Shallower ReLU Network Representations via Exact Linear Algebra

We prove that the maximum of $n$ real numbers is exactly representable by a ReLU network with two hidden layers for every $n\le 10$. The constructions are obtained by reducing the problem to exact rational linear algebra: after a symmetry reduction, the necessary cancellations are encoded in finite linear systems over $\mathbb{Q}$, which we solve and verify computationally. The representation of $\max_{10}$ has a structured first hidden layer consisting only of pairwise maxima, a feature that allows it to be recursively substituted into larger networks. We use this to show that for every $n>10$, the maximum $\max_{n}$ can be exactly represented with $\lceil{\log_5 (n / 2)\rceil}+1 < \log_5(n) +1.5694$ hidden layers. Via the generalized hinging-hyperplane representation [Wang, Sun, IEEE Trans. Inf. Theory 2005], the same depth bound holds for all continuous piecewise-linear functions on $\mathbb{R}^d$, with $d+1$ in place of $n$. In particular, every continuous piecewise-linear function on $\mathbb{R}^d$ for $d\le 9$ admits a two-hidden-layer ReLU representation. Our results improve on [Bakaev, Brunck, Hertrich, Stade, Yehudayoff, STOC'26]. In that work, the authors established a two-hidden-layer representation for $\max_{5}$ and an upper bound of $\lceil{\log_3 (n-2)\rceil}+1$ hidden layers for $\max_{n}$.

From ex(p) to poly: Gaussian Splatting with Polynomial Kernels

Recent advancements in Gaussian Splatting (3DGS) have introduced various modifications to the original kernel, resulting in significant performance improvements. However, many of these kernel changes are incompatible with existing datasets optimized for the original Gaussian kernel, presenting a challenge for widespread adoption. In this work, we address this challenge by proposing an alternative kernel that maintains compatibility with existing datasets while improving computational efficiency. Specifically, we replace the original exponential kernel with a polynomial approximation combined with a ReLU function. This modification allows for more aggressive culling of Gaussians, leading to enhanced performance across different 3DGS implementations. Our results show a notable performance improvement of 4 to 15% with negligible impact on image quality. We also provide a detailed mathematical analysis of the new kernel and discuss its potential benefits for 3DGS implementations on NPU hardware.

Gradient-based Weight Density Balancing for Robust Dynamic Sparse Training

Training a sparse neural network from scratch requires optimizing connections at the same time as the weights themselves. Typically, the weights are redistributed after a predefined number of weight updates, removing a fraction of the parameters of each layer and inserting them at different locations in the same layers. The density of each layer is determined using heuristics, often purely based on the size of the parameter tensor. While the connections per layer are optimized multiple times during training, the density of each layer remains constant. This leaves great unrealized potential, especially in scenarios with a high sparsity of 90% and more. We propose Global Gradient-based Redistribution, a technique which distributes weights across all layers - adding more weights to the layers that need them most. Our evaluation shows that our approach is less prone to unbalanced weight distribution at initialization than previous work and that it is able to find better performing sparse subnetworks at very high sparsity levels.