems that have dive...
research
05/04/2023

Emulation Learning for Neuromimetic Systems

Building on our recent research on neural heuristic quantization systems...

Please sign up or login with your details

Forgot password? Click here to reset