An official website of the United States government
Combinatorial optimization problems prevail in engineering and industry. Some are NP-hard and thus become difficult to solve on edge devices due to limited power and computing resources. Quadratic Unconstrained Binary Optimization (QUBO) problem is a valuable emerging model that can formulate numerous combinatorial problems, such as Max-Cut, traveling salesman problems, and graphic coloring. QUBO model also reconciles with two emerging computation models, quantum computing and neuromorphic computing, which can potentially boost the speed and energy efficiency in solving combinatorial problems. In this work, we design a neuromorphic QUBO solver composed of a swarm of spiking neural networks (SNN) that conduct a population-based meta-heuristic search for solutions. The proposed model can achieve about x20 40 speedup on large QUBO problems in terms of time steps compared to a traditional neural network solver. As a codesign, we evaluate the neuromorphic swarm solver on a 40nm 25mW Resistive RAM (RRAM) Compute-in-Memory (CIM) SoC with a 2.25MB RRAM-based accelerator and an embedded Cortex M3 core. The collaborative SNN swarm can fully exploit the specialty of CIM accelerator in matrix and vector multiplications. Compared to previous works, such an algorithm-hardware synergized solver exhibits advantageous speed and energy efficiency for edge devices.
more »
« less
The (Un)Scalability of Informed Heuristic Function Estimation in NP-Hard Search Problems
The A* algorithm is commonly used to solve NP-hard combinatorial optimization problems. When provided with a completely informed heuristic function, A* can solve such problems in time complexity that is polynomial in the solution cost and branching factor. In light of this fact, we examine a line of recent publications that propose fitting deep neural networks to the completely informed heuristic function. We assert that these works suffer from inherent scalability limitations since --- under the assumption of NP P/poly --- such approaches result in either (a) network sizes that scale super-polynomially in the instance sizes or (b) the accuracy of the fitted deep neural networks scales inversely with the instance sizes. Complementing our theoretical claims, we provide experimental results for three representative NP-hard search problems. The results suggest that fitting deep neural networks to informed heuristic functions requires network sizes that grow quickly with the problem instance size. We conclude by suggesting that the research community should focus on scalable methods for integrating heuristic search with machine learning, as opposed to methods relying on informed heuristic estimation.
more »
« less
- Award ID(s):
- 2238979
- PAR ID:
- 10498043
- Publisher / Repository:
- https://openreview.net/forum?id=JllRdycmLk
- Date Published:
- Journal Name:
- Transactions on Machine Learning Research
- ISSN:
- 2835-8856
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Quadratic Unconstrained Binary Optimization (QUBO) problem becomes an attractive and valuable optimization problem formulation in that it can easily transform into a variety of other combinatorial optimization problems such as Graph/number Partition, Max-Cut, SAT, Vertex Coloring, TSP, etc. Some of these problems are NP-hard and widely applied in industry and scientific research. Meanwhile, QUBO has been discovered to be compatible with two emerging computing paradigms, neuromorphic computing, and quantum computing, with tremendous potential to speed up future optimization solvers. In this paper, we propose a novel neuromorphic computing paradigm that employs multiple collaborative spiking neural networks to solve QUBO problems. Each SNN conducts a local stochastic gradient descent search and shares the global best solutions periodically to perform a meta-heuristic search for optima. We simulate our model and compare it to a single SNN solver and a mult-SNN solver without collaboration. Through tests on benchmark problems, the proposed method is demonstrated to be more efficient and effective in searching for QUBO optima. Specifically, it exhibits x10 and x15-20 speedup respectively on the multi-SNN solver without collaboration and the single-SNN solver.more » « less
-
Probabilistic circuits (PCs) such as sum-product networks efficiently represent large multi-variate probability distributions. They are preferred in practice over other probabilistic representations, such as Bayesian and Markov networks, because PCs can solve marginal inference (MAR) tasks in time that scales linearly in the size of the network. Unfortunately, the most probable explanation (MPE) task and its generalization, the marginal maximum-a-posteriori (MMAP) inference task remain NP-hard in these models. Inspired by the recent work on using neural networks for generating near-optimal solutions to optimization problems such as integer linear programming, we propose an approach that uses neural networks to approximate MMAP inference in PCs. The key idea in our approach is to approximate the cost of an assignment to the query variables using a continuous multilinear function and then use the latter as a loss function. The two main benefits of our new method are that it is self-supervised, and after the neural network is learned, it requires only linear time to output a solution. We evaluate our new approach on several benchmark datasets and show that it outperforms three competing linear time approximations: max-product inference, max-marginal inference, and sequential estimation, which are used in practice to solve MMAP tasks in PCs.more » « less
-
To verify safety and robustness of neural networks, researchers have successfully appliedabstract interpretation, primarily using the interval abstract domain. In this paper, we study the theoretical power and limits of the interval domain for neural-network verification. First, we introduce theinterval universal approximation(IUA) theorem. IUA shows that neural networks not only can approximate any continuous functionf(universal approximation) as we have known for decades, but we can find a neural network, using any well-behaved activation function, whose interval bounds are an arbitrarily close approximation of the set semantics off(the result of applyingfto a set of inputs). We call this notion of approximationinterval approximation. Our theorem generalizes the recent result of Baader et al. from ReLUs to a rich class of activation functions that we callsquashable functions. Additionally, the IUA theorem implies that we can always construct provably robust neural networks under ℓ∞-norm using almost any practical activation function. Second, we study the computational complexity of constructing neural networks that are amenable to precise interval analysis. This is a crucial question, as our constructive proof of IUA is exponential in the size of the approximation domain. We boil this question down to the problem of approximating the range of a neural network with squashable activation functions. We show that the range approximation problem (RA) is a Δ2-intermediate problem, which is strictly harder thanNP-complete problems, assumingcoNP⊄NP. As a result,IUA is an inherently hard problem: No matter what abstract domain or computational tools we consider to achieve interval approximation, there is no efficient construction of such a universal approximator. This implies that it is hard to construct a provably robust network, even if we have a robust network to start with.more » « less
-
Pappas, George; Ravikumar, Pradeep; Seshia, Sanjit A (Ed.)We study the problem of learning neural network models for Ordinary Differential Equations (ODEs) with parametric uncertainties. Such neural network models capture the solution to the ODE over a given set of parameters, initial conditions, and range of times. Physics-Informed Neural Networks (PINNs) have emerged as a promising approach for learning such models that combine data-driven deep learning with symbolic physics models in a principled manner. However, the accuracy of PINNs degrade when they are used to solve an entire family of initial value problems characterized by varying parameters and initial conditions. In this paper, we combine symbolic differentiation and Taylor series methods to propose a class of higher-order models for capturing the solutions to ODEs. These models combine neural networks and symbolic terms: they use higher order Lie derivatives and a Taylor series expansion obtained symbolically, with the remainder term modeled as a neural network. The key insight is that the remainder term can itself be modeled as a solution to a first-order ODE. We show how the use of these higher order PINNs can improve accuracy using interesting, but challenging ODE benchmarks. We also show that the resulting model can be quite useful for situations such as controlling uncertain physical systems modeled as ODEs.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- The DOI is not currently available.
