arXiv research

Controller seeks informative system observations to predict nonlinear dynamics.

Graph neural controlled differential equations learn graph dynamics from vertex observations.

In stochastic control problems delicate issues arise when the controlled system can jump due to both exogenous shocks and endogenous controls. Here one has to specify what the controller knows when about the exogenous shocks and how and when she can act on this information. We propose to use Meyer-$σ$-fields as a flexi…

Paper formulates mutual information optimal control for discrete-time systems.

New method controls bias in training data for fair outcomes.

We investigated publicly reported security breaches of internal controls in corporate systems to determine whether SOX assessments are information bearing with respect to breaches which can lead to materially significant losses and misstatements. SOX Section 404 adverse decisions on effectiveness of controls occurred i…

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

AC-State discovers minimal latent state for control.

Bayesian PROCOVA uses AI to adjust for covariates in RCTs.

Develops methods to select informative conformal prediction sets with FCR control.

DART2 enhances multiple testing by leveraging ancillary information robustly.

We describe a novel extension of soft actor-critics for hierarchical Deep Q-Networks (HDQN) architectures using mutual information metric. The proposed extension provides a suitable framework for encouraging explorations in such hierarchical networks. A natural utilization of this framework is an adversarial setting, w…

A method for logistic regression inference using both internal and external data.

Estimates non-parametric logistic model using case-control data and external summary info.

We consider an investor faced with the utility maximization problem in which the risky asset price process has pure-jump dynamics affected by an unobservable continuous-time finite-state Markov chain, the intensity of which can also be controlled by actions of the investor. Using the classical filtering theory, we redu…

Policy optimization on high-dimensional continuous control tasks exhibits its difficulty caused by the large variance of the policy gradient estimators. We present the action subspace dependent gradient (ASDG) estimator which incorporates the Rao-Blackwell theorem (RB) and Control Variates (CV) into a unified framework…

In this paper, we utilize information theory to study the fundamental performance limitations of generic feedback systems, where both the controller and the plant may be any causal functions/mappings while the disturbance can be with any distributions. More specifically, we obtain fundamental $\mathcal{L}_p$ bounds on …

Investors pay for additional asset information based on utility maximization.

Physics-informed learning framework for pH systems and EB-PBC control.

Action-bisimulation learns long-horizon controllability for reinforcement learning.

New approach uses contrastive learning for better wireless power control.

GeoIB uses information geometry to control compression in deep learning models.

A new pricing controller handles resource constraints to infer target prices effectively.

A new active learning method for Gaussian process models.

GCVAE improves disentanglement in VAEs while balancing reconstruction error.

Meta-active learning optimizes control of safety-critical systems by efficiently learning dynamics and configurations.

Develops a method to plan exploration that learns strong policies with fewer samples.

NeurT-FDR controls FDR by incorporating feature hierarchy.

We study the optimal dividend problem for a firm's manager who has partial information on the profitability of the firm. The problem is formulated as one of singular stochastic control with partial information on the drift of the underlying process and with absorption. In the Markovian formulation, we have a 2-dimensio…

Graph neural networks improve topology control of power grids.

New causal measures improve feature selection in AI models.

Study utility indifference pricing with delayed investment information in a Bachelier model.

CPCMs integrate causal drivers for robust portfolio optimization.

A simple strategy optimizes broker-client trading, reducing price discounts for informed traders.

Industrial control systems are critical to the operation of industrial facilities, especially for critical infrastructures, such as refineries, power grids, and transportation systems. Similar to other information systems, a significant threat to industrial control systems is the attack from cyberspace---the offensive …

Attempts from different disciplines to provide a fundamental understanding of deep learning have advanced rapidly in recent years, yet a unified framework remains relatively limited. In this article, we provide one possible way to align existing branches of deep learning theory through the lens of dynamical system and …

Enhances quantum circuit synthesis using deep learning and geometric methods.

This paper presents a reinforcement learning approach to synthesizing task-driven control policies for robotic systems equipped with rich sensory modalities (e.g., vision or depth). Standard reinforcement learning algorithms typically produce policies that tightly couple control actions to the entirety of the system's …

PI-SAC agents learn predictive information to improve RL efficiency.

New framework controls generalization for heavy-tailed data in RLHF and SGLD.

Market makers optimize bid/ask quotes under hidden Markov chain uncertainty.

Study utility maximization with delayed information in continuous time Gaussian markets.

In reinforcement learning, an agent learns to reach a set of goals by means of an external reward signal. In the natural world, intelligent organisms learn from internal drives, bypassing the need for external signals, which is beneficial for a wide range of tasks. Motivated by this observation, we propose to formulate…

Unified control theory and machine learning for safety in uncertain systems.

In this paper we consider an energy storage optimization problem in finite time in a model with partial information that allows for a changing economic environment. The state process consists of the storage level controlled by the storage manager and the energy price process, which is a diffusion process the drift of w…

Designs adaptive controller for networked control systems with wireless data transmission.

Class-conditional generative models are crucial tools for data generation from user-specified class labels. Existing approaches for class-conditional generative models require nontrivial modifications of backbone generative architectures to model conditional information fed into the model. This paper introduces a plug-…

The paper tackles robust control with uncertain dependence using data-driven methods.