42 citations · 63 across the 11 of their papers we have counts for
12 papers
Global Optimality of Elman-type RNN in the Mean-Field Regime
Andrea Agazzi, Jianfeng Lu, Sayan Mukherjee
We analyze Elman-type Recurrent Reural Networks (RNNs) and their training in the mean-field regime. Specifically, we show convergence of gradient descent training dynamics of the R…
Random Splitting of Fluid Models: Positive Lyapunov Exponents
Andrea Agazzi, Jonathan C. Mattingly, Omar Melikechi
In this paper we give sufficient conditions for random splitting systems to have a positive top Lyapunov exponent. We verify these conditions for random splittings of two fluid mod…
Random Splitting of Fluid Models: Ergodicity and Convergence
Andrea Agazzi, Jonathan C. Mattingly, Omar Melikechi
We introduce a family of stochastic models motivated by the study of nonequilibrium steady states of fluid equations. These models decompose the deterministic dynamics of interest…
A homotopic approach to policy gradients for linear quadratic regulators with nonlinear controls
Craig Xu Chen, Andrea Agazzi
We study the convergence of deterministic policy gradient algorithms in continuous state and action space for the prototypical Linear Quadratic Regulator (LQR) problem when the sea…
Large deviations for Markov jump processes with uniformly diminishing rates
Andrea Agazzi, Luisa Andreis, Robert I. A. Patterson +1
We prove a large-deviation principle (LDP) for the sample paths of jump Markov processes in the small noise limit when, possibly, all the jump rates vanish uniformly, but slowly en…
Urgency-aware Optimal Routing in Repeated Games through Artificial Currencies
Mauro Salazar, Dario Paccagnan, Andrea Agazzi +2
When people choose routes minimizing their individual delay, the aggregate congestion can be much higher compared to that experienced by a centrally-imposed routing. Yet centralize…
Global optimality of softmax policy gradient with single hidden layer neural networks in the mean-field regime
Andrea Agazzi, Jianfeng Lu
We study the problem of policy optimization for infinite-horizon discounted Markov Decision Processes with softmax policy and nonlinear function approximation trained with policy g…
Temporal-difference learning with nonlinear function approximation: lazy training and mean field regimes
Andrea Agazzi, Jianfeng Lu
We discuss the approximation of the value function for infinite-horizon discounted Markov Reward Processes (MRP) with nonlinear functions trained with the Temporal-Difference (TD)…
Seemingly stable chemical kinetics can be stable, marginally stable, or unstable
Andrea Agazzi, Jonathan C. Mattingly
We present three examples of chemical reaction networks whose ordinary differential equation scaling limit are almost identical and in all cases stable. Nevertheless, the Markov ju…
On the geometry of chemical reaction networks: Lyapunov function and large deviations
Andrea Agazzi, Amir Dembo, Jean-Pierre Eckmann
In an earlier paper, we proved the validity of large deviations theory for the particle approximation of quite general chemical reaction networks (CRNs). In this paper, we extend i…
Large deviations theory for Markov jump models of chemical reaction networks
Andrea Agazzi, Amir Dembo, Jean-Pierre Eckmann
We prove a sample path Large Deviation Principle (LDP) for a class of jump processes whose rates are not uniformly Lipschitz continuous in phase space. Building on it we further es…
The Colored Hofstadter Butterfly for the Honeycomb Lattice
Andrea Agazzi, Jean-Pierre Eckmann, Gian Michele Graf
We rely on a recent method for determining edge spectra and we use it to compute the Chern numbers for Hofstadter models on the honeycomb lattice having rational magnetic flux per…