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.
To realize efficient computational fluid dynamics (CFD) prediction of two-phase flow, a multi-scale framework was proposed in this paper by applying a physics-guided data-driven approach. Instrumental to this framework, Feature Similarity Measurement (FSM) technique was developed for error estimation in two-phase flow …
Hybrid model combines neural networks and fluid dynamics for efficient, generalized simulations.
Surrogate models improve chemical process equipment design and optimization.
FLUID-LLM uses LLMs to predict fluid dynamics with improved accuracy.
Generative Adversarial Networks simulate elevator group control without extensive data.
A multi-objective prediction method of multi-stage pump method based on neural network with data augmentation is proposed. In order to study the highly nonlinear relationship between key design variables and centrifugal pump external characteristic values (head and power), the neural network model (NN) is built in comp…
Deep learning speeds up real-time emission monitoring.
Contracts for Difference (CfDs) are forwards on the spread between an area price and the system price. Together with the system price forwards, these products are used to hedge the area price risk in the Nordic electricity market. The CfDs are typically available for the next two months, three quarters and three years.…
Optimizes UUV hull design with a two-orders-of-magnitude speedup.
Methane is considered being a good choice as a propellant for future reusable launch systems. However, the heat transfer prediction for supercritical methane flowing in cooling channels of a regeneratively cooled combustion chamber is challenging. Because accurate heat transfer predictions are essential to design relia…
Implicit Generative Models (IGMs) such as GANs have emerged as effective data-driven models for generating samples, particularly images. In this paper, we formulate the problem of learning an IGM as minimizing the expected distance between characteristic functions. Specifically, we minimize the distance between charact…
New algorithms improve vascular flow simulations in aortic aneurysms.
Computational Fluid Dynamics (CFD) is a hugely important subject with applications in almost every engineering field, however, fluid simulations are extremely computationally and memory demanding. Towards this end, we present Lat-Net, a method for compressing both the computation time and memory usage of Lattice Boltzm…
We show that Bordered Heegaard Floer invariant of a knot complement in is invariant under the elliptic involution on its boundary.
We show that bordered Heegaard Floer homology detects incompressible surfaces and bordered-sutured Floer homology detects partly boundary parallel tangles and bridges, in natural ways. For example, there is a bimodule Lambda so that the tensor product of CFD(Y) and Lambda is Hom-orthogonal to CFD(Y) if and only if the …
Knot Floer homology is reinterpreted as immersed curves.
New deep learning method improves 4D Flow MRI super-resolution under domain shift.
FAST selects coresets more efficiently by matching distributions in the frequency domain.
We propose an extension of the concept of Expected Improvement criterion commonly used in Kriging based optimization. We extend it for more complex Kriging models, e.g. models using derivatives. The target field of application are CFD problems, where objective function are extremely expensive to evaluate, but the theor…
Study shows how knot Floer homology and bordered Floer theory are linked.
Compact models for methane/air combustion reduce complexity without sacrificing accuracy.
Physics-based simulations are often used to model and understand complex physical systems and processes in domains like fluid dynamics. Such simulations, although used frequently, have many limitations which could arise either due to the inability to accurately model a physical process owing to incomplete knowledge abo…
A new method for efficient optimization of expensive simulations on HPC.
Motivated by the idea of turbomachinery active subspace performance maps, this paper studies dimension reduction in turbomachinery 3D CFD simulations. First, we show that these subspaces exist across different blades---under the same parametrization---largely independent of their Mach number or Reynolds number. This is…
The Poisson equation is commonly encountered in engineering, for instance in computational fluid dynamics (CFD) where it is needed to compute corrections to the pressure field to ensure the incompressibility of the velocity field. In the present work, we propose a novel fully convolutional neural network (CNN) architec…
This paper presents a physics-based data-driven method to learn predictive reduced-order models (ROMs) from high-fidelity simulations, and illustrates it in the challenging context of a single-injector combustion process. The method combines the perspectives of model reduction and machine learning. Model reduction brin…
Analyzes financial return distributions over various time scales.
RSF models censored functional data for better survival analysis.
We define a sutured cobordism category of surfaces with boundary and 3-manifolds with corners. In this category a sutured 3-manifold is regarded as a morphism from the empty surface to itself. In the process we define a new class of geometric objects, called bordered sutured manifolds, that generalize both sutured 3-ma…
Proposes FIPO-BC for efficient online calibration of complex models.
Automated method creates compact chemical models from detailed ones, reducing complexity and improving accuracy.
AMORE uses neural operators to efficiently predict multiple thermochemical states in stiff chemical kinetics.
A formula for bordered Floer homology of concordances and satellites
Engineering problems often involve data sources of variable fidelity with different costs of obtaining an observation. In particular, one can use both a cheap low fidelity function (e.g. a computational experiment with a CFD code) and an expensive high fidelity function (e.g. a wind tunnel experiment) to generate a dat…
Compressed Federated Distillation reduces communication in federated learning.
This paper gives a geometric interpretation of bordered Heegaard Floer homology for manifolds with torus boundary. If is such a manifold, we show that the type D structure may be viewed as a set of immersed curves decorated with local systems in . These curves-with-decoration ar…
Vortex induced vibrations of bluff bodies occur when the vortex shedding frequency is close to the natural frequency of the structure. Of interest is the prediction of the lift and drag forces on the structure given some limited and scattered information on the velocity field. This is an inverse problem that is not str…
BODE enhances deep neural network predictions and uncertainty quantification in safety modeling.
ALMAB-DC optimizes expensive black-box experiments using active learning and distributed computing.
Improved deep learning framework for estimating combustion variables.
The simulator is an R package that streamlines the process of performing simulations by creating a common infrastructure that can be easily used and reused across projects. Methodological statisticians routinely write simulations to compare their methods to preexisting ones. While developing ideas, there is a temptatio…
PAMS is a Python-based platform for simulating artificial markets.
The interpretability of machine learning, particularly for deep neural networks, is crucial for decision making in real-world applications. One approach is replacing the un-interpretable machine learning model with a surrogate model, which has a simple structure for interpretation. Another approach is understanding the…
Smartfluidnet accelerates Eulerian fluid simulation with neural networks.
Proposes a new simulator for complex arrival processes.
ACE improves GBI for simulators by approximating cost functions, making inference more efficient.
New method improves sample-efficiency in neural posterior estimation using simulator gradients.
Simulates risk-neutral markets using neural spline flows.