arXiv research

Deep learning models generate music with arbitrary control strategies.

e-LOND algorithm controls FDR in online testing with arbitrary dependencies.

Hybrid controller combines model-based and policy-based reinforcement learning.

We are given a video of a person performing a certain activity, from which we extract a controllable model. The model generates novel image sequences of that person, according to arbitrary user-defined control signals, typically marking the displacement of the moving body. The generated video can have an arbitrary back…

We develop a method for user-controllable semantic image inpainting: Given an arbitrary set of observed pixels, the unobserved pixels can be imputed in a user-controllable range of possibilities, each of which is semantically coherent and locally consistent with the observed pixels. We achieve this using a deep generat…

The paper solves optimal control problems for various convex sets using convex trigonometry.

We propose a method to compute optimal control paths for autonomous vehicles deployed for the purpose of inferring a velocity field. In addition to being advected by the flow, the vehicles are able to effect a fixed relative speed with arbitrary control over direction. It is this direction that is used as the basis for…

We introduce a new algorithm for online linear-quadratic control in a known system subject to adversarial disturbances. Existing regret bounds for this setting scale as $\sqrt{T}$ unless strong stochastic assumptions are imposed on the disturbance process. We give the first algorithm with logarithmic regret for arbitra…

We investigate whether a robot arm can learn to pick and throw arbitrary objects into selected boxes quickly and accurately. Throwing has the potential to increase the physical reachability and picking speed of a robot arm. However, precisely throwing arbitrary objects in unstructured settings presents many challenges:…

Paper tackles overestimation bias in continuous control, improving performance by 25%.

In this paper, we derive curvature estimates for strongly stable hypersurfaces with constant mean curvature immersed in $\mathbb{R}^{n+1}$, which show that the locally controlled volume growth yields a globally controlled volume growth if $\partial M=\emptyset$. Moreover, we deduce a Bernstein-type theorem for complete…

Random features enhance control of complex systems.

A new convenient method of describing flat convex compact sets is proposed. It generalizes classical trigonometric functions $\sin$ and $\cos$. Apparently, this method may be very useful for explicit description of solutions of optimal control problems with two-dimensional control. Using this method a series of sub-Fin…

IG-RL learns adaptive traffic signals for any network, outperforming existing methods.

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

Motivated by control-affine systems in optimal control theory, we introduce the notion of a point-affine distribution on a manifold X - i.e., an affine distribution F together with a distinguished vector field contained in F. We compute local invariants for point-affine distributions of constant type when dim(X)=n, ran…

Deep reinforcement learning has been shown to solve challenging tasks where large amounts of training experience is available, usually obtained online while learning the task. Robotics is a significant potential application domain for many of these algorithms, but generating robot experience in the real world is expens…

This is an introductory chapter in a series in which we take a systematic study of the Yang-Mills equations on curved space-times. In this first, we provide standard material that consists in writing the proof of the global existence of Yang-Mills fields on arbitrary curved space-times using the Klainerman-Rodnianski p…

Proves existence of minimal surfaces of arbitrary genus with two ends.

This paper tackles inventory control with general arrival dynamics and post-processing, improving profitability.

The article concerns the geometrical theory of general systems $Ω$ of partial differential equations in the \emph{absolute sense}, i.e., without any additional structure and subject to arbitrary change of variables in the widest possible meaning. The main result describes the composition series $Ω^0\subsetΩ^1\subset\cd…

Decision tree learning is a popular classification technique most commonly used in machine learning applications. Recent work has shown that decision trees can be used to represent provably-correct controllers concisely. Compared to representations using lookup tables or binary decision diagrams, decision trees are sma…

Deep Hedging learns optimal strategies for various risk levels.

We consider the problem of asynchronous online testing, aimed at providing control of the false discovery rate (FDR) during a continual stream of data collection and testing, where each test may be a sequential test that can start and stop at arbitrary times. This setting increasingly characterizes real-world applicati…

LineFlow is a framework for training RL agents to control production lines.

Derives a fluid model for fish swarming in arbitrary dimensions.

Paper uses VAEs to control IVS features for financial modeling.

Paper proposes method for optimal control of unknown systems with latent states.

TSC improves causal effect estimation in panel data.

Voltage control plays an important role in the operation of electricity distribution networks, especially with high penetration of distributed energy resources. These resources introduce significant and fast varying uncertainties. In this paper, we focus on reactive power compensation to control voltage in the presence…

Finite resources limit false discovery rate control in structured hypothesis spaces.

Paper proposes SCALLION and SCAFCOM for compressed FL with reduced communication.

In this paper, two Q-learning (QL) methods are proposed and their convergence theories are established for addressing the model-free optimal control problem of general nonlinear continuous-time systems. By introducing the Q-function for continuous-time systems, policy iteration based QL (PIQL) and value iteration based…

Nonparametric IPSS selects features with false discovery control.

Study helical motions of lines in 3D spaces, solving control problems.

We show LLMs can be locally linear, enabling better control of activations.

We frame the problem of selecting an optimal audio encoding scheme as a supervised learning task. Through uniform convergence theory, we guarantee approximately optimal codec selection while controlling for selection bias. We present rigorous statistical guarantees for the codec selection problem that hold for arbitrar…

New method controls false discoveries in online testing with deadlines.

We provide faster algorithms for the problem of Gaussian summation, which occurs in many machine learning methods. We develop two new extensions - an O(Dp) Taylor expansion for the Gaussian kernel with rigorous error bounds and a new error control scheme integrating any arbitrary approximation method - within the best …

The paper studies distributions and controllability in quantum mechanical systems.

Gradient-based methods for optimisation of objectives in stochastic settings with unknown or intractable dynamics require estimators of derivatives. We derive an objective that, under automatic differentiation, produces low-variance unbiased estimators of derivatives at any order. Our objective is compatible with arbit…

New bounds for SA with arbitrary norm contractions and Markovian noise.

A new method models continuous-time counterfactual outcomes using neural controlled differential equations.

We prove Birkhoff-type results showing that $L^2$ solutions of the linearized Einstein equations around Riemannian Kottler ("Schwarzschild-anti de Sitter") metrics in arbitrary dimension and horizon topology, which are not controlled by "master functions" are pure gauge. Together with earlier results this implies that …

We provide the first differentially private algorithms for controlling the false discovery rate (FDR) in multiple hypothesis testing, with essentially no loss in power under certain conditions. Our general approach is to adapt a well-known variant of the Benjamini-Hochberg procedure (BHq), making each step differential…

Optimizes exploration for nonlinear systems to learn controllers efficiently.

New algorithm achieves optimal regret in non-stochastic control, showing stochasticity is not beneficial.

The paper proves the existence of H-spheres with arbitrary codimensions in certain Riemannian manifolds.