This paper offers a mathematical introduction to GANs.
problem Understanding GANs from a mathematical perspective.
method Mathematical analysis of GANs.
result Provides clarity for math-oriented students.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,694 papers · 148 categories
Trend · papers per month
48 results for “mathematical understanding”
We provide an introduction to selected recent advances in the mathematical understanding of Einstein's theory of gravitation.
This article reviews mathematical insights into neural networks and machine learning.
problem Understanding the success and subtleties of neural network-based machine learning.
method Rigorous mathematical analysis, numerical experiments, and simplified models.
result Identification of open problems in the field.
Transformers learn topic structure through embedding and attention mechanisms.
problem Understanding how transformers capture semantic structure in text.
method Combination of mathematical analysis and experiments on Wikipedia and synthetic data.
result Embedding and attention layers encode topic structure in transformers.
Mathematical framework for understanding attention in neural networks.
problem Lack of theoretical understanding of attention in neural networks.
method Proposes a measure-theoretic model of attention and interprets self-attention as a system of self-interacting particles.
result Shows that attention is Lipschitz-continuous under suitable assumptions.
Higgs bundles appeared a few decades ago as solutions to certain equations from physics and have attracted much attention in geometry as well as other areas of mathematics and physics. Here, we take a very informal stroll through some aspects of linear algebra that anticipate the deeper structure in the moduli space of…
Lecture Notes on Linear Neural Networks: A Tale of Optimization and Generalization in Deep Learningcs.LG
Lecture notes on linear neural networks for deep learning optimization and generalization.
problem Understanding optimization and generalization in deep learning models.
method Mathematical tools and dynamical systems theory.
result Potential of mathematical tools to enhance understanding of deep learning.
In this paper, we aim to understand Residual Network (ResNet) in a scientifically sound way by providing a bridge between ResNet and Feynman path integral. In particular, we prove that the effect of residual block is equivalent to partial differential equation, and the ResNet transforming process can be equivalently co…
Label smoothing improves generalization by controlling generalization loss.
problem Lack of mathematical understanding of label smoothing's effectiveness.
method Proposed a theoretical framework to show how label smoothing controls generalization loss in the label noise setting.
result Predicted an optimal label smoothing point that minimizes generalization loss.
AI mirrors modern math's autonomous development, raising interpretive challenges.
problem AI's effectiveness in math mirrors historical autonomy of math.
method Analyzes historical evolution of modern mathematics and AI's role.
result AI's affinity with math's historical autonomy suggests interpretive limits.
Neural networks are mathematically represented via quiver representations.
problem Understanding how neural networks process data and create representations.
method Representing neural networks as quiver representations with activation functions.
result Neural networks' computations can be studied algebraically and geometrically.
Several recent works have empirically observed that Convolutional Neural Nets (CNNs) are (approximately) invertible. To understand this approximate invertibility phenomenon and how to leverage it more effectively, we focus on a theoretical explanation and develop a mathematical model of sparse signal recovery that is c…
Data science enhances knot theory by analyzing invariant relations.
problem Understanding the complex relations between knot invariants.
method Topological data analysis applied to knot theory.
result New insights into long-standing conjectures about knots.
The mathematical features of a string theory compactification determine the physics of the effective four-dimensional theory. For this reason, understanding the mathematical structure of the possible compactification spaces is of profound importance. It is well established that the compactification space for M-Theory m…
t-SNE loses important features in data visualization.
problem t-SNE's loss of important features in data visualization.
method Established mathematical framework to understand t-SNE's loss in different scenarios.
result t-SNE loses important features of data in various scenarios.
Mathematical framework for language models processes text and predicts next tokens.
problem Understanding and optimizing the performance of large language models.
method Describes encoding, prediction models, learning from data, and deployment of LLMs.
result Demonstrates remarkable empirical successes and provides a platform for further research.
Develops a logifold structure for understanding datasets.
problem Understanding and classifying complex datasets.
method Local-to-global approach using measure-theoretical models.
result Improves accuracy in data classification problems.
Recent studies show overparameterized neural networks behave like convex systems.
problem Understanding the behavior of overparameterized neural networks.
method Analysis of two-layer neural networks, focusing on restricted settings and neural tangent kernel space.
result Overparameterized neural networks behave like convex systems under certain conditions.
Mathematical reasoning---a core ability within human intelligence---presents some unique challenges as a domain: we do not come to understand and solve mathematical problems primarily on the back of experience and evidence, but on the basis of inferring, learning, and exploiting laws, axioms, and symbol manipulation ru…
Sequences of Arbitragesq-fin.TR
The goal of this article is to understand some interesting features of sequences of arbitrage operations, which look relevant to various processes in Economics and Finances. In the second part of the paper, analysis of sequences of arbitrages is reformulated in the linear algebra terms. This admits an elegant geometric…
This paper explores how deep learning models can fit data exactly and why this is important.
problem Understanding why deep learning models can fit data exactly and generalize well.
method Interpolation and over-parameterization as key themes to understand deep learning.
result Interpolation and over-parameterization are crucial for deep learning models to fit data exactly and generalize well.
Explains classic quantitative strategies and their workings.
problem Debunking the magic behind black-box quantitative strategies.
method Derives from simple intuitions and mathematics, addressing both formal and informal aspects.
result Provides a deeper understanding of quantitative strategies.
We discuss classical gravitational aspects of the AdS/CFT correspondence, with the aim of obtaining a rigorous (mathematical) understanding of the semi-classical limit of the gravitational partition function. The paper surveys recent progress in the area, together with a selection of new results and open problems.
LLMs struggle with arithmetic tasks unless they use high numerical precision.
problem Improving arithmetical reasoning capabilities of LLMs.
method Theoretical analysis and empirical experiments on numerical precision.
result LLMs require high numerical precision to efficiently handle arithmetic tasks.
Mathematical method based on a direct or indirect analysis of growth rates is described. It is shown how simple assumptions and a relatively easy analysis can be used to describe mathematically complicated trends and to predict growth. Only rudimentary knowledge of calculus is required. Projected trajectories based on …
This paper provides a mathematical framework for understanding distribution learning models.
problem The paradox between memorization and generalization in distribution learning models.
method A unified mathematical framework to derive various distribution learning models.
result The models enjoy implicit regularization, avoiding the curse of dimensionality and resolving the paradox.
in [2] is zeromath.DG
In this short Note, we establish that the constant in Lemma of the correction (Correction to Section 19.2 of Ricci Flow and the Poincare Conjecture, arXiv/math/DG:1512.00699 (2015)) by John Morgan and Gang Tian to their Clay Institute Monograph (Ricci Flow and the Poincare Conjecture, vol. 3, Clay Mathemati…
Mathematical framework to understand neural network vulnerability.
problem Understanding and quantifying adversarial vulnerability in neural networks.
method Develops a geometric framework using Ricci curvature to measure decision boundaries and adversarial perturbations.
result Establishes a new theory linking adversarial attacks to Ricci curvature of decision boundaries.
Researchers study the normalizing constant of a continuous categorical distribution.
problem Understanding the normalizing constant of the continuous categorical distribution.
method Characterize numerical behavior and present theoretical and methodological advances.
result The normalizing constant can be written in closed form using elementary functions.
Logifold improves ensemble machine learning by identifying fuzzy domains.
problem Improving ensemble machine learning accuracy.
method Formulating logifold structure and interpreting local charts of datasets.
result Logifold improves accuracy compared to averaging model outputs.
Preparation for Gauge Theorymath-ph
Class lecture notes at a beginning graduate level on the mathematical background needed to understand classical gauge theory. Covers group actions, fiber bundles, principal bundles, connections, gauge transformations, parallel transport, curvature, covariant derivatives, pseudo-riemannian manifolds, lagrangians, cliffo…
Develops statistical guarantees for neural networks with regularization.
problem Lack of comprehensive mathematical theories for neural networks.
method General statistical guarantee for least-squares with regularizers.
result Prediction error increases sub-linearly in layers, logarithmically in parameters.
In this paper we describe multigraded generalizations of some constructions useful for mathematical understanding of gauge theories: we perform a near-at-hand generalization of the Aleksandrov--Kontsevich--Schwarz--Zaboronsky procedure, we also extend the formalism of -bundles introduced first by A. Kotov and T. Str…
Deep convolutional networks provide state of the art classifications and regressions results over many high-dimensional problems. We review their architecture, which scatters data with a cascade of linear filter weights and non-linearities. A mathematical framework is introduced to analyze their properties. Computation…
Financial markets provide a natural quantitative lab for understanding some of the most advanced human behaviours. Among them is the use of mathematical tools known as financial instruments. Besides money, the two most fundamental financial instruments are bonds and equities. More than 30 years ago Mehra and Prescott f…
Towards Understanding Residual and Dilated Dense Neural Networks via Convolutional Sparse Codingcs.LG
Convolutional neural network (CNN) and its variants have led to many state-of-art results in various fields. However, a clear theoretical understanding about them is still lacking. Recently, multi-layer convolutional sparse coding (ML-CSC) has been proposed and proved to equal such simply stacked networks (plain networ…
Survey on moduli spaces of differentials from algebraic geometry perspective.
problem Understanding the topology of moduli spaces of differentials remains limited.
method Algebraic geometry perspective, connections to various fields.
result Many open problems and connections to other fields.
Encoder-decoder networks using convolutional neural network (CNN) architecture have been extensively used in deep learning literatures thanks to its excellent performance for various inverse problems. However, it is still difficult to obtain coherent geometric view why such an architecture gives the desired performance…
In this pedagogical study, carried out by adopting standard mathematical methods of nonlinear dynamics, we have presented some simple analytical models to understand terminal behaviour in industrial growth. This issue has also been addressed from a dynamical systems perspective, with especial emphasis on the concept of…
Paper revisits PCA for anomaly detection in network security.
problem Understanding and improving anomaly detection in network security.
method Revisit probabilistic PCA model and its connection to MSNM framework.
result Mathematical model connects PCA to MSNM for anomaly detection.
A new mathematical approach detects frequency-based alterations in brain networks.
problem Understanding disease-relevant brain alterations through network analysis.
method Proposes a novel connectome harmonic analysis framework using common harmonic waves learned from Stiefel manifolds.
result Identifies more significant and reproducible network dysfunction patterns in Alzheimer's disease.
Principal component analysis (PCA) is a mainstay of modern data analysis - a black box that is widely used but (sometimes) poorly understood. The goal of this paper is to dispel the magic behind this black box. This manuscript focuses on building a solid intuition for how and why principal component analysis works. Thi…
Language models help text classification tasks by predicting next words.
problem Lack of theoretical understanding of why language models perform well on downstream tasks.
method Mathematical study of the connection between next word prediction and text classification, formalizing it and quantifying the benefit.
result Language models that are ε-optimal in cross-entropy learn features that can solve classification tasks with linear approximation.
Book introduces deep learning methods with math, theory, and applications.
problem Understanding deep learning algorithms and their mathematical foundations.
method Reviews various ANN architectures and optimization methods, covers theoretical aspects.
result Provides a solid mathematical foundation for deep learning.
Symmetry, a central concept in understanding the laws of nature, has been used for centuries in physics, mathematics, and chemistry, to help make mathematical models tractable. Yet, despite its power, symmetry has not been used extensively in machine learning, until rather recently. In this article we show a general wa…
Signatures simplify analysis of evolving data streams.
problem Understanding and analyzing irregular, non-stationary data streams.
method Mathematical signatures reduce noise and preserve key information.
result Signatures manage the exponential scaling of data complexity.
Developable ruled surfaces generated by curvature axes of curves.
problem Creating simple and understandable ruled surfaces for practical design.
method Investigating a straightforward method to generate developable ruled surfaces using curvature axes of curves.
result Developable ruled surfaces are generated by the curvature axes of curves, and these surfaces are developable.
The study evaluates how prediction helps identify the worst-off in welfare programs.
problem Identifying the most vulnerable individuals for support.
method Mathematical models and real-world case study on long-term unemployment.
result Prediction is more effective than other policy levers in surfacing the worst-off.