arXiv research

New method learns time-invariant rewards from demonstrations.

SPAQL improves RL by adaptively partitioning state-action space and learning a time-invariant policy.

New findings on universal learning in contextual bandits with adversarial rewards.

New algorithm tackles multi-agent bandits with heavy-tailed data.

Study reveals how travel times on cylindrical boundaries can identify spacetime structure.

Evolution of planar curves under a nonlocal geometric equation is investigated. It models the simultaneous contraction and growth of carbonate particles called ooids in geosciences. Using classical ODE results and a bijective mapping we demonstrate that the steady parameters associated with the physical environment det…

Paper proposes a method for learning and planning in time-varying environments.

Paper tests if beta coefficients in AMF model are consistent over time.

New algorithm models satiation in recommender systems.

New algorithm achieves consistent learning from context in bandit problems.

A method for learning with autoregressive chain-of-thoughts.

We build a simple diagnostic criterion for approximate factor structure in large cross-sectional equity datasets. Given a model for asset returns with observable factors, the criterion checks whether the error terms are weakly cross-sectionally correlated or share at least one unobservable common factor. It only requir…

The paper introduces a new method to assess system stability using torsion of state trajectories.

New test uncovers causal links in rare event dynamics.

The focal point of this paper is the issue of "drawdown" which arises in recursive betting scenarios and related applications in the stock market. Roughly speaking, drawdown is understood to mean drops in wealth over time from peaks to subsequent lows. Motivated by the fact that this issue is of paramount concern to co…

Dynamic portfolio strategy using generative model with attention mechanism.

Paper derives an error bound for stochastic LTI systems.

New scalable MARL framework for dynamic networked systems.

The paper tackles joint learning of linear systems, improving accuracy with pooled data.

This paper combines RL with CPPI and TIPP for better trading strategies.

Paper tackles temporal overfitting in wind power curve modeling.

Ensemble++ uses shared-factor ensembles to scale Thompson Sampling for linear and nonlinear bandits.

KKR uses Koopman theory to improve forecasting in complex systems.

This paper focuses on using the first curvature $κ(t)$ of trajectory to describe the stability of linear time-invariant system. We extend the results for two and three-dimensional systems [Y. Wang, H. Sun, Y. Song et al., arXiv:1808.00290] to $n$-dimensional systems. We prove that for a system $\dot{r}(t)=Ar(t)$, (i) i…

ForecastNet uses a time-variant deep feed-forward neural network for better multi-step-ahead time series forecasting.

New model stabilizes asynchronous LTI systems, independent of synchronous stability.

We provide a brief tutorial on the use of concentration inequalities as they apply to system identification of state-space parameters of linear time invariant systems, with a focus on the fully observed setting. We draw upon tools from the theories of large-deviations and self-normalized martingales, and provide both d…

This work represents an application of constant mean curvature graphs (as solutions of the mean curvature PDE) to non-linear non-Darcy flows in porous media. It relates time invariant pressure distribution graphs to graphs of constant mean curvature surfaces. This differential geometric interpretation provides an impor…

AR model forecasts partially observed dynamical time series by estimating evolution function and imputing missing variables.

Study static Einstein-Maxwell space invariant by translation.

Off-policy evaluation (OPE) in reinforcement learning is notoriously difficult in long- and infinite-horizon settings due to diminishing overlap between behavior and target policies. In this paper, we study the role of Markovian and time-invariant structure in efficient OPE. We first derive the efficiency bounds for OP…

Proposes a method to prove closing of periodic orbits in dynamical systems.

This paper proposes an active sampling method for meta-learning using MDPs.

Autoencoder detects subtle changes in time series data.

We prove that stochastic gradient descent efficiently converges to the global optimizer of the maximum likelihood objective of an unknown linear time-invariant dynamical system from a sequence of noisy observations generated by the system. Even though the objective function is non-convex, we provide polynomial running …

In this paper we construct the differential equations of the stream lines that characterize plasma regarded as a non-isotropic medium geometrized by a jet rheonomic time-invariant Berwald-Moor metric. Section 1 contains historical notes regarding the Plasma Physics and its geometrical description. Section 2 analyzes th…

New method calibrates asynchronous, error-prone covariates for longitudinal data.

Improved speech separation and enhancement using neural beamforming.

We study the problem of controlling linear time-invariant systems with known noisy dynamics and adversarially chosen quadratic losses. We present the first efficient online learning algorithms in this setting that guarantee $O(\sqrt{T})$ regret under mild assumptions, where $T$ is the time horizon. Our algorithms rely …

Neural ordinary differential equations (ODEs) have been attracting increasing attention in various research domains recently. There have been some works studying optimization issues and approximation capabilities of neural ODEs, but their robustness is still yet unclear. In this work, we fill this important gap by expl…

We consider the problem of learning a realization for a linear time-invariant (LTI) dynamical system from input/output data. Given a single input/output trajectory, we provide finite time analysis for learning the system's Markov parameters, from which a balanced realization is obtained using the classical Ho-Kalman al…

A dynamical system can be regarded as an information processing apparatus that encodes input streams from the external environment to its state and processes them through state transitions. The information processing capacity (IPC) is an excellent tool that comprehensively evaluates these processed inputs, providing de…

Study constructs solutions for evolving hypersurfaces using inverse spacetime mean curvature.

Reward hacking exploits misspecified rewards, affecting agent capabilities and true performance.

Over the past few years, we developed a mathematically rigorous method to study the dynamical processes associated to nonlinear Forchheimer flows for slightly compressible fluids. We have proved the existence of a geometric transformation which relates constant mean curvature surfaces and time-invariant pressure distri…

Paper introduces PRMs to learn non-Markovian stochastic rewards for reinforcement learning.

This work analyzes the value of future reward information in RL.

We develop a cross-sectional research design to identify causal effects in the presence of unobservable heterogeneity without instruments. When units are dense in physical space, it may be sufficient to regress the "spatial first differences" (SFD) of the outcome on the treatment and omit all covariates. The identifyin…