Neural Networks and (Virtual) Extended Formulations

Neural networks with piecewise linear activation functions, such as rectified linear units (ReLU) or maxout, are among the most fundamental models in modern machine learning. We make a step towards proving lower bounds on the size of such neural networks by linking their representative capabilities to the notion of the extension complexity $\mathrm{xc}(P)$ of a polytope $P$, a well-studied quantity in combinatorial optimization and polyhedral geometry. To this end, we propose the notion of virtual extension complexity $\mathrm{vxc}(P)=\min\{\mathrm{xc}(Q)+\mathrm{xc}(R)\mid P+Q=R\}$. This generalizes $\mathrm{xc}(P)$ and describes the number of inequalities needed to represent the linear optimization problem over $P$ as a difference of two linear programs. We prove that $\mathrm{vxc}(P)$ is a lower bound on the size of a neural network that optimizes over $P$. While it remains open to derive strong lower bounds on virtual extension complexity, we show that powerful results on the ordinary extension complexity can be converted into lower bounds for monotone neural networks, that is, neural networks with only nonnegative weights. Furthermore, we show that one can efficiently optimize over a polytope $P$ using a small virtual extended formulation. We therefore believe that virtual extension complexity deserves to be studied independently from neural networks, just like the ordinary extension complexity. As a first step in this direction, we derive an example showing that extension complexity can go down under Minkowski sum.

Decomposition Polyhedra of Piecewise Linear Functions

In this paper we contribute to the frequently studied question of how to decompose a continuous piecewise linear (CPWL) function into a difference of two convex CPWL functions. Every CPWL function has infinitely many such decompositions, but for applications in optimization and neural network theory, it is crucial to find decompositions with as few linear pieces as possible. This is a highly challenging problem, as we further demonstrate by disproving a recently proposed approach by Tran and Wang [Minimal representations of tropical rational functions. Algebraic Statistics, 15(1):27-59, 2024]. To make the problem more tractable, we propose to fix an underlying polyhedral complex determining the possible locus of nonlinearity. Under this assumption, we prove that the set of decompositions forms a polyhedron that arises as intersection of two translated cones. We prove that irreducible decompositions correspond to the bounded faces of this polyhedron and minimal solutions must be vertices. We then identify cases with a unique minimal decomposition, and illustrate how our insights have consequences in the theory of submodular functions. Finally, we improve upon previous constructions of neural networks for a given convex CPWL function and apply our framework to obtain results in the nonconvex case.

Mode Connectivity in Auction Design

Optimal auction design is a fundamental problem in algorithmic game theory. This problem is notoriously difficult already in very simple settings. Recent work in differentiable economics showed that neural networks can efficiently learn known optimal auction mechanisms and discover interesting new ones. In an attempt to theoretically justify their empirical success, we focus on one of the first such networks, RochetNet, and a generalized version for affine maximizer auctions. We prove that they satisfy mode connectivity, i.e., locally optimal solutions are connected by a simple, piecewise linear path such that every solution on the path is almost as good as one of the two local optima. Mode connectivity has been recently investigated as an intriguing empirical and theoretically justifiable property of neural networks used for prediction problems. Our results give the first such analysis in the context of differentiable economics, where neural networks are used directly for solving non-convex optimization problems.

Training Neural Networks is NP-Hard in Fixed Dimension

We study the parameterized complexity of training two-layer neural networks with respect to the dimension of the input data and the number of hidden neurons, considering ReLU and linear threshold activation functions. Albeit the computational complexity of these problems has been studied numerous times in recent years, several questions are still open. We answer questions by Arora et al. [ICLR '18] and Khalife and Basu [IPCO '22] showing that both problems are NP-hard for two dimensions, which excludes any polynomial-time algorithm for constant dimension. We also answer a question by Froese et al. [JAIR '22] proving W[1]-hardness for four ReLUs (or two linear threshold neurons) with zero training error. Finally, in the ReLU case, we show fixed-parameter tractability for the combined parameter number of dimensions and number of ReLUs if the network is assumed to compute a convex map. Our results settle the complexity status regarding these parameters almost completely.

Lower Bounds on the Depth of Integral ReLU Neural Networks via Lattice Polytopes

We prove that the set of functions representable by ReLU neural networks with integer weights strictly increases with the network depth while allowing arbitrary width. More precisely, we show that $\lceil\log_2(n)\rceil$ hidden layers are indeed necessary to compute the maximum of $n$ numbers, matching known upper bounds. Our results are based on the known duality between neural networks and Newton polytopes via tropical geometry. The integrality assumption implies that these Newton polytopes are lattice polytopes. Then, our depth lower bounds follow from a parity argument on the normalized volume of faces of such polytopes.

Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete

We consider the algorithmic problem of finding the optimal weights and biases for a two-layer fully connected neural network to fit a given set of data points. This problem is known as empirical risk minimization in the machine learning community. We show that the problem is $\exists\mathbb{R}$-complete. This complexity class can be defined as the set of algorithmic problems that are polynomial-time equivalent to finding real roots of a polynomial with integer coefficients. Our results hold even if the following restrictions are all added simultaneously. $\bullet$ There are exactly two output neurons. $\bullet$ There are exactly two input neurons. $\bullet$ The data has only 13 different labels. $\bullet$ The number of hidden neurons is a constant fraction of the number of data points. $\bullet$ The target training error is zero. $\bullet$ The ReLU activation function is used. This shows that even very simple networks are difficult to train. The result offers an explanation (though far from a complete understanding) on why only gradient descent is widely successful in training neural networks in practice. We generalize a recent result by Abrahamsen, Kleist and Miltzow [NeurIPS 2021]. This result falls into a recent line of research that tries to unveil that a series of central algorithmic problems from widely different areas of computer science and mathematics are $\exists\mathbb{R}$-complete: This includes the art gallery problem [JACM/STOC 2018], geometric packing [FOCS 2020], covering polygons with convex polygons [FOCS 2021], and continuous constraint satisfaction problems [FOCS 2021].

Towards Lower Bounds on the Depth of ReLU Neural Networks

We contribute to a better understanding of the class of functions that is represented by a neural network with ReLU activations and a given architecture. Using techniques from mixed-integer optimization, polyhedral theory, and tropical geometry, we provide a mathematical counterbalance to the universal approximation theorems which suggest that a single hidden layer is sufficient for learning tasks. In particular, we investigate whether the class of exactly representable functions strictly increases by adding more layers (with no restrictions on size). This problem has potential impact on algorithmic and statistical aspects because of the insight it provides into the class of functions represented by neural hypothesis classes. However, to the best of our knowledge, this question has not been investigated in the neural network literature. We also present upper bounds on the sizes of neural networks required to represent functions in these neural hypothesis classes.

The Computational Complexity of ReLU Network Training Parameterized by Data Dimensionality

Understanding the computational complexity of training simple neural networks with rectified linear units (ReLUs) has recently been a subject of intensive research. Closing gaps and complementing results from the literature, we present several results on the parameterized complexity of training two-layer ReLU networks with respect to various loss functions. After a brief discussion of other parameters, we focus on analyzing the influence of the dimension $d$ of the training data on the computational complexity. We provide running time lower bounds in terms of W[1]-hardness for parameter $d$ and prove that known brute-force strategies are essentially optimal (assuming the Exponential Time Hypothesis). In comparison with previous work, our results hold for a broad(er) range of loss functions, including $\ell^p$-loss for all $p\in[0,\infty]$. In particular, we extend a known polynomial-time algorithm for constant $d$ and convex loss functions to a more general class of loss functions, matching our running time lower bounds also in these cases.

ReLU Neural Networks for Exact Maximum Flow Computation

Understanding the great empirical success of artificial neural networks (NNs) from a theoretical point of view is currently one of the hottest research topics in computer science. In this paper we study the expressive power of NNs with rectified linear units from a combinatorial optimization perspective. In particular, we show that, given a directed graph with $n$ nodes and $m$ arcs, there exists an NN of polynomial size that computes a maximum flow from any possible real-valued arc capacities as input. To prove this, we develop the pseudo-code language Max-Affine Arithmetic Programs (MAAPs) and show equivalence between MAAPs and NNs concerning natural complexity measures. We then design a MAAP to exactly solve the Maximum Flow Problem, which translates to an NN of size $\mathcal{O}(m^2 n^2)$.

Provably Good Solutions to the Knapsack Problem via Neural Networks of Bounded Size

In view of the undisputed success of neural networks and due to the remarkable recent improvements in their ability to solve a huge variety of practical problems, the development of a satisfying and rigorous mathematical understanding of their performance is one of the main challenges in the field of learning theory. Against this background, we study the expressive power of neural networks through the example of the classical NP-hard Knapsack Problem. Our main contribution is a class of recurrent neural networks (RNNs) with rectified linear units that are iteratively applied to each item of a Knapsack instance and thereby compute optimal or provably good solution values. In order to find optimum Knapsack solutions, an RNN of depth four and width depending quadratically on the profit of an optimum Knapsack solution is sufficient. We also prove the following tradeoff between the size of an RNN and the quality of the computed Knapsack solution: For Knapsack instances consisting of $n$ items, an RNN of depth five and width $w$ computes a solution of value at least $1-\mathcal{O}(n^2/\sqrt{w})$ times the optimum solution value. Our results build upon a dynamic programming formulation of the Knapsack Problem as well as a careful rounding of profit values that is also at the core of the well-known fully polynomial-time approximation scheme for the Knapsack Problem. Finally, we point out that similar results can be achieved for other optimization problems that can be solved by dynamic programming, such as, e.g., various Shortest Path Problems and the Longest Common Subsequence Problem.