We consider a new form of reinforcement learning (RL) that is based on opportunities to directly learn the optimal control policy and a general Markov decision process (MDP) framework devised to support these opportunities. Derivations of general classes of our control-based RL methods are presented, together with form…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,657 papers · 148 categories
Trend · papers per month
48 results for “Control Framework”
A framework integrates machine learning with robust control for safer, more reliable systems.
problem Combining machine learning with robust control for systems with stringent safety and reliability requirements.
method Integrates Gaussian Process Regression and state-of-the-art robust controller synthesis within a framework that provides rigorous guarantees.
result Demonstrated improved performance with more data while maintaining rigorous guarantees.
FinFlowRL: An Imitation-Reinforcement Learning Framework for Adaptive Stochastic Control in Financeq-fin.CP
FinFlowRL learns from experts to optimize financial control in changing markets.
problem Traditional finance control methods fail in real-world, non-stationary markets.
method Imitation-Reinforcement Learning framework that pretrains on expert strategies and finetunes in noise space.
result Consistently outperforms individually optimized experts across diverse market conditions.
Optimizes control interventions in real-world networks using deep-learning and network science.
problem Optimizing control over socioeconomic networks subject to constraints.
method Integrates optimization tools from deep-learning with network science.
result Characterizes vulnerability of corporate networks to takeovers.
Framework calibrates ML models for risk control in various tasks.
problem Achieving statistical guarantees for model predictions.
method Reframing risk control as multiple hypothesis testing, applying statistical techniques.
result New calibration methods for multi-label classification, instance segmentation, outlier detection, and confidence set coverage.
NewtonianVAE: Proportional Control and Goal Identification from Pixels via Physical Latent Spacescs.LG
Framework simplifies vision-based control and goal discovery.
problem Learning proportional control from visual data.
method Introduces NewtonianVAE for proportional control and goal discovery.
result Dramatic simplification and acceleration of vision-based controllers.
LineFlow is a framework for training RL agents to control production lines.
problem Designing control systems for production lines is challenging.
method Introduces LineFlow, an extensible Python framework for simulating and training RL agents.
result RL agents approach optimal performance in well-understood scenarios but face challenges in complex industrial lines.
New framework for policy gradient methods in continuous time reinforcement learning.
problem Addressing policy gradient methods for continuous time reinforcement learning.
method Control randomisation technique to derive policy gradient representation for various Markovian control problems.
result Demonstrated application to optimal switching problems in the energy sector.
There are over 15 distinct communities that work in the general area of sequential decisions and information, often referred to as decisions under uncertainty or stochastic optimization. We focus on two of the most important fields: stochastic optimal control, with its roots in deterministic optimal control, and reinfo…
Physics-informed learning framework for pH systems and EB-PBC control.
problem Control of port-Hamiltonian systems from trajectory data.
method Co-learning of pH system model and EB-PBC through alternating optimization.
result Proven stability and robustness of the learned controller.
Novel Bayesian meta-reinforcement learning framework improves traffic signal control robustness.
problem Lack of robustness and stability in adaptation for traffic signal control.
method Value-based Bayesian meta-reinforcement learning framework BM-DQN with fast-adaptation variation and DQN fast-update advantage.
result Framework adapts more quickly and robustly to new scenarios than previous methods.
Unified framework for FDR control in knockoffs, validating Gaussian knockoffs.
problem Asymptotic FDR control in knockoffs with user-specified distributions.
method Unified theoretical framework, three conditions on approximate knockoff statistics, Gaussian knockoffs generator based on moments matching.
result Gaussian knockoffs generator achieves asymptotic FDR control.
Framework for estimating treatment effects using external control data.
problem Improving efficiency in estimating average treatment effects (ATE) in hybrid trials.
method Developed a formal causal inference framework based on exchangeability assumptions and graphical criteria. Proposed estimators and efficient doubly-robust methods.
result Established finite-sample performance and demonstrated application to spinal muscular atrophy trial.
Just as an explicit parameterisation of system dynamics by state, i.e., a choice of coordinates, can impede the identification of general structure, so it is too with an explicit parameterisation of system dynamics by control. However, such explicit and fixed parameterisation by control is commonplace in control theory…
GAICF proposes a framework for governing generative AI in banking.
problem Generative AI's impact on financial decision-making and governance.
method SR 26-2-compatible governance framework for generative AI applications.
result GAICF aligns generative AI practices with SR 26-2 supervisory expectations.
Novel framework controls FDR in high-dimensional, dependent data.
problem FDR control failure in high-dimensional, dependent data.
method Dependency-aware T-Rex selector integrating hierarchical graphical models and martingale theory.
result First to control FDR in high-dimensional, dependent data.
A new framework for generative modeling using controlled vector fields.
problem Expressive modeling with limited parameters.
method Continuous-time modeling with modulated fixed vector fields and learned scalar controls.
result Expressive transport achieved with a small number of learned control channels.
This work frames active inference through control as inference, offering robust control algorithms.
problem Active inference framework lacks practical sensorimotor control algorithms.
method Frame active inference through control as inference, presenting trajectory optimization as inference.
result AI may be framed as partially-observed CaI when the cost function is defined in observation states.
FinFlowRL: An Imitation-Reinforcement Learning Framework for Adaptive Stochastic Control in Financeq-fin.CP
FinFlowRL combines imitation and reinforcement learning for better financial control.
problem Traditional stochastic control methods fail in real-world finance due to changing market conditions.
method FinFlowRL uses imitation learning to pretrain an adaptive meta policy, then finetunes it with reinforcement learning.
result FinFlowRL consistently outperforms individual strategies across various market conditions.
New framework for Bayesian inference using neural Schrödinger-Föllmer flows.
problem Approximate Bayesian inference in large datasets.
method Stochastic control, Schrödinger bridges, SDE-based models.
result Advocates stochastic control as a finite time and low variance alternative to SGLD.
Extended mean-field games with multi-dimensional singular controls and non-linear jump impactmath.OC
New framework for analyzing games with multi-dimensional singular controls and non-linear jumps.
problem Analyzing games with multi-dimensional singular controls and non-linear jump impacts.
method Probabilistic framework with novel class of MFGs (MFGs of parametrisations).
result Existence of equilibria and equivalence with MFGs of singular controls.
New method solves nonseparable stochastic control problems.
problem Nonseparable and non-monotonic stochastic control problems.
method Scenario-decomposition solution framework using progressive hedging algorithm.
result Extends reach of stochastic optimal control.
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…
GAICF proposes a framework for managing generative AI risks in banking.
problem Generative AI's impact on financial decision-making and governance.
method SR 26-2-compatible governance framework for generative AI.
result GAICF aligns generative AI practices with SR 26-2 supervisory expectations.
Paper uses VAEs to control IVS features for financial modeling.
problem Generating realistic IVSs with desired characteristics.
method Variational autoencoder architecture with controllable latent variables.
result Controlled generation of IVSs with specified features.
Agents acting in the natural world aim at selecting appropriate actions based on noisy and partial sensory observations. Many behaviors leading to decision mak- ing and action selection in a closed loop setting are naturally phrased within a control theoretic framework. Within the framework of optimal Control Theory, o…
Paper introduces a method to control early classification accuracy gaps.
problem Maintaining accuracy in early classification without full input processing.
method Statistical framework for a calibrated stopping rule.
result Reduces up to 94% of timesteps while controlling accuracy gaps.
Develops a control framework for systemic risk under uncertainty.
problem Systemic risk under model uncertainty.
method Linear-quadratic mean-field control framework with viscosity solutions and verification theorems.
result Explicit feedback controls derived from a coupled Riccati system, preserving analytical tractability.
Geometric framework for dynamic feedback linearization of control systems with symmetry.
problem Dynamic feedback linearization of control systems with symmetry.
method Geometric framework based on Lie symmetry, systematic procedure for all smooth, generic system trajectories.
result Sufficient condition for dynamic feedback linearizability obtained.
Nonlinear optimal control problems are often solved with numerical methods that require knowledge of system's dynamics which may be difficult to infer, and that carry a large computational cost associated with iterative calculations. We present a novel neurobiologically inspired hierarchical learning framework, Reinfor…
Paper develops a novel approach for optimal control using kernel methods.
problem Optimal control of nonlinear stochastic systems.
method Infinitesimal generator approach in reproducing kernel Hilbert spaces.
result Data-driven solution to optimal control problems.
Controller-Augmented Hidden Markov Models (CHMMs) are a framework for constrained sequential inference.
problem Hidden Markov models fail under pathwise constraints like precedence, visitation, or monotonic state progression.
method CHMMs compile constraints into finite-state controllers, then use standard forward-backward and Viterbi recursions to compute exact constrained posteriors and paths.
result CHMMs provide exact constrained inference, monotone ascent in constrained EM, and linear complexity in controller cardinality.
We study the question of how to aggregate controllers for dynamical systems in order to improve their performance. To this end, we propose a framework of boosting for online control. Our main result is an efficient boosting algorithm that combines weak controllers into a provably more accurate one. Empirical evaluation…
New framework calibrates models to control risk under performativity.
problem Calibrating models to ensure reliable decision-making under performativity.
method Iteratively refined calibration process for different risk measures and tail bounds.
result Statistically rigorous risk control under performativity demonstrated.
ACS is an interactive framework for model-free selection with guaranteed error control.
problem Model-free selection with rigorous error control.
method Adaptive conformal selection with human-in-the-loop data exploration and new information incorporation.
result ACS provides concrete selection algorithms for various goals, including model update/selection, diversified selection, and incorporating new data.
We study the inverse optimal control problem in social sciences: we aim at learning a user's true cost function from the observed temporal behavior. In contrast to traditional phenomenological works that aim to learn a generative model to fit the behavioral data, we propose a novel variational principle and treat user …
New control methods for systems with adversarial perturbations.
problem Control systems with adversarial noise.
method Online convex optimization and convex relaxations.
result Low regret policies against adversarial perturbations.
Finite resources limit false discovery rate control in structured hypothesis spaces.
problem Controlling false discovery rate in hypothesis testing with finite data and structured hypothesis spaces.
method Framework for exact FDR control and adaptive power maximization.
result Exact FDR control and adaptive power maximization.
New framework for online control in evolving populations.
problem Control of evolving populations in real-world conditions.
method Online control framework for linear and non-linear dynamical systems.
result Near-optimal regret bounds for gradient-based controllers.
Improves risk control in predictions using semi-supervised calibration.
problem Noisy hyper-parameter tuning from limited labeled data.
method Semi-supervised calibration using unlabeled data to tune hyper-parameters rigorously.
result Improves prediction accuracy without sacrificing statistical validity.
A new framework for controllable generation of discrete masked models.
problem Efficient controllable generation of discrete data models.
method Plug-and-play framework based on importance sampling.
result Demonstrates versatility across multiple domains, including protein design.
Optimal control of affine connection control systems from the point of view of Lie algebroidsmath.OC
The purpose of this paper is to use the framework of Lie algebroids to study optimal control problems for affine connection control systems on Lie groups. In this context, the equations for critical trajectories of the problem are geometrically characterized as a Hamiltonian vector field.
Energy-Based In-Domain Control and Observer Design for Infinite-Dimensional Port-Hamiltonian Systemsmath.OC
In this paper, we consider infinite-dimensional port-Hamiltonian systems with in-domain actuation by means of an approach based on Stokes-Dirac structures as well as in a framework that exploits an underlying jet-bundle structure. In both frameworks, a dynamic controller based on the energy-Casimir method is derived in…
A new framework uses stochastic optimal control to estimate rare events more accurately.
problem Estimating rare events like chemical reactions in biomolecules is computationally challenging.
method The approach casts committor estimation as a stochastic optimal control problem, developing direct and off-policy Value Matching losses.
result The framework yields more accurate committor estimates, reaction rates, and equilibrium constants.
Researchers develop a new framework to control neural network sensitivity.
problem Understanding and controlling the behavior of neural networks.
method Direct parameterization of bi-Lipschitzness in convex neural networks.
result A clear and tight control of neural network sensitivity achieved.
Investigates optimal strategies for behavioral control problems with finite variation controls.
problem Behavioral singular stochastic control problems with finite variation controls.
method Abstract framework, applied to storage management and portfolio investment problems, using CPT preferences and Skorokhod representation theorem.
result Existence of optimal strategies for various goal functionals, including CPT preferences.
Control of non-episodic, finite-horizon dynamical systems with uncertain dynamics poses a tough and elementary case of the exploration-exploitation trade-off. Bayesian reinforcement learning, reasoning about the effect of actions and future observations, offers a principled solution, but is intractable. We review, then…
Bayesian optimisation tackles stochastic MPC hyper-parameter tuning.
problem Fine-tuning hyper-parameters in stochastic MPC models.
method Heteroscedastic Bayesian optimisation framework.
result Framework effectively tunes hyper-parameters in control problems.