Physarum Powered Differentiable Linear Programming Layers and Applications

Abstract

Consider a learning algorithm, which involves an internal call to an optimization routine such as a generalized eigenvalue problem, a cone programming problem or even sorting. Integrating such a method as layers within a trainable deep network in a numerically stable way is not simple – for instance, only recently, strategies have emerged for eigendecomposition and differentiable sorting. We propose an efficient and differentiable solver for general linear programming problems which can be used in a plug and play manner within deep neural networks as a layer. Our development is inspired by a fascinating but not widely used link between dynamics of slime mold (physarum) and mathematical optimization schemes such as steepest descent. We describe our development and demonstrate the use of our solver in a video object segmentation task and meta-learning for few-shot learning. We review the relevant known results and provide a technical analysis describing its applicability for our use cases. Our solver performs comparably with a customized projected gradient descent method on the first task and outperforms the very recently proposed differentiable CVXPY solver on the second task. Experiments show that our solver converges quickly without the need for a feasible initial point. Interestingly, our scheme is easy to implement and can easily serve as layers whenever a learning procedure needs a fast approximate solution to a LP, within a larger network.

An Improved Visual SLAM Algorithm Based on Graph Neural Network

“…where S is the goodness-of-fit of the match pair in the lowquality set, and M and N are the rows and columns of the low goodness-of-fit set. Since the solution of the above large-scale matching pair optimization problem presents a discrete distribution, we use the LP Solver (Linear Program Solver) algorithm [29] to solve the Fit matrix…”

Applications of Deep Learning for Drug Discovery Systems with BigData

“…The amounts of data and computational power required for learning have increased. Deep learning uses DNNs with hundreds of layers and a large number of parameters related to structure [145][146][147][148][149][150][151][152][153][154][155][156][157][158][159][160][161]. Therefore, it is prone to overfitting, which is a condition where the learning data are overfitted, generalization is not possible, and high accuracy cannot be achieved with unknown data.…”