arXiv research

Develops VAEs for learning complex physical systems from data.

Semi-parametric framework for nonlinear system identification

Physics-guided model improves deep learning for nonlinear systems.

We introduce physics informed neural networks -- neural networks that are trained to solve supervised learning tasks while respecting any given law of physics described by general nonlinear partial differential equations. In this second part of our two-part treatise, we focus on the problem of data-driven discovery of …

Unified framework detects change-points and estimates parameters in nonlinear systems with regime switching.

Unified bounds for neural networks incorporating physical laws.

Bayesian model learns physics laws from data with uncertainty quantification.

Harmonic maps from Riemann surfaces arise from a conformally invariant variational problem. Therefore, on one hand, they are intimately connected with moduli spaces of Riemann surfaces, and on the other hand, because the conformal group is noncompact, constitute a prototype for the formation of singularities, the so-ca…

Unified physics-informed learning method improves generalization performance.

SOAD model improves data assimilation for nonlinear systems.

We introduce physics informed neural networks -- neural networks that are trained to solve supervised learning tasks while respecting any given law of physics described by general nonlinear partial differential equations. In this two part treatise, we present our developments in the context of solving two main classes …

A novel solve-training framework is proposed to train neural network in representing low dimensional solution maps of physical models. Solve-training framework uses the neural network as the ansatz of the solution map and train the network variationally via loss functions from the underlying physical models. Solve-trai…

The paper extends IPC framework to stationary physical systems and validates it with a photonic system.

GyroSwin models plasma turbulence with neural nets, reducing costs and capturing neglected nonlinearities.

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…

The financial rogue waves are reported analytically in the nonlinear option pricing model due to Ivancevic, which is nonlinear wave alternative of the Black-Scholes model. These solutions may be used to describe the possible physical mechanisms for rogue wave phenomenon in financial markets and related fields.

Efficient surrogate modeling for complex PDEs with physical laws.

We provide an introduction to the mathematics and physics of the deformed Hermitian-Yang-Mills equation, a fully nonlinear geometric PDE on Kahler manifolds which plays an important role in mirror symmetry. We discuss the physical origin of the equation, and some recent progress towards its solution. In dimension 3 we …

Reduces nonlinear electromechanical dynamics through quasi-steady state hypothesis.

Intelligent agents need a physical understanding of the world to predict the impact of their actions in the future. While learning-based models of the environment dynamics have contributed to significant improvements in sample efficiency compared to model-free reinforcement learning algorithms, they typically fail to g…

Automated denoising score matching handles nonlinear diffusion processes.

A new method infers parameters from PDEs using Gaussian processes.

Proposes a framework to identify and correct model-form errors in nonlinear systems.

The paper studies minimal resistance dynamics in radial fields, finding unique solutions for incompressible flows.

A new method estimates parameters of complex models using ordinary least squares.

We propose a new framework for constructing geometric and physical models on nonholonomic manifolds provided both with Clifford -- Lie algebroid symmetry and nonlinear connection structure. Explicit parametrizations of generic off-diagonal metrics and linear and nonlinear connections define different types of Finsler, …

Physics-constrained deep learning predicts geophysical dynamics with boundedness.

Physics-based deep learning improves fiber-optic communication efficiency.

Soft-constrained PINN solves ODEs with minimal data, improving efficiency and robustness.

Dataset of Bose-Einstein condensates images aids ML in many-body physics.

In this paper we introduce a simple continuous-time asset pricing framework, based on general multi-dimensional diffusion processes, that combines semi-analytic pricing with a nonlinear specification for the market price of risk. Our framework guarantees existence of weak solutions of the nonlinear SDEs under the physi…

Equivariant neural network simplifies particle physics models.

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…

PICN learns physical fields from shallow neural networks, improving AI in multi-physical systems.

DynNet models dynamic responses of linear and nonlinear systems with fewer variables and higher accuracy.

New algorithms tackle data challenges in physics model selection.

RS-PINN uses randomized smoothing to speed up high-dimensional PDE simulations without sacrificing accuracy.

Neural networks simplify uncertainty quantification of locally nonlinear systems.

Develops scalable differentiable physics for complex object interactions.

Physics-consistent method improves seismic inversion accuracy.

The aim of this paper is to open the problem of construction of a nonlinear connection $Γ=(M^{(i)}_{(α)β}, N^{(i)}_{(α)j})$ on the jet bundle of first order $J^1(T,M)$, which to be canonically produced by a Kronecker product vertical metrical d-tensor $G^{(α)(β)}_{(i)(j)}=h^{αβ}g_{ij}$, possibly provided by multi-time …

The coupled nonlinear volatility and option pricing model presented recently by Ivancevic is investigated, which generates a leverage effect, i.e., stock volatility is (negatively) correlated to stock returns, and can be regarded as a coupled nonlinear wave alternative of the Black-Scholes option pricing model. In this…

LDDNN learns physical dynamics from data without exact solutions.

I discuss certain applications of the Ricci flow in physics. I first review how it arises in the renormalization group (RG) flow of a nonlinear sigma model. I then review the concept of a Ricci soliton and recall how a soliton was used to discuss the RG flow of mass in 2-dimensions. I then present recent results obtain…

General formulas for the construction of exact solutions of the equation of the minimal surface in $R^3$, which appears in various physical problems, have been derived by the Zakharov-Shabat "dressing" method. Particular examples are considered.

We conjecture that a non-flat $D$-real-dimensional compact Calabi-Yau manifold, such as a quintic hypersurface with D=6, or a K3 manifold with D=4, has locally length minimizing closed geodesics, and that the number of these with length less than L grows asymptotically as L^{D}. We also outline the physical arguments b…

Predicting outcomes and planning interactions with the physical world are long-standing goals for machine learning. A variety of such tasks involves continuous physical systems, which can be described by partial differential equations (PDEs) with many degrees of freedom. Existing methods that aim to control the dynamic…

The Ricci flow has been of fundamental importance in mathematics, most famously though its use as a tool for proving the Poincaré Conjecture and Thurston's Geometrization Conjecture. It has a parallel life in physics, arising as the first order approximation of the Renormalization Group flow for the nonlinear sigma mod…