SearcharxivSearch

arXiv subjects

Martin Lotz

Publications and source records attributed to Martin Lotz.

At least 19 recordsLinked to original sources

Monotone invariant valuations on convex cones

We classify the monotone $\SOn d$-invariant valuations, $d\ge2$, on the space of all closed convex cones. They are precisely the linear combinations of the conic intrinsic volumes with nondecreasing coefficients, or equivalently, the nonnegative linear combinations of intrinsic volume tails, up to an additive constant. On nonzero pointed cones we obtain the corresponding characterisation by Grassmann angles, settling a conjecture of McMullen. Every such valuation is automatically continuous in the spherical Hausdorff topology and is $\On d$-invariant. Our proof builds on the signed simplex and averaging arguments of Wang and Wu, but does not rely on the continuous classification theorem.

math.MG

Khovanskii's Bezout-type Theorem for Pfaffian Functions: A Self-Contained Proof, and Applications

We present a direct and self-contained proof of Khovanskii's Bezout-type bound for the number of nondegenerate solutions of a system of Pfaffian equations. We isolate the ingredients of Khovanskii's original argument and assemble them into a proof that avoids the general theory of integral manifolds developed in his monograph. Our formulation mildly refines the classical statement: rather than depending on the ambient dimension, our bound depends on the maximum number of variables on which any function in the Pfaffian chain depends. As a consequence, we obtain a refined bound on the number of connected components of a Pfaffian set.

math.AG

Tubular Neighbourhoods of Pfaffian Sets and Applications to Neural Networks

We derive bounds for the volume of tubular neighbourhoods of smooth Pfaffian hypersurfaces, generalising known results for algebraic varieties. The bounds are given in terms of the Pfaffian format of the defining functions. As an application, we obtain tail bounds on the probability distribution of a condition number measuring the robustness of neural network classifiers with Pfaffian activation functions, in both the uniform and Gaussian settings. In the special case of single-hidden-layer sigmoid networks with rational weights, we derive polynomial-in-width bounds for tubular neighbourhoods of the decision boundary.

math.AG

Image Categorization and Search via a GAT Autoencoder and Representative Models

We propose a method for image categorization and retrieval that leverages graphs and a graph attention network (GAT)-based autoencoder. Our approach is representative-centric, that is, we execute the categorization and retrieval process via the representative models we construct for the images and image categories. We utilize a graph where nodes represent images (or their representatives) and edges capture similarity relationships. GAT highlights important features and relationships between images, enabling the autoencoder to construct context-aware latent representations that capture the key features of each image relative to its neighbors. We obtain category representatives from these embeddings and categorize a query image by comparing its representative to the category representatives. We then retrieve the most similar image to the query image within its identified category. We demonstrate the effectiveness of our representative-centric approach through experiments with both the GAT autoencoders and standard feature-based techniques.

cs.CV

Performance-Efficiency Trade-off for Fashion Image Retrieval

The fashion industry has been identified as a major contributor to waste and emissions, leading to an increased interest in promoting the second-hand market. Machine learning methods play an important role in facilitating the creation and expansion of second-hand marketplaces by enabling the large-scale valuation of used garments. We contribute to this line of work by addressing the scalability of second-hand image retrieval from databases. By introducing a selective representation framework, we can shrink databases to 10% of their original size without sacrificing retrieval accuracy. We first explore clustering and coreset selection methods to identify representative samples that capture the key features of each garment and its internal variability. Then, we introduce an efficient outlier removal method, based on a neighbour-homogeneity consistency score measure, that filters out uncharacteristic samples prior to selection. We evaluate our approach on three public datasets: DeepFashion Attribute, DeepFashion Con2Shop, and DeepFashion2. The results demonstrate a clear performance-efficiency trade-off by strategically pruning and selecting representative vectors of images. The retrieval system maintains near-optimal accuracy, while greatly reducing computational costs by reducing the images added to the vector database. Furthermore, applying our outlier removal method to clustering techniques yields even higher retrieval performance by removing non-discriminative samples before the selection.

cs.CV

Categorising SME Bank Transactions with Machine Learning and Synthetic Data Generation

Despite their significant economic contributions, Small and Medium Enterprises (SMEs) face persistent barriers to securing traditional financing due to information asymmetries. Cash flow lending has emerged as a promising alternative, but its effectiveness depends on accurate modelling of transaction-level data. The main challenge in SME transaction analysis lies in the unstructured nature of textual descriptions, characterised by extreme abbreviations, limited context, and imbalanced label distributions. While consumer transaction descriptions often show significant commonalities across individuals, SME transaction descriptions are typically nonstandard and inconsistent across businesses and industries. To address some of these challenges, we propose a bank categorisation pipeline that leverages synthetic data generation to augment existing transaction data sets. Our approach comprises three core components: (1) a synthetic data generation module that replicates transaction properties while preserving context and semantic meaning; (2) a fine-tuned classification model trained on this enriched dataset; and (3) a calibration methodology that aligns model outputs with real-world label distributions. Experimental results demonstrate that our approach achieves 73.49% (+-5.09) standard accuracy on held-out data, with high-confidence predictions reaching 90.36% (+-6.52) accuracy. The model exhibits robust generalisation across different types of SMEs and transactions, which makes it suitable for practical deployment in cash-flow lending applications. By addressing core data challenges, namely, scarcity, noise, and imbalance, our framework provides a practical solution to build robust classification systems in data-sparse SME lending contexts.

cs.CE

A Neural Difference-of-Entropies Estimator for Mutual Information

Estimating Mutual Information (MI), a key measure of dependence of random quantities without specific modelling assumptions, is a challenging problem in high dimensions. We propose a novel mutual information estimator based on parametrizing conditional densities using normalizing flows, a deep generative model that has gained popularity in recent years. This estimator leverages a block autoregressive structure to achieve improved bias-variance trade-offs on standard benchmark tasks.

stat.ML

Partitioning Theorems for Sets of Semi-Pfaffian Sets, with Applications

We generalize the seminal polynomial partitioning theorems of Guth and Katz to a set of semi-Pfaffian sets. Specifically, given a set $\Gamma \subseteq \mathbb{R}^n$ of $k$-dimensional semi-Pfaffian sets, where each $\gamma \in \Gamma$ is defined by a fixed number of Pfaffian functions, and each Pfaffian function is in turn defined with respect to a Pfaffian chain $\vec{q}$ of length $r$, for any $D \ge 1$, we prove the existence of a polynomial $P \in \mathbb{R}[X_1, \ldots, X_n]$ of degree at most $D$ such that each connected component of $\mathbb{R}^n \setminus Z(P)$ intersects at most $\sim \frac{|\Gamma|}{D^{n - k - r}}$ elements of $\Gamma$. Also, under some mild conditions on $\vec{q}$, for any $D \ge 1$, we prove the existence of a Pfaffian function $P'$ of degree at most $D$ defined with respect to $\vec{q}$, such that each connected component of $\mathbb{R}^n \setminus Z(P')$ intersects at most $\sim \frac{|\Gamma|}{D^{n-k}}$ elements of $\Gamma$. To do so, given a $k$-dimensional semi-Pfaffian set $\mathcal{X} \subseteq \mathbb{R}^n$, and a polynomial $P \in \mathbb{R}[X_1, \ldots, X_n]$ of degree at most $D$, we establish a uniform bound on the number of connected components of $\mathbb{R}^n \setminus Z(P)$ that $\mathcal{X}$ intersects; that is, we prove that the number of connected components of $(\mathbb{R}^n \setminus Z(P)) \cap \mathcal{X}$ is at most $\sim D^{k+r}$. Finally as applications, we derive Pfaffian versions of Szemer\'edi-Trotter type theorems, and also prove bounds on the number of joints between Pfaffian curves.

math.LO

Sharp phase transitions in Euclidean integral geometry

The intrinsic volumes of a convex body are fundamental invariants that capture information about the average volume of the projection of the convex body onto a random subspace of fixed dimension. The intrinsic volumes also play a central role in integral geometry formulas that describe how moving convex bodies interact. Recent work has demonstrated that the sequence of intrinsic volumes concentrates sharply around its centroid, which is called the central intrinsic volume. The purpose of this paper is to derive finer concentration inequalities for the intrinsic volumes and related sequences. These concentration results have striking implications for high-dimensional integral geometry. In particular, they uncover new phase transitions in formulas for random projections, rotation means, random slicing, and the kinematic formula. In each case, the location of the phase transition is determined by reducing each convex body to a single summary parameter.

math.MG

Dimensionality Reduction for $k$-Distance Applied to Persistent Homology

Given a set P of n points and a constant k, we are interested in computing the persistent homology of the Cech filtration of P for the k-distance, and investigate the effectiveness of dimensionality reduction for this problem, answering an open question of Sheehy [Proc. SoCG, 2014]. We show that any linear transformation that preserves pairwise distances up to a (1 +/- e) multiplicative factor, must preserve the persistent homology of the Cech filtration up to a factor of (1-e)^(-1). Our results also show that the Vietoris-Rips and Delaunay filtrations for the k-distance, as well as the Cech filtration for the approximate k-distance of Buchet et al. [J. Comput. Geom., 2016] are preserved up to a (1 +/- e) factor. We also prove extensions of our main theorem, for point sets (i) lying in a region of bounded Gaussian width or (ii) on a low-dimensional submanifold, obtaining embeddings having the dimension bounds of Lotz [Proc. Roy. Soc., 2019] and Clarkson [Proc. SoCG, 2008] respectively. Our results also work in the terminal dimensionality reduction setting, where the distance of any point in the original ambient space, to any point in P, needs to be approximately preserved.

cs.CG

Wilkinson's bus: Weak condition numbers, with an application to singular polynomial eigenproblems

We propose a new approach to the theory of conditioning for numerical analysis problems for which both classical and stochastic perturbation theory fail to predict the observed accuracy of computed solutions. To motivate our ideas, we present examples of problems that are discontinuous at a given input and have infinite classical and stochastic condition number, but where the solution is still computed to machine precision without relying on structured algorithms. Stimulated by the failure of classical and stochastic perturbation theory in capturing such phenomena, we define and analyse a weak worst-case and a weak stochastic condition number. This new theory is a more powerful predictor of the accuracy of computations than existing tools, especially when the worst-case and the expected sensitivity of a problem to perturbations of the input is not finite. We apply our analysis to the computation of simple eigenvalues of matrix polynomials, including the more difficult case of singular matrix polynomials. In addition, we show how the weak condition numbers can be estimated in practice.

math.NA

Effective Condition Number Bounds for Convex Regularization

We derive bounds relating Renegar's condition number to quantities that govern the statistical performance of convex regularization in settings that include the $\ell_1$-analysis setting. Using results from conic integral geometry, we show that the bounds can be made to depend only on a random projection, or restriction, of the analysis operator to a lower dimensional space, and can still be effective if these operators are ill-conditioned. As an application, we get new bounds for the undersampling phase transition of composite convex regularizers. Key tools in the analysis are Slepian's inequality and the kinematic formula from integral geometry.

math.NA

Persistent homology for low-complexity models

We show that recent results on randomized dimension reduction schemes that exploit structural properties of data can be applied in the context of persistent homology. In the spirit of compressed sensing, the dimension reduction is determined by the Gaussian width of a structure associated to the data set, rather than its size, and such a reduction can be computed efficiently. We further relate the Gaussian width to the doubling dimension of a finite metric space, which appears in the study of the complexity of other methods for approximating persistent homology. We can therefore literally replace the ambient dimension by an intrinsic notion of dimension related to the structure of the data.

cs.CG

On the Error in Phase Transition Computations for Compressed Sensing

Evaluating the statistical dimension is a common tool to determine the asymptotic phase transition in compressed sensing problems with Gaussian ensemble. Unfortunately, the exact evaluation of the statistical dimension is very difficult and it has become standard to replace it with an upper-bound. To ensure that this technique is suitable, [1] has introduced an upper-bound on the gap between the statistical dimension and its approximation. In this work, we first show that the error bound in [1] in some low-dimensional models such as total variation and $\ell_1$ analysis minimization becomes poorly large. Next, we develop a new error bound which significantly improves the estimation gap compared to [1]. In particular, unlike the bound in [1] that is not applicable to settings with overcomplete dictionaries, our bound exhibits a decaying behavior in such cases.

cs.IT

Concentration of the Intrinsic Volumes of a Convex Body

The intrinsic volumes are measures of the content of a convex body. This paper uses probabilistic and information-theoretic methods to study the sequence of intrinsic volumes of a convex body. The main result states that the intrinsic volume sequence concentrates sharply around a specific index, called the central intrinsic volume. Furthermore, among all convex bodies whose central intrinsic volume is fixed, an appropriately scaled cube has the intrinsic volume sequence with maximum entropy.

math.MG

Intrinsic Volumes of Polyhedral Cones: A combinatorial perspective

The theory of intrinsic volumes of convex cones has recently found striking applications in areas such as convex optimization and compressive sensing. This article provides a self-contained account of the combinatorial theory of intrinsic volumes for polyhedral cones. Direct derivations of the General Steiner formula, the conic analogues of the Brianchon-Gram-Euler and the Gauss-Bonnet relations, and the Principal Kinematic Formula are given. In addition, a connection between the characteristic polynomial of a hyperplane arrangement and the intrinsic volumes of the regions of the arrangement, due to Klivans and Swartz, is generalized and some applications are presented.

math.CO

Average-case complexity without the black swans

We introduce the concept of weak average-case analysis as an attempt to achieve theoretical complexity results that are closer to practical experience than those resulting from traditional approaches. This concept is accepted in other areas such as non-asymptotic random matrix theory and compressive sensing, and has a particularly convincing interpretation in the most common situation encountered for condition numbers, where it amounts to replacing a null set of ill-posed inputs by a "numerical null set". We illustrate the usefulness of these notions by considering three settings: (1) condition numbers that are inversely proportional to a distance of a homogeneous algebraic set of ill-posed inputs; (2) the running time of power iteration for computing a leading eigenvector of a Hermitian matrix; (3) Renegar's condition number for conic optimisation.

math.NA

Gordon's inequality and condition numbers in conic optimization

The probabilistic analysis of condition numbers has traditionally been approached from different angles; one is based on Smale's program in complexity theory and features integral geometry, while the other is motivated by geometric functional analysis and makes use of the theory of Gaussian processes. In this note we explore connections between the two approaches in the context of the biconic homogeneous feasiblity problem and the condition numbers motivated by conic optimization theory. Key tools in the analysis are Slepian's and Gordon's comparision inequalities for Gaussian processes, interpreted as monotonicity properties of moment functionals, and their interplay with ideas from conic integral geometry.

math.PR