arXiv research

Method improves volatility targeting for index construction.

Study proposes a neural network approach for high inflation investment portfolios with leverage constraints.

Curriculum learning and imitation learning improve control over financial time-series data.

We present a simple agent-based model of a financial system composed of leveraged investors such as banks that invest in stocks and manage their risk using a Value-at-Risk constraint, based on historical observations of asset prices. The Value-at-Risk constraint implies that when perceived risk is low, leverage is high…

NeurT-FDR controls FDR by incorporating feature hierarchy.

Meta-CVs leverage task similarity to reduce variance with limited data.

DART2 enhances multiple testing by leveraging ancillary information robustly.

New method controls linear systems with partial info and disturbances.

We introduce a control-tutored reinforcement learning (CTRL) algorithm. The idea is to enhance tabular learning algorithms so as to improve the exploration of the state-space, and substantially reduce learning times by leveraging some limited knowledge of the plant encoded into a tutoring model-based control strategy. …

We study the constrained linear quadratic regulator with unknown dynamics, addressing the tension between safety and exploration in data-driven control techniques. We present a framework which allows for system identification through persistent excitation, while maintaining safety by guaranteeing the satisfaction of st…

Framework for controlling multiple risks in AI models.

ACSSM models irregular time series with continuous dynamics.

The paper tackles data-driven optimal control of unknown nonlinear systems using RKHS.

Deep learning solves complex stochastic control with jumps.

Computational Drug Repositioning (CDR) is the task of discovering potential new indications for existing drugs by mining large-scale heterogeneous drug-related data sources. Leveraging the patient-level temporal ordering information between numeric physiological measurements and various drug prescriptions provided in E…

Optimal control in changing systems without strong convexity assumptions.

Paper develops a novel approach for optimal control using kernel methods.

Improved confidence interval estimation with control variates.

Optimizes bank capital structure under Basel III constraints, simplifying complex dynamics.

New measure EC assesses node contributions in nonlinear, time-varying systems.

Paper uses DeePC to improve urban traffic lights, reducing congestion and emissions.

The paper analyzes optimal overbetting strategies for a satellite investment account.

We present HiDe, a novel hierarchical reinforcement learning architecture that successfully solves long horizon control tasks and generalizes to unseen test scenarios. Functional decomposition between planning and low-level control is achieved by explicitly separating the state-action spaces across the hierarchy, which…

Method predicts hardware resource usage by control software with guaranteed linear convergence.

Distribution grids are currently challenged by frequent voltage excursions induced by intermittent solar generation. Smart inverters have been advocated as a fast-responding means to regulate voltage and minimize ohmic losses. Since optimal inverter coordination may be computationally challenging and preset local contr…

Deep RL controller outperforms market making benchmarks in a Hawkes process model.

Two-stage risk control for ranked retrieval systems.

In this work, we propose a robust approach to design distributed controllers for unknown-but-sparse linear and time-invariant systems. By leveraging modern techniques in distributed controller synthesis and structured linear inverse problems as applied to system identification, we show that near-optimal distributed con…

Deep reinforcement learning controls drones without model knowledge.

New algorithm uses control variates to improve multi-armed bandit performance.

Bayesian PROCOVA uses AI to adjust for covariates in RCTs.

Bayesian optimisation tackles stochastic MPC hyper-parameter tuning.

New methods optimize transport and sampling for neural networks.

Value-based methods constitute a fundamental methodology in planning and deep reinforcement learning (RL). In this paper, we propose to exploit the underlying structures of the state-action value function, i.e., Q function, for both planning and deep RL. In particular, if the underlying system dynamics lead to some glo…

We consider adaptive control of the Linear Quadratic Regulator (LQR), where an unknown linear system is controlled subject to quadratic costs. Leveraging recent developments in the estimation of linear systems and in robust controller synthesis, we present the first provably polynomial time algorithm that provides high…

Finding optimal feedback controllers for nonlinear dynamic systems from data is hard. Recently, Bayesian optimization (BO) has been proposed as a powerful framework for direct controller tuning from experimental trials. For selecting the next query point and finding the global optimum, BO relies on a probabilistic desc…

New algorithm solves mean-field control problems using actor-critic learning with moment neural networks.

This work proposes a new method for simultaneous probabilistic identification and control of an observable, fully-actuated mechanical system. Identification is achieved by conditioning stochastic process priors on observations of configurations and noisy estimates of configuration derivatives. In contrast to previous w…

In many vision-based reinforcement learning (RL) problems, the agent controls a movable object in its visual field, e.g., the player's avatar in video games and the robotic arm in visual grasping and manipulation. Leveraging action-conditioned video prediction, we propose an end-to-end learning framework to disentangle…

A reinforcement learning approach prepares quantum squeezed states in open spin systems.

Develops a new model for controllable and realistic traffic simulation.

Study shows how to control jump-diffusion processes with stable feedback controls in reinforcement learning.

In modern portfolio theory, the balancing of expected returns on investments against uncertainties in those returns is aided by the use of utility functions. The Kelly criterion offers another approach, rooted in information theory, that always implies logarithmic utility. The two approaches seem incompatible, too loos…

Non-invasive myoelectric prostheses require a long training time to obtain satisfactory control dexterity. These training times could possibly be reduced by leveraging over training efforts by previous subjects. So-called domain adaptation algorithms formalize this strategy and have indeed been shown to significantly r…

CAD-DA controls anomaly detection under domain adaptation.

New estimator improves policy evaluation in resource allocation RCTs.

Paper proposes adaptive control for unknown systems using reinforcement learning.

Reinforcement Learning (RL) algorithms have found limited success beyond simulated applications, and one main reason is the absence of safety guarantees during the learning process. Real world systems would realistically fail or break before an optimal controller can be learned. To address this issue, we propose a cont…