arXiv research

Framework for quantifying uncertainty in dynamic processes.

Study dynamics and topology of flows near non-saddle sets or W-sets.

This work extends set-valued risk measures to discrete time, using difference inclusions and equations.

The paper explores dynamic regret with switching cost in online decision making.

GDM models time series with smoother transitions and interpretable states.

SPICE estimates sparse linear dynamic networks without hyperparameters.

In this paper, we prove a limit set intersection theorem in relatively hyperbolic groups. Our approach is based on a study of dynamical quasiconvexity of relatively quasiconvex subgroups. Using dynamical quasiconvexity, many well-known results on limit sets of geometrically finite Kleinian groups are derived in general…

Proposes a method to learn stable invariant sets in dynamical systems.

Study best-response learning dynamics in zero-sum polymatrix games under full and minimal information settings.

Paper studies generic dynamics of MCFs with spherical singularities.

This paper gives an overview of the theory of dynamic convex risk measures for random variables in discrete time setting. We summarize robust representation results of conditional convex risk measures, and we characterize various time consistency properties of dynamic risk measures in terms of acceptance sets, penalty …

In this paper we propose the notion of dynamic deviation measure, as a dynamic time-consistent extension of the (static) notion of deviation measure. To achieve time-consistency we require that a dynamic deviation measures satisfies a generalised conditional variance formula. We show that, under a domination condition,…

We investigate the random dynamics of polynomial maps on the Riemann sphere and the dynamics of semigroups of polynomial maps on the Riemann sphere. In particular, the dynamics of a semigroup $G$ of polynomials whose planar postcritical set is bounded and the associated random dynamics are studied. In general, the Juli…

This paper demonstrates dynamic hyper-parameter setting, for deep neural network training, using Mutual Information (MI). The specific hyper-parameter studied in this paper is the learning rate. MI between the output layer and true outcomes is used to dynamically set the learning rate of the network through the trainin…

DADI framework dynamically discovers fair information using reinforcement learning.

Extends super-replication theorem with dynamic strategies and transaction costs.

The article discusses invariant measures outside homogeneous dynamics.

Study homeomorphisms on fine curve graph of surfaces, revealing new types of dynamics.

Neural networks compress and sample WDN contamination dynamics efficiently.

Study analyzes stock market dynamics using recurrence measures and transitions.

Valid prediction sets for dynamic graphs using conformal prediction.

Guaranteed reachable set for unknown nonlinear systems on manifolds.

New algorithm reduces dynamic regret in time-varying movement costs.

The paper studies random dynamical systems of polynomial automorphisms on C^2 and finds mean stability.

Formulates Markov property for risk-sensitive dynamic optimisation.

Study on learning to predict dynamical systems without assuming their structure.

Paper tackles dynamic pricing in a geometrically decaying environment, achieving better occupancy with lower rates.

In this paper we present a theoretical framework for studying coherent acceptability indices in a dynamic setup. We study dynamic coherent acceptability indices and dynamic coherent risk measures, and we establish a duality between them. We derive a representation theorem for dynamic coherent risk measures in terms of …

Study dynamics of automorphisms on cubic surfaces and their connection to Painlevé 6.

Paper tackles reinforcement learning with complex observations and simple latent dynamics.

Many complex dynamical phenomena can be effectively modeled by a system that switches among a set of conditionally linear dynamical modes. We consider two such models: the switching linear dynamical system (SLDS) and the switching vector autoregressive (VAR) process. Our Bayesian nonparametric approach utilizes a hiera…

New algorithm reduces sample complexity for online reinforcement learning.

Paper uses DRL for dynamic pricing on e-commerce platforms.

Study risk-controlling prediction sets for single trajectory data from dynamical systems.

Develops a dynamic mean field theory for reinforcement learning.

Characterizes convex cocompact actions in projective space with dynamical properties.

This paper introduces a linear state-space model with time-varying dynamics. The time dependency is obtained by forming the state dynamics matrix as a time-varying linear combination of a set of matrices. The time dependency of the weights in the linear combination is modelled by another linear Gaussian dynamical model…

Different approaches to defining dynamic market risk measures are available in the literature. Most are focused or derived from probability theory, economic behavior or dynamic programming. Here, we propose an approach to define and implement dynamic market risk measures based on recursion and state economy representat…

Pairs (Hamiltonian system, Lagrangian distribution), called dynamical Lagrangian distributions, appear naturally in Differential Geometry, Calculus of Variations and Rational Mechanics. The basic differential invariants of a dynamical Lagrangian distribution w.r.t. the action of the group of symplectomorphisms of the a…

Safe learning of stochastic dynamics with safety constraints.

Algorithm selects best model based on state, reducing costs.

Study connects bank default models using dynamic contagion.

Algorithm learns optimal dynamic mechanisms from data.

Abstract: Deltoid map connects complex dynamics and algebra.

In this paper, we study online convex optimization in dynamic environments, and aim to bound the dynamic regret with respect to any sequence of comparators. Existing work have shown that online gradient descent enjoys an $O(\sqrt{T}(1+P_T))$ dynamic regret, where $T$ is the number of iterations and $P_T$ is the path-le…

Method learns dynamics of slow variables from stochastic data.

Set-Sequence model learns cross-sectional dynamics directly from time series data.

Study optimal control in unknown nonlinear systems with near-optimal regret bound.