arXiv research

Advocates a local feedback approach for RL in unknown systems.

Learning optimal feedback control laws capable of executing optimal trajectories is essential for many robotic applications. Such policies can be learned using reinforcement learning or planned using optimal control. While reinforcement learning is sample inefficient, optimal control only plans an optimal trajectory fr…

A new method steers Gaussian distributions with minimal effort.

Study tests feasibility of linear programs with bandit feedback.

Study shows Direct Feedback Alignment fails to offer more efficient scaling than backpropagation.

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 …

We introduce an autoregressive-type model of prices in financial market taking into account the self-modulation effect. We find that traders are mainly using strategies with weighted feedbacks of past prices. These feedbacks are responsible for the slow diffusion in short times, apparent trends and power law distributi…

Calibrates Hawkes models for market events, revealing power-law feedback kernels.

Algometrics analyzes how predictive models affect their own forecasts in algorithmic markets.

It is now well established empirically that financial price changes are distributed according to a power law, with cubic exponent. This is a fascinating regularity, as it holds for various classes of securities, on various markets, and on various time scales. The universality of this law suggests that there must be som…

Controlled interacting particle systems such as the ensemble Kalman filter (EnKF) and the feedback particle filter (FPF) are numerical algorithms to approximate the solution of the nonlinear filtering problem in continuous time. The distinguishing feature of these algorithms is that the Bayesian update step is implemen…

New insights into cascade feedback linearization of control systems.

Exact asymptotic solutions found for nonlinear Hawkes processes.

Study improves understanding and performance of FA learning rules in neural networks.

Browsing and finding relevant information for Bangladeshi laws is a challenge faced by all law students and researchers in Bangladesh, and by citizens who want to learn about any legal procedure. Some law archives in Bangladesh are digitized, but lack proper tools to organize the data meaningfully. We present a text vi…

We introduce an autoregressive-type model with self-modulation effects for a foreign exchange rate by separating the foreign exchange rate into a moving average rate and an uncorrelated noise. From this model we indicate that traders are mainly using strategies with weighted feedbacks of the past rates in the exchange …

Study scaling laws of reward model overoptimization in reinforcement learning.

In this paper we explain the wild fluctuations of financial prices from the intrinsic amplifying feedback of speculative supply and demand. Formally, we show that an asset return follows a multiplicative random growth with exogenous input, which is well-known to be a generic power-law generating process, and which coul…

Test for linearizing 2-input systems with 2D feedback.

Control Barrier Functions (CBF) have been recently utilized in the design of provably safe feedback control laws for nonlinear systems. These feedback control methods typically compute the next control input by solving an online Quadratic Program (QP). Solving QP in real-time can be a computationally expensive process …

New algorithm reduces regret in delayed feedback generalised linear bandits.

This paper explores a new form of the linear bandit problem in which the algorithm receives the usual stochastic rewards as well as stochastic feedback about which features are relevant to the rewards, the latter feedback being the novel aspect. The focus of this paper is the development of new theory and algorithms fo…

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

New algorithm controls linear systems with bandit feedback, achieving optimal regret.

Neural algorithms optimize arm selection with human preference feedback for complex reward functions.

Perfect tracking control for real-world Euler-Lagrange systems is challenging due to uncertainties in the system model and external disturbances. The magnitude of the tracking error can be reduced either by increasing the feedback gains or improving the model of the system. The latter is clearly preferable as it allows…

A new dual test for forward-flatness simplifies computations.

Paper studies CLO with partial feedback, improving decision-making in uncertain contexts.

LLT transforms time series features based on linear laws.

Easy conditions found for simplifying complex systems.

Scaling laws in linear regression explain model performance improvements with size and data.

By combining (i) the economic theory of rational expectation bubbles, (ii) behavioral finance on imitation and herding of investors and traders and (iii) the mathematical and statistical physics of bifurcations and phase transitions, the log-periodic power law (LPPL) model has been developed as a flexible tool to detec…

Improved scaling laws in linear regression using data reuse.

The paper studies symmetry reduction of control systems and its implications for feedback linearization.

A new algorithm for conversational recommendation systems using dueling bandits in GLMs.

Unified LP framework for offline reward learning from human demonstrations and feedback.

Proposes a new theoretical framework for PbRL that requires less human feedback.

FA algorithm provides convergence guarantees for deep linear networks.

Study absolute equivalence for Pfaffian systems, applying to control systems.

The paper tackles exact linearization and control of flat discrete-time systems.

Banker-OMD improves online learning with delayed feedback.

Neural ODEs control graph dynamics with low energy feedback.

Optimal control of stochastic nonlinear dynamical systems is a major challenge in the domain of robot learning. Given the intractability of the global control problem, state-of-the-art algorithms focus on approximate sequential optimization techniques, that heavily rely on heuristics for regularization in order to achi…

The paper tackles combinatorial pure exploration with various feedback structures and proposes efficient algorithms.

Paper finds linear laws in Bitcoin price changes, aiding anomaly detection.

New budget quantifies drift in closed-loop learning, improving reproducibility.

SignSGD outperforms SGD in linear regression with optimal scaling laws under PLRF model.

Geometric framework for dynamic feedback linearization of control systems with symmetry.