Research
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.

168,657 papers · 148 categories

Trend · papers per month

91181272362 · Jun 202019922001200920172026
48 results for mean-field limits

Kernel methods are studied in a mean field limit for high-dimensional data.

problem Analyzing kernel methods in high-dimensional data with many variables.
method Investigation of kernel methods in the mean field limit of interacting particle systems.
result Rigorous mean field limit of kernels and detailed analysis of the limiting reproducing kernel Hilbert space.

The paper studies Hawkes processes under mean-field limits and criticality conditions.

problem Analyzing nearly unstable Hawkes processes in a mean-field regime.
method Extending the method by Jaisson and Rosenbaum, establishing scaling limits and propagation of chaos.
result Scaling limits of Hawkes processes are stochastic Volterra diffusions of affine type, with three distinct limiting regimes.

Global convergence proved for three-layer neural networks in mean field regime.

problem Optimization efficiency of multilayer neural networks in the mean field regime.
method Developed a rigorous framework for mean field limit of three-layer networks using stochastic gradient descent and neuronal embedding.
result Global convergence guarantee for unregularized feedforward three-layer networks in the mean field regime.

The paper connects PSO and CBO methods using stochastic modeling and mean-field limits.

problem Global optimization problems with particle swarm optimization and consensus based optimization.
method Stochastic differential equations and mean-field approximation to derive macroscopic hydrodynamic equations.
result Derives mean-field approximation for PSO and links it to CBO methods.

We study the convergence of Nash equilibria in a game of optimal stopping. If the associated mean field game has a unique equilibrium, any sequence of nn-player equilibria converges to it as nn\to\infty. However, both the finite and infinite player versions of the game often admit multiple equilibria. We show that me…

2018-06-03abs ↗pdf ↗

Study on mean field games with singular controls and their applications.

problem Optimal productivity expansion in dynamic oligopolies.
method Existence and uniqueness of mean field equilibria through nonlinear equations, Abelian limit for discounted and ergodic games.
result Valid connection between discounted and ergodic games, approximation of Nash equilibria.

Study shows finite agent equilibrium converges to mean-field limit in asset pricing.

problem Asset pricing equilibrium in markets with finite vs infinite agents.
method Existence of finite agent equilibrium and strong convergence to mean-field limit.
result Finite agent equilibrium converges to mean-field limit under suitable conditions.

Revises mean-field theory of Santa Fe model using kinetic theory.

problem Deriving a solid mathematical foundation for the Santa Fe model.
method Systematic derivation of BBGKY hierarchy from exact master equation.
result Explicit and closed-form solutions for mean-field equations.

In this work we introduce a model of default contagion that combines the approaches of Eisenberg-Noe interbank networks and dynamic mean field interactions. The proposed contagion mechanism provides an endogenous rule for early defaults in a network of financial institutions. The main result is to demonstrate a mean fi…

2019-12-18abs ↗pdf ↗

In this paper we study a continuous time equilibrium model of limit order book (LOB) in which the liquidity dynamics follows a non-local, reflected mean-field stochastic differential equation (SDE) with evolving intensity. Generalizing the basic idea of Ma et al. (2015), we argue that the frontier of the LOB (e.g., the…

2020-02-28abs ↗pdf ↗

Mean field game theory studies the behavior of a large number of interacting individuals in a game theoretic setting and has received a lot of attention in the past decade (Lasry and Lions, Japanese journal of mathematics, 2007). In this work, we derive mean field game partial differential equation systems from determi…

2019-10-29abs ↗pdf ↗

Gradient descent dynamics in wide neural networks are analyzed using a dynamical CLT.

problem Understanding the fluctuations in wide shallow neural networks trained via gradient descent.
method Dynamical Central Limit Theorem (CLT) applied to neural network dynamics.
result Asymptotic fluctuations remain bounded in mean square throughout training.

Analysis of SGD for Gaussian mixture classification using dynamical mean-field theory.

problem Learning dynamics of SGD for a neural network classifying Gaussian mixture.
method Applying dynamical mean-field theory to track SGD dynamics in high dimensions.
result Reveals how SGD navigates the non-convex loss landscape.

Paper analyzes SHB method for neural networks, proving stability, connectivity, and global convergence.

problem Theoretical understanding of SHB method for neural networks.
method Mean-field analysis of SHB dynamics related to a partial differential equation.
result SHB method converges to global optimum and exhibits stability and connectivity.

Study explores optimal strategies in games with multiple players and mean-field interactions.

problem Optimal strategies in games with multiple players and mean-field interactions.
method Exploration of three different notions of optimality, including mean-field control solution, mean-field coarse correlated equilibria, and mean-field Nash equilibria.
result Approximation of cooperative and competitive equilibria in large NN-player games by mean-field control and mean-field equilibria.

Study on price formation in a market with a major player and minor firms.

problem Equilibrium price formation in a market with a major financial firm and many minor firms.
method Analyzes the equilibrium price process in both finite and mean field models, considering idiosyncratic and common noises.
result Derives the functional form of price impact for the major firm in both market sizes.

We rigorously prove a central limit theorem for neural network models with a single hidden layer. The central limit theorem is proven in the asymptotic regime of simultaneously (A) large numbers of hidden units and (B) large numbers of stochastic gradient descent training iterations. Our result describes the neural net…

2018-08-28abs ↗pdf ↗

Two-layer neural networks learn efficiently using kernel methods in mean-field analysis.

problem Feature learning ability of two-layer neural networks in the mean-field regime.
method Mean-field analysis through kernel methods, focusing on dynamics of the first layer's kernel.
result Two-layer neural networks can learn a union of multiple reproducing kernel Hilbert spaces more efficiently than kernel methods.

Develops a dynamic mean field theory for reinforcement learning.

problem Finite state and action Bayesian reinforcement learning in large state spaces.
method Analogies with statistical physics, interpreting probabilities as couplings and values as spins, solving mean field equations.
result State-action values are statistically independent in the asymptotic state space limit, with exact or approximate equations for computation.

We review recent quantitative results on the approximation of mean field diffusion equations by large systems of interacting particles, obtained by optimal coupling methods. These results concern a larger range of models, more precise senses of convergence and links with the long time behaviour of the systems to be con…

2010-09-20abs ↗pdf ↗

The study analyzes a three-layer neural network's training dynamics using a functional-space mean-field theory.

problem Understanding the training dynamics of partially-trained three-layer neural networks.
method Generalized mean-field theory to functional spaces, proving convergence and feature learning.
result The training loss of the model decays to zero at a linear rate in the L2L_2 regression setting.

Study connects bank default models using dynamic contagion.

problem Understanding default contagion in heterogeneous interbank systems.
method Proposes a dynamic default contagion model with endogenous early defaults for a finite set of banks, reformulating as a stochastic particle system.
result Existence of clearing systems and continuity of the system response for the mean-field problem.

New framework for understanding infinite-width neural networks.

problem Understanding the infinite-width limit behavior of neural networks.
method General framework to study limit behavior of neural models based on hyperparameter scaling.
result Derives scaling for existing mean-field and neural tangent kernel limits and introduces new dynamically stable limits.

Bayesian neural networks learn efficiently at infinite width, matching polynomial-width performance.

problem Understanding the inductive bias of infinite-width neural networks.
method Analyzing the reduced entropy and using subsampling techniques.
result The Bayesian mean-field learner generalizes exactly on polynomially-bounded targets.

Study examines infinite limits of transformer dynamics, identifying key parameterizations.

problem Understanding the training dynamics of transformer models in the feature learning regime.
method Analysis of infinite scaling limits using dynamical mean field theory.
result Identified parameterizations that admit well-defined infinite width and depth limits.

Enhanced ensemble filters use machine learning to improve accuracy in filtering models.

problem Accuracy limitations of traditional ensemble Kalman filters.
method Introduces a measure neural mapping (MNM) to map joint predicted state and observation to updated state estimates.
result Superior root-mean-square-error performance compared to leading methods in filtering models.

Paper analyzes Transformer learning dynamics, proving benign landscape for in-context learning.

problem Understanding how Transformers learn in context with nonlinear features.
method Mean-field and two-timescale analysis of Transformer dynamics, proving nonconvex but benign landscape.
result Proves mean-field dynamics avoid saddle points, leading to improved optimization.

The paper analyzes optimal investment strategies in a game with jump risk, deriving mean field equilibria.

problem Optimal investment strategies in a game with jump risk and peer competition.
method Formulated mean field game and n-player game models, characterized equilibrium states, and derived approximation errors.
result Explicit mean field equilibrium and approximate Nash equilibrium for large n-player games.

Paper studies convergence of Mean-Field GDA dynamics for MNE of continuous games.

problem Finding mixed Nash equilibria in continuous games.
method Two-scale Mean-Field Gradient Descent Ascent dynamics.
result Two-scale Mean-Field GDA converges exponentially to MNE without convexity assumptions.

Study on price formation among investors with exponential utility and liabilities.

problem Equilibrium price formation among investors with heterogeneous risk-averseness and liabilities.
method Mean-field game theory and mean-field backward stochastic differential equations (BSDE).
result Existence of equilibrium risk-premium process and market clearing in the large population limit.

Game-theoretic models predict asset prices in financial markets.

problem Understanding price formation in financial markets with limited liquidity.
method Developed game-theoretic models for many-person and mean-field games, derived analytical formulas, and numerically assessed results.
result The derived price converges to the mean-field counterpart under specific conditions.

In this paper we study iterative procedures for stationary equilibria in games with large number of players. Most of learning algorithms for games with continuous action spaces are limited to strict contraction best reply maps in which the Banach-Picard iteration converges with geometrical convergence rate. When the be…

2012-10-17abs ↗pdf ↗

Wide neural networks learn features under μμP, identifying weights and decomposing support.

problem Feature learning in wide neural networks under μμP.
method Proving mean-field limit, characterizing identifiability, sparse-dictionary decomposition, and feature-learning-error decomposition.
result The triple (w,Dorb,S)(w^*, D^*_{\mathrm{orb}}, S^*) identifies the natural learning cell of the architecture-data pair (σ,ρ)(σ, ρ).

Analyzes SGD dynamics in two-layer networks, bridging different regimes.

problem Understanding SGD dynamics in high-dimensional and mean-field settings.
method Rigorous analysis via deterministic low-dimensional description of sufficient statistics.
result Infinite-width dynamics remains close to a low-dimensional subspace.

Improved particle approximation for mean-field neural networks.

problem Particle approximation error for mean-field neural networks.
method Improved particle approximation error by leveraging the problem structure in risk minimization.
result Established an LSI-constant-free particle approximation error concerning the objective gap.

This work studies fluctuation in multilayer neural networks using mean field theory.

problem Understanding fluctuation in multilayer neural networks with mean field training.
method Developed a second-order mean field limit to capture fluctuation, demonstrating stability of gradient descent training.
result Gradient descent training in multilayer networks biases towards minimal fluctuation, even after convergence.

Novel approach to Nash equilibrium in mean-field stochastic games with operator resolvents.

problem Finding Nash equilibrium in mean-field stochastic games with mean-field interaction.
method Proposed a novel approach to derive Nash equilibrium semi-explicitly using operator resolvents and stochastic Fredholm equations.
result Equilibrium of the NN-player game converges to mean-field equilibrium, and ε\varepsilon-Nash equilibrium derived as a by-product.

The mean-field variant of the model of limit order driven market introduced recently by Maslov is formulated and solved. The agents do not have any strategies and the memory of the system is kept within the order book. We show that he evolution of the order book is governed by a matrix multiplicative process. The resul…

2001-04-27abs ↗pdf ↗

In this paper, we give an algebraic construction of the solution to the following mean field equation Δψ+eψ=4πi=12g+2δPi, Δψ+e^ψ=4π\sum_{i=1}^{2g+2}δ_{P_{i}}, on a genus g2g\geq 2 hyperelliptic curve (X,ds2)(X,ds^{2}) where ds2ds^{2} is a canonical metric on XX and {P1,,P2g+2}\{P_{1},\cdots,P_{2g+2}\} is the set of Weierstrass points on X.X. Furt…

2017-05-24abs ↗pdf ↗