I am not qualified to evaluate this work in term of its relevance within the literature. Therefore my judgment is only about the paper content itself. Also, I have only reviewed the proofs contained in the main paper the one of Lemma A.1. Theorem 3.2 guarantees a significant improvement upon the passive learner characterized by 3.1. I find the example in line2 141-143 about the 1/sqrt(m) order very helpful and I suggest the authors to include it in the introduction as well.

Empirically, Deep Learning (DL) has demonstrated unprecedented success in practical applications. However, DL remains by and large a mysterious "black-box", spurring recent theoretical research to build its mathematical foundations. In this paper, we investigate DL for data classification through the prism of metric topology. Considering that conventional Euclidean metric over the network parameter space typically fails to discriminate DL networks according to their classification outcomes, we propose from a probabilistic point of view a meaningful distance measure, whereby DL networks yielding similar classification performances are close. The proposed distance measure defines such an equivalent relation among network parameter vectors that networks performing equally well belong to the same equivalent class. Interestingly, our proposed distance measure can provably serve as a metric on the quotient set modulo the equivalent relation. Then, under quite mild conditions it is shown that, apart from a vanishingly small subset of networks likely to predict non-unique labels, our proposed metric space is compact, and coincides with the well-known quotient topological space. Our study contributes to fundamental understanding of DL, and opens up new ways of studying DL using fruitful metric space theory.

Magnitude is a real-valued invariant of metric spaces which, in the finite setting, can be understood as recording the 'effective number of points' in a space as the scale of the metric varies. Motivated by applications in topological data analysis, this paper investigates the stability of magnitude: its continuity properties with respect to the Gromov-Hausdorff topology. We show that magnitude is nowhere continuous on the Gromov-Hausdorff space of finite metric spaces. Yet, we find evidence to suggest that it may be 'generically continuous', in the sense that generic Gromov-Hausdorff limits are preserved by magnitude. We make the case that, in fact, 'generic stability' is what matters for applicability.

We introduce, for the first time, a cohomology-based Gromov-Hausdorff ultrametric method to analyze 1-dimensional and higher-dimensional (co)homology groups, focusing on loops, voids, and higher-dimensional cavity structures in simplicial complexes, to address typical clustering questions arising in molecular data analysis. The Gromov-Hausdorff distance quantifies the dissimilarity between two metric spaces. In this framework, molecules are represented as simplicial complexes, and their cohomology vector spaces are computed to capture intrinsic topological invariants encoding loop and cavity structures. These vector spaces are equipped with a suitable distance measure, enabling the computation of the Gromov-Hausdorff ultrametric to evaluate structural dissimilarities. We demonstrate the methodology using organic-inorganic halide perovskite (OIHP) structures. The results highlight the effectiveness of this approach in clustering various molecular structures. By incorporating geometric information, our method provides deeper insights compared to traditional persistent homology techniques.

The purpose of this article is twofold. Firstly, we use the next-token probabilities given by a language model to explicitly define a $[0,1]$-enrichment of a category of texts in natural language, in the sense of Bradley, Terilla, and Vlassopoulos. We consider explicitly the terminating conditions for text generation and determine when the enrichment itself can be interpreted as a probability over texts. Secondly, we compute the M\"obius function and the magnitude of an associated generalized metric space $\mathcal{M}$ of texts using a combinatorial version of these quantities recently introduced by Vigneaux. The magnitude function $f(t)$ of $\mathcal{M}$ is a sum over texts $x$ (prompts) of the Tsallis $t$-entropies of the next-token probability distributions $p(-|x)$ plus the cardinality of the model's possible outputs. The derivative of $f$ at $t=1$ recovers a sum of Shannon entropies, which justifies seeing magnitude as a partition function. Following Leinster and Schulman, we also express the magnitude function of $\mathcal M$ as an Euler characteristic of magnitude homology and provide an explicit description of the zeroeth and first magnitude homology groups.

At the risk of overstating the case, connectionist approaches to machine learning, i.e. neural networks, are enjoying a small vogue right now. However, these methods require large volumes of data and produce models that are uninterpretable to humans. An alternative framework that is compatible with neural networks and gradient-based learning, but explicitly models compositionality, is Vector Symbolic Architectures (VSAs). VSAs are a family of algebras on high-dimensional vector representations. They arose in cognitive science from the need to unify neural processing and the kind of symbolic reasoning that humans perform. While machine learning methods have benefited from category theoretical analyses, VSAs have not yet received similar treatment. In this paper, we present a first attempt at applying category theory to VSAs. Specifically, we conduct a brief literature survey demonstrating the lacking intersection of these two topics, provide a list of desiderata for VSAs, and propose that VSAs may be understood as a (division) rig in a category enriched over a monoid in Met (the category of Lawvere metric spaces). This final contribution suggests that VSAs may be generalised beyond current implementations. It is our hope that grounding VSAs in category theory will lead to more rigorous connections with other research, both within and beyond, learning and cognition.

We consider a minimax problem motivated by distributionally robust optimization (DRO) when the worst-case distribution is continuous, leading to significant computational challenges due to the infinite-dimensional nature of the optimization problem. Recent research has explored learning the worst-case distribution using neural network-based generative models to address these computational challenges but lacks algorithmic convergence guarantees. This paper bridges this theoretical gap by presenting an iterative algorithm to solve such a minimax problem, achieving global convergence under mild assumptions and leveraging technical tools from vector space minimax optimization and convex analysis in the space of continuous probability densities. In particular, leveraging Brenier's theorem, we represent the worst-case distribution as a transport map applied to a continuous reference measure and reformulate the regularized discrepancy-based DRO as a minimax problem in the Wasserstein space. Furthermore, we demonstrate that the worst-case distribution can be efficiently computed using a modified Jordan-Kinderlehrer-Otto (JKO) scheme with sufficiently large regularization parameters for commonly used discrepancy functions, linked to the radius of the ambiguity set. Additionally, we derive the global convergence rate and quantify the total number of subgradient and inexact modified JKO iterations required to obtain approximate stationary points. These results are potentially applicable to nonconvex and nonsmooth scenarios, with broad relevance to modern machine learning applications.

Kernel methods map data into high-dimensional spaces, enabling linear algorithms to learn nonlinear functions without explicitly storing the feature vectors. Quantum kernel methods promise efficient learning by encoding feature maps into exponentially large Hilbert spaces inherent in quantum systems. In this work we implement quantum kernels on a 10-qubit star-topology register in a nuclear magnetic resonance (NMR) platform. We experimentally encode classical data in the evolution of multiple quantum coherence orders using data-dependent unitary transformations and then demonstrate one-dimensional regression and two-dimensional classification tasks. By extending the register to a double-layered star configuration, we propose an extended quantum kernel to handle non-parametrized operator inputs. By numerically simulating the extended quantum kernel, we show classification of entangling and nonentangling unitaries. These results confirm that quantum kernels exhibit strong capabilities in classical as well as quantum machine learning tasks.

The generation of Scalable Vector Graphics (SVG) assets from textual data remains a significant challenge, largely due to the scarcity of high-quality vector datasets and the limitations in scalable vector representations required for modeling intricate graphic distributions. This work introduces SVGFusion, a Text-to-SVG model capable of scaling to real-world SVG data without reliance on a text-based discrete language model or prolonged SDS optimization. The essence of SVGFusion is to learn a continuous latent space for vector graphics with a popular Text-to-Image framework. Specifically, SVGFusion consists of two modules: a Vector-Pixel Fusion Variational Autoencoder (VP-VAE) and a Vector Space Diffusion Transformer (VS-DiT). VP-VAE takes both the SVGs and corresponding rasterizations as inputs and learns a continuous latent space, whereas VS-DiT learns to generate a latent code within this space based on the text prompt. Based on VP-VAE, a novel rendering sequence modeling strategy is proposed to enable the latent space to embed the knowledge of construction logics in SVGs. This empowers the model to achieve human-like design capabilities in vector graphics, while systematically preventing occlusion in complex graphic compositions. Moreover, our SVGFusion's ability can be continuously improved by leveraging the scalability of the VS-DiT by adding more VS-DiT blocks. A large-scale SVG dataset is collected to evaluate the effectiveness of our proposed method. Extensive experimentation has confirmed the superiority of our SVGFusion over existing SVG generation methods, achieving enhanced quality and generalizability, thereby establishing a novel framework for SVG content creation. Code, model, and data will be released at: \href{https://ximinng.github.io/SVGFusionProject/}{https://ximinng.github.io/SVGFusionProject/}

Many methods have been proposed to find vector representation for words, but most rely on capturing context from the text to find semantic relationships between these vectors. We propose a novel method of using dictionary meanings and image depictions to find word vectors independent of any context. We use auto-encoder on the word images to find meaningful representations and use them to calculate the word vectors. We finally evaluate our method on word similarity, concept categorization and outlier detection tasks. Our method performs comparably to context-based methods while taking much less training time.