Antonio León Villares

Torkel E. Loman, Yurij Salmaniw, Antonio Leon Villares et al.

Partial differential equations often contain unknown functions that are difficult or impossible to measure directly, hampering our ability to derive predictions from the model. Workflows for recovering scalar PDE parameters from data are well studied: here we show how similar workflows can be used to recover functions from data. Specifically, we embed neural networks into the PDE and show how, as they are trained on data, they can approximate unknown functions with arbitrary accuracy. Using nonlocal aggregation-diffusion equations as a case study, we recover interaction kernels and external potentials from steady state data. Specifically, we investigate how a wide range of factors, such as the number of available solutions, their properties, sampling density, and measurement noise, affect our ability to successfully recover functions. Our approach is advantageous because it can utilise standard parameter-fitting workflows, and in that the trained PDE can be treated as a normal PDE for purposes such as generating system predictions.

Bidipta Sarkar, Mattie Fellows, Juan Agustin Duque et al.

We introduce Evolution Guided General Optimization via Low-rank Learning (EGGROLL), an evolution strategies (ES) algorithm designed to scale backprop-free optimization to large population sizes for modern large neural network architectures with billions of parameters. ES is a set of powerful blackbox optimisation methods that can handle non-differentiable or noisy objectives with excellent scaling potential through parallelisation. Na{ï}ve ES becomes prohibitively expensive at scale due to the computational and memory costs associated with generating matrix perturbations $E\in\mathbb{R}^{m\times n}$ and the batched matrix multiplications needed to compute per-member forward passes. EGGROLL overcomes these bottlenecks by generating random matrices $A\in \mathbb{R}^{m\times r},\ B\in \mathbb{R}^{n\times r}$ with $r\ll \min(m,n)$ to form a low-rank matrix perturbation $A B^\top$ that are used in place of the full-rank perturbation $E$. As the overall update is an average across a population of $N$ workers, this still results in a high-rank update but with significant memory and computation savings, reducing the auxiliary storage from $mn$ to $r(m+n)$ per layer and the cost of a forward pass from $\mathcal{O}(mn)$ to $\mathcal{O}(r(m+n))$ when compared to full-rank ES. A theoretical analysis reveals our low-rank update converges to the full-rank update at a fast $\mathcal{O}\left(\frac{1}{r}\right)$ rate. Our experiments show that (1) EGGROLL does not compromise the performance of ES in tabula-rasa RL settings, despite being faster, (2) it is competitive with GRPO as a technique for improving LLM reasoning, and (3) EGGROLL enables stable pre-training of nonlinear recurrent language models that operate purely in integer datatypes.