arXiv research

New method controls linear systems with partial info and disturbances.

IDS optimizes regret in stochastic partial monitoring with linear rewards.

IDS algorithm optimizes sequential decisions in various monitoring settings.

Proposes a partially linear structure to capture nonlinear relationships in mixture of experts models.

Differentiable relaxation for inferring partial orders from noisy linear data.

Algorithm reduces regret in partially observable systems by learning dynamics and using optimistic control.

On any space-like W-surface in the three-dimensional Minkowski space we introduce locally natural principal parameters and prove that such a surface is determined uniquely up to motion by a special invariant function, which satisfies a natural non-linear partial differential equation. This result can be interpreted as …

Introduces a new model for mapping matrices to matrices, subsuming linear regression.

Linear recurrent networks explain reinforcement learning performance in partially observable settings.

Flexible DNN for survival data, avoiding proportional hazards assumption.

Study of transitivity in partially hyperbolic maps with expanding linear part.

Study efficient reinforcement learning for partially observed systems with linear structure.

AdaptOn achieves logarithmic regret in adaptive control of unknown partially observable linear systems.

Study uses deep neural networks for inference in partially linear models with dependent data.

This paper provides estimation and inference methods for an identified set's boundary (i.e., support function) where the selection among a very large number of covariates is based on modern regularized tools. I characterize the boundary using a semiparametric moment equation. Combining Neyman-orthogonality and sample s…

New method disentangles perceptual uncertainty and behavioral costs in partially observable systems.

New algorithm for partially observable contexts in finance.

We tackle linear bandits with partially observable features, achieving sublinear regret.

We formulate stochastic partial differential equations on Riemannian manifolds, moving surfaces, general evolving Riemannian manifolds (with appropriate assumptions) and Riemannian manifolds with random metrics, in the variational setting of the analysis to stochastic partial differential equations. Considering mainly …

Absolutely partially hyperbolic surface endomorphisms have a coherent center foliation.

New algorithms solve robust MDPs efficiently, significantly faster than existing methods.

TOFU-POV tackles partially observed linear bandits, achieving sublinear regret with low-dimensional action vectors.

Paper addresses linear regression with partially mismatched data using local search with theoretical guarantees.

The aim of this article is to show that systems of linear partial differential equations on filtered manifolds, which are of weighted finite type, can be canonically rewritten as first order systems of a certain type. This leads immediately to obstructions to the existence of solutions. Moreover, we will deduce that th…

New Thompson sampling algorithm for stochastic partial monitoring achieves logarithmic regret.

On contact manifolds we describe a notion of (contact) finite-type for linear partial differential operators satisfying a natural condition on their leading terms. A large class of linear differential operators are of finite-type in this sense, and for any such operator we construct a partial connection on a (finite ra…

The intrinsic geometric properties of generalized Darboux-Manakov-Zakharov systems of semilinear partial differential equations \label{GDMZabstract} \frac{\partial^2 u}{\partial x_i\partial x_j}=f_{ij}\Big(x_k,u,\frac{\partial u}{\partial x_l}\Big), 1\leq i<j\leq n, k,l\in\{1,...,n\} for a real-valued function $u(x_1,.…

Improved RL algorithm with linear MDPs for offline learning with partial data coverage.

KalmanNet uses neural networks to improve state estimation in systems with unknown dynamics.

PCBM improves neural network generalization by partially observing concepts.

A new method combines machine learning with mixed-effects models for better repeated measurement analysis.

Algorithm learns linear systems from partial observations with near-optimal rate.

The generalized partially linear additive model (GPLAM) is a flexible and interpretable approach to building predictive models. It combines features in an additive manner, allowing each to have either a linear or nonlinear effect on the response. However, the choice of which features to treat as linear or nonlinear is …

We study time-like surfaces in the three-dimensional Minkowski space with diagonalizable second fundamental form. On any time-like W-surface we introduce locally natural principal parameters and prove that such a surface is determined uniquely (up to motion) by a special invariant function, which satisfies a natural no…

A new screening method for high-dimensional data reduces computational cost.

This paper improves system identification by reducing sample complexity for high-dimensional linear dynamical systems.

These lecture notes are concerned with the solvability of the second boundary value problem of the prescribed affine mean curvature equation and related regularity theory of the Monge-Ampère and linearized Monge-Ampère equations. The prescribed affine mean curvature equation is a fully nonlinear, fourth order, geometri…

We propose a partially linear additive Gaussian graphical model (PLA-GGM) for the estimation of associations between random variables distorted by observed confounders. Model parameters are estimated using an $L_1$-regularized maximal pseudo-profile likelihood estimator (MaPPLE) for which we prove $\sqrt{n}$-sparsisten…

We introduce an effective method to solve the $\bar\partial$-harmonic forms on the Kodaira-Thurston manifold endowed with an almost complex structure and an Hermitian metric. Using the Weil-Brezin transform, we reduce the elliptic PDE system to countably many linear ODE systems. By solving a fundamental problem on line…

The paper addresses nonconvex penalized LAD estimation in partial linear models using DNNs.

Study shows solutions to certain equations form smooth manifolds.

Paper develops a method for estimating PFLM with minimized rates in high dimensions.

Method estimates sparse inverse covariance and partial correlation matrices efficiently.

The Trek Separation Theorem (Sullivant et al. 2010) states necessary and sufficient conditions for a linear directed acyclic graphical model to entail for all possible values of its linear coefficients that the rank of various sub-matrices of the covariance matrix is less than or equal to n, for any given n. In this pa…

Although various distributed machine learning schemes have been proposed recently for pure linear models and fully nonparametric models, little attention has been paid on distributed optimization for semi-paramemetric models with multiple-level structures (e.g. sparsity, linearity and nonlinearity). To address these is…

This paper studies the question of filtering and maximizing terminal wealth from expected utility in a partially information stochastic volatility models. The special features is that the only information available to the investor is the one generated by the asset prices, and the unobservable processes will be modeled …

New method uses Gaussian processes for solving linear PDEs with boundary conditions.

Oracle-efficient algorithm for offline RL with partial data coverage.