Uniform-in-time analysis for Stein Variational Gradient Descent across various metrics.
problem Understanding long-term behavior of finite-particle systems in relation to their mean-field limits.
method Developed uniform-in-time propagation-of-chaos results for continuous-time SVGD using cutoff strategies and finite-dimensional theories.
result Uniform-in-time propagation-of-chaos bounds in various metrics, including Langevin kernel Stein discrepancy, Wasserstein-1, and Wasserstein-2 distances.
A new stochastic algorithm approximates optimal distributions without requiring propagation of chaos.
problem Optimizing functionals over probability distributions using finite particle systems.
method Virtual particle stochastic approximation, viewed as a form of stochastic gradient descent in the Wasserstein space.
result The algorithm's output converges to the optimal distribution and produces i.i.d. samples.
Existence of calibrated local stochastic volatility models proven for non-regular coefficients.
problem Existence of calibrated local stochastic volatility models in finance.
method Investigation of McKean--Vlasov equations with minimal continuity assumptions on coefficients, providing existence and propagation of chaos results.
result Existence of calibrated local stochastic volatility models for appropriate stochastic volatility parameters.
Study shows uniform-time chaos propagation in mean field Langevin dynamics.
problem Understanding the convergence of marginal distributions in mean field dynamics.
method Assumed functional convexity of energy, used Lp-convergence and Wasserstein metrics. result Uniform-in-time propagation of chaos proved in both L2-Wasserstein and relative entropy. Improved PoC for MFLD reduces approximation error and provides model ensemble guarantees.
problem Quantifying optimization complexity in mean-field Langevin dynamics.
method Refined defective log-Sobolev inequality for neural network training.
result Improved PoC result with reduced approximation error and theoretical model ensemble guarantees.
This work develops a particle system to approximate Fisher-Rao gradient flows in mean-field optimization.
problem Optimizing probability measures in neural network contexts.
method Constructing an interacting particle system approximating Fisher-Rao gradient flows.
result Propagation of chaos for the Fisher-Rao gradient flow in entropic mean-field optimization.
Study shows how SGD in large neural networks behaves as neurons increase.
problem Understanding SGD behavior in overparameterized neural networks.
method Probabilistic approach to continuous-time dynamics of SGD, focusing on particle interactions.
result Particles' interactions asymptotically vanish, leading to a mean-field limit.
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.
Proves existence and uniqueness of calibrated LSV model.
problem Calibrating a local stochastic volatility model to market data.
method Proves strong existence and uniqueness of solution to a McKean-Vlasov SDE.
result Establishes well-posedness of a calibrated two-factor LSV model.
New algorithm for solving minimax problems over distributions converges to Nash equilibrium.
problem Solving minimax problems over probability distributions.
method Symmetric Mean-field Langevin Dynamics (MFL-AG and MFL-ABR) with weighted averaging and best response dynamics.
result Converges to mixed Nash equilibrium with average-iterate and last-iterate convergence.
Develops a framework for analyzing neural networks and ODE models using control theory.
problem Analyzing deep neural networks and neural ODE models trained with stochastic gradient algorithms.
method Identifies connections between control theory, deep learning, and statistical sampling; derives Pontryagin's optimality principle and Mean-Field Langevin dynamics.
result Derives explicit convergence rates and provides quantitive bounds on generalization error, showing dimension-independent rates.
Novel RKHS approach solves complex financial model equations.
problem Calibrating singular local stochastic volatility models.
method Reproducing Kernel Hilbert Space (RKHS) regularization.
result Regularized model is well-posed and replicates option prices.
Improved sampling from complex distributions with reduced bias.
problem Reducing bias in high-dimensional sampling algorithms.
method Hierarchical entropy analysis to weaken assumptions and expand scope.
result Bias reduction in low-dimensional marginals scales with lower dimension, not full dimension.
Uniform bounds for neural network convergence without strong convexity assumptions.
problem Understanding the convergence of neural networks in the feature-learning regime.
method Establishing uniform-in-time weak propagation-of-chaos via mean-field deterministic Wasserstein-gradient-flow dynamics.
result Uniform bounds on the difference between infinite-width and finite-width neural network outputs, showing that fewer neurons can achieve a desired loss.
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.
The paper analyzes arbitrage opportunities in a large investor market with common stock noises.
problem Identifying arbitrage opportunities in a market with many competitive investors.
method Stochastic differential games and mean-field systems to study market dynamics and optimal arbitrage.
result Optimal arbitrage is characterized by a solution to a Cauchy PDE involving volatility terms.
Nonlinear MCMC improves Bayesian machine learning sampling.
problem Sampling problems in Bayesian machine learning.
method Nonlinear MCMC technique with convergence guarantees.
result Improves sampling in Bayesian neural networks.
Improved convergence rates for MFLD in various gradient estimators.
problem Proving convergence rates for mean-field Langevin dynamics with stochastic gradient updates.
method General framework for propagation of chaos, including finite-particle approximation, time-discretization, and stochastic gradient approximation.
result Improved convergence rates for SGD and SVRG settings.
Study simulates Heston-type local stochastic volatility model using particle method.
problem Simulate calibrated Heston-type local stochastic volatility model with non-standard coefficients.
method Monte Carlo particle method, Euler-Maruyama scheme, full truncation Euler scheme.
result Strong convergence of Euler-Maruyama scheme with rate 1/2 in time, up to a logarithmic factor.
New SGD variant makes neural networks compressible without assumptions.
problem Improving neural network compressibility without strong assumptions.
method Introducing heavy-tailed noise to SGD iterates.
result Compressible outputs with high probability for any compression rate.
We contribute to the understanding of how systemic risk arises in a network of credit-interlinked agents. Motivated by empirical studies we formulate a network model which, despite its simplicity, depicts the nature of interbank markets better than a homogeneous model. The components of a vector Ornstein-Uhlenbeck proc…
We consider systems of diffusion processes ("particles") interacting through their ranks (also referred to as "rank-based models" in the mathematical finance literature). We show that, as the number of particles becomes large, the process of fluctuations of the empirical cumulative distribution functions converges to t…
ResNets converge to a limit model with improved error rates.
problem Understanding convergence of ResNets in the large-scale limit.
method Combining cavity method and propagation of chaos arguments on skeleton maps.
result Convergence rate of O(1/sqrt(D)) for ResNets in the large-scale limit.
Study controlled contagion with state-dependent killing, proving a comparison principle.
problem Analyzing controlled McKean--Vlasov contagion with state-dependent killing.
method Proof of a comparison principle using Wasserstein smooth-gauge comparison and killing-jump absorption estimates.
result Established a comparison principle for the two-population killed-particle HJB.
The paper studies how noise synchronizes tokens in deep transformer models.
problem Understanding synchronization in deep learning models with noise.
method Proves convergence to a stochastic particle system and identifies the limiting SDE.
result The limiting model displays synchronization by noise and exponential dissipation of interaction energy.
Extends Langevin dynamics for constrained domains.
problem Optimization of constrained probability measures.
method Mirror mean-field Langevin dynamics (MMFLD).
result Linear convergence guarantees and propagation of chaos results.
Improved sampling from mean-field stationary distributions.
problem Sampling from the stationary distribution of mean-field SDEs.
method Decoupling the problem into two aspects: approximation of mean-field SDE and sampling from finite-particle distribution.
result Improved guarantees in various settings, including optimizing neural networks.
The paper studies stochastic optimization on matrices and its limits as dimensions grow.
problem Optimizing functions on large symmetric matrices using stochastic gradient descent.
method Deterministic limits of random curves on matrices, using graphons and stochastic differential equations.
result The limit is a gradient flow on graphons, extending classical McKean-Vlasov limits.
Study shows polynomial-width neural networks can closely approximate infinite-width networks in polynomial time.
problem Approximating dynamics of polynomial-width neural networks with infinite-width networks.
method Bounding approximation gap through a differential equation governed by mean-field dynamics, considering local Hessian.
result Polynomially many neurons are sufficient to closely approximate mean-field dynamics.
New method solves supercooled Stefan problem, proving minimal solutions are physical.
problem Evolution of solid-liquid boundary in substances below freezing point.
method Construct solutions through McKean-Vlasov equation, proving tightness and propagation of chaos.
result Minimal solutions of McKean-Vlasov equation are physical under integrable initial conditions.
Motivated by a probabilistic approach to Kahler-Einstein metrics we consider a general non-equilibrium statistical mechanics model in Euclidean space consisting of the stochastic gradient flow of a given (possibly singular) quasi-convex N-particle interaction energy. We show that a deterministic "macroscopic" evolution…
PVI improves SIVI by directly optimizing ELBO without parametric assumptions.
problem Intractable variational densities in SIVI methods.
method Particle Variational Inference (PVI) using empirical measures to approximate optimal mixing distributions.
result PVI directly optimizes the ELBO and performs favorably compared to other SIVI methods.
Study optimal investment in large populations of competitive, heterogeneous agents.
problem Maximizing utility in a large, interacting agent system with relative performance concerns.
method Analyzes stochastic utility maximization game in finite and infinite agent settings, using graphon models and backward stochastic differential equations.
result Convergence of Nash equilibria and optimal utilities from finite to infinite agent models under specific conditions.
Improved convergence rates for Stein Variational Gradient Descent in finite-particle settings.
problem Improving convergence rates for Stein Variational Gradient Descent in finite-particle settings.
method Analyzing the time derivative of relative entropy and splitting it into dominant and smaller parts.
result Finite-particle convergence rates of order 1/\sqrt{N} for Kernelized Stein Discrepancy and Wasserstein-2 metrics.
Framework for robust control in cooperative systems with uncertain common noise.
problem Optimizing collective behavior of agents in the presence of uncertain common noise.
method Proposes a robust mean-field control framework and proves existence of optimal controls.
result Existence of optimal open-loop controls linked to a lifted robust Markov decision problem.
Develops a mean-field theory for multi-head self-attention under cross-entropy training.
problem Mean-field analysis of multi-head self-attention under cross-entropy training.
method Mean-field theory for a simplified single-layer causal multi-head self-attention model.
result Proves a static finite-head approximation bound for the optimal risk.
Paper formulates EnKF as optimal transport problem for unique control law.
problem Unique control law for EnKF algorithms.
method Formulated as optimal transportation problem, derived explicit control law.
result Mean squared error converges to zero with finite particles.
Develops a gradient flow for Muon optimizer, a method for optimization.
problem Optimization of complex systems with matrix-valued parameters.
method Gradient flow on probability measures induced by regularized Muon optimizer.
result Derives continuous-time limits and proves Hamiltonian dissipation.
Wide neural networks learn features under μP, identifying weights and decomposing support.
problem Feature learning in wide neural networks under μP. method Proving mean-field limit, characterizing identifiability, sparse-dictionary decomposition, and feature-learning-error decomposition.
result The triple (w∗,Dorb∗,S∗) identifies the natural learning cell of the architecture-data pair (σ,ρ).