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.
LLMs struggle with arithmetic tasks unless they use high numerical precision.
The study uncovers latent capabilities of language models via causal representation learning.
Existing approaches for automatically generating mathematical word problems are deprived of customizability and creativity due to the inherent nature of template-based mechanisms they employ. We present a solution to this problem with the use of deep neural language generation mechanisms. Our approach uses a Character …
Mathematical study shows post-hoc explanations are better than attention weights alone.
Benchmark for math reasoning models from human proofs.
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…
Mathematical framework for differential machine learning in finance.
Machine learning impacts computational math, offering new functions approximations.
Transformers with CoT don't enhance reasoning power across all tasks.
There is a need for affordable, widely deployable maternal-fetal ECG monitors to improve maternal and fetal health during pregnancy and delivery. Based on the diffusion-based channel selection, here we present the mathematical formalism and clinical validation of an algorithm capable of accurate separation of maternal …
AER dynamically adjusts entropy regularization for better LLM reinforcement learning.
Paper introduces a new measure combining entropy and Gini index.
This paper deals with the explicit design of strategy formulations to make the best strategic choices from a conventional matrix form of representing strategic choices. The explicit strategy formulation is an analytical model which is targeted to provide a mathematical strategy framework to find the best moment for str…
Recently, artificial neural networks (ANNs) in conjunction with stochastic gradient descent optimization methods have been employed to approximately compute solutions of possibly rather high-dimensional partial differential equations (PDEs). Very recently, there have also been a number of rigorous mathematical results …
GFN-SR uses deep learning to generate diverse mathematical expressions.
Transformers learn topic structure through embedding and attention mechanisms.
We incorporate Tensor-Product Representations within the Transformer in order to better support the explicit representation of relation structure. Our Tensor-Product Transformer (TP-Transformer) sets a new state of the art on the recently-introduced Mathematics Dataset containing 56 categories of free-form math word-pr…
The paper analyzes financial market turbulence using mathematical physics.
Distance metric learning is a branch of machine learning that aims to learn distances from the data, which enhances the performance of similarity-based algorithms. This tutorial provides a theoretical background and foundations on this topic and a comprehensive experimental analysis of the most-known algorithms. We sta…
A long-standing problem at the interface of artificial intelligence and applied mathematics is to devise an algorithm capable of achieving human level or even superhuman proficiency in transforming observed data into predictive mathematical models of the physical world. In the current era of abundance of data and advan…
PDGM uses neural nets to solve complex financial equations.
TIR expands LLM capabilities by enabling problem-solving strategies.
Mathematical modeling with Ordinary Differential Equations (ODEs) has proven to be extremely successful in a variety of fields, including biology. However, these models are completely deterministic given a certain set of initial conditions. We convert mathematical ODE models of three benchmark biological systems to Dyn…
Paper introduces Prob-SSI for robust OMA in noisy data.
TNet combines DL with physics models to solve inverse problems efficiently.
We demonstrate the application of an algorithmic trading strategy based upon the recently developed dynamic mode decomposition (DMD) on portfolios of financial data. The method is capable of characterizing complex dynamical systems, in this case financial market dynamics, in an equation-free manner by decomposing the s…
The presence of symmetries in a Hamiltonian system usually implies the existence of conservation laws that are represented mathematically in terms of the dynamical preservation of the level sets of a momentum mapping. The symplectic or Marsden--Weinstein reduction procedure takes advantage of this and associates to the…
Uniform consistency proven for spatial distribution and depth estimators in any dimension.
Kolmogorov-Arnold Networks promise scalable performance in high dimensions.
Geometric arbitrage theory reformulates a generic asset model possibly allowing for arbitrage by packaging all asset and their forward dynamics into a stochastic principal fibre bundle, with a connection whose parallel transport encodes discounting and portfolio rebalancing, and whose curvature measures, in this geomet…
Enhances math problem-solving models with multi-turn preference learning.
We study the dynamics of a particle in a space that is non-differentiable. Non-smooth geometrical objects have an inherently probabilistic nature and, consequently, introduce stochasticity in the motion of a body that lives in their realm. We use the mathematical concept of fiber bundle to characterize the multivalued …
While there is currently a lot of enthusiasm about "big data", useful data is usually "small" and expensive to acquire. In this paper, we present a new paradigm of learning partial differential equations from {\em small} data. In particular, we introduce \emph{hidden physics models}, which are essentially data-efficien…
The mixed-fractional CEV model improves CDS pricing by accounting for default risk.
We study the problem of predicting rare critical transition events for a class of slow-fast nonlinear dynamical systems. The state of the system of interest is described by a slow process, whereas a faster process drives its evolution and induces critical transitions. By taking advantage of recent advances in reservoir…
Bayesian Causal Forests model assesses part-time work's impact on student growth.
The paper proposes a method to identify causal structure in complex dynamical systems.
When people learn mathematical patterns or sequences, they are able to identify the concepts (or rules) underlying those patterns. Having learned the underlying concepts, humans are also able to generalize those concepts to other numbers, so far as to even identify previously unseen combinations of those rules. Current…
DeepONets improve surrogate modeling for engineering systems.
Model for dynamic pricing across multiple RE groups to maximize revenue.
Auto-CEI improves LLM reasoning by balancing assertiveness and conservativeness.
Bayesian Gaussian Processes layer detects out-of-distribution data in medical imaging.
FML uses neural networks to model unknown systems accurately.
Transformers learn functionals from distributions without losing information.
Study proposes a new metric for comparing Gaussian mixtures in RKHS.
In this paper, we study a multi-step interactive recommendation problem, where the item recommended at current step may affect the quality of future recommendations. To address the problem, we develop a novel and effective approach, named CFRL, which seamlessly integrates the ideas of both collaborative filtering (CF) …
Advanced mathematical relativity course for math and physics students.
The paper surveys mathematical results on filtration enlargement with financial examples.