arXiv research

Cyclic coordinate descent identifies models in finite time and converges linearly.

New bounds derived for KG algorithm's performance in finite time.

The OLS estimator optimally identifies stable linear systems with a finite number of samples.

Efficiently identifies best policies in tabular MDPs with reduced computational cost.

A distributed system identification method for LTI systems using reverse experience replay.

Active learning method estimates nonlinear systems efficiently.

We identify linear dynamical systems under convex constraints with fewer samples.

Algorithm identifies bilinear dynamical systems from noisy data.

Improved SGD bounds for machine learning models with Markovian noise.

We consider the problem of learning a realization for a linear time-invariant (LTI) dynamical system from input/output data. Given a single input/output trajectory, we provide finite time analysis for learning the system's Markov parameters, from which a balanced realization is obtained using the classical Ho-Kalman al…

The main challenge for adaptive regulation of linear-quadratic systems is the trade-off between identification and control. An adaptive policy needs to address both the estimation of unknown dynamics parameters (exploration), as well as the regulation of the underlying system (exploitation). To this end, optimism-based…

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

New continuous-time optimization algorithms converge in finite time to local minima.

We study the problem of finding the optimal dosage in early stage clinical trials through the multi-armed bandit lens. We advocate the use of the Thompson Sampling principle, a flexible algorithm that can accommodate different types of monotonicity assumptions on the toxicity and efficacy of the doses. For the simplest…

Study finite time singularities in Ricci flow with bounded scalar curvature.

We study local complexity measures for stochastic convex optimization problems, providing a local minimax theory analogous to that of Hájek and Le Cam for classical statistical problems. We give complementary optimality results, developing fully online methods that adaptively achieve optimal convergence guarantees. Our…

Algorithm identifies best arm in combinatorial bandits with semi-bandit feedback.

Finite-time blow-up in Yang-Mills flow for small energy initial connections.

Estimates for VPMCF show ancient MCF solutions and finite-time behavior.

The paper analyzes deep neural networks using control theory to set a time limit for their convergence.

The paper tackles joint learning of linear systems, improving accuracy with pooled data.

We show that if on a compact Kahler threefold there is a solution of the Kahler-Ricci flow which encounters a finite time collapsing singularity, then the manifold admits a Fano fibration. Furthermore, if there is finite time extinction then the manifold is Fano and the initial class is a positive multiple of the first…

We consider the question of whether solutions of variants of Teichmüller harmonic map flow from surfaces $M$ to general targets can degenerate in finite time. For the original flow from closed surfaces of genus at least $2$, as well as the flow from cylinders, we prove that such a finite-time degeneration must occur in…

We give concentration bounds for martingales that are uniform over finite times and extend classical Hoeffding and Bernstein inequalities. We also demonstrate our concentration bounds to be optimal with a matching anti-concentration inequality, proved using the same method. Together these constitute a finite-time versi…

New approach incentivizes strategic agents to explore, making exploration almost free.

Study of deep neural networks using finite-time Lyapunov exponents.

Study on SA with heavy-tailed and LRD noise, establishing finite-time bounds.

Algorithm optimally estimates linear dynamical systems with active input selection.

In this note we study finite-time singularities in the Chern-Ricci flow. We show that finite-time singularities are characterized by the blow-up of the scalar curvature of the Chern connection.

First-order method solves stochastic bilevel optimization with linear constraints.

In this short paper, we show that Kähler-Ricci flows over closed manifolds would have scalar curvature blown-up for finite time singularity. Certain control of the blowing-up is achieved with some mild assumption.

The paper analyzes finite-time singularities in Spin(7)-structure flows using Shi-type estimates.

Paper analyzes finite-time performance of SA in RL with Markovian noise.

Compact curve solution emerges from non-compact curve.

Efficiently controls unknown linear systems with black-box interactions.

Ricci flow singularities on compact Kähler surfaces are of Type I.

Paper analyzes convergence rates for multi-agent learning in games.

Paper analyzes Q-learning with neural networks, proving a fast convergence rate.

Finite-time extinction and smoothing effects in fractional fast diffusion on manifolds.

This paper provides a set of sensitivity analysis and activity identification results for a class of convex functions with a strong geometric structure, that we coined "mirror-stratifiable". These functions are such that there is a bijection between a primal and a dual stratification of the space into partitioning sets…

Study optimal stopping problems with finite-time horizon and proves continuity and strict monotonicity of the boundary.

Given any embedded Lagrangian on a four dimensional compact Calabi-Yau, we find another Lagrangian in the same Hamiltonian isotopy class which develops a finite time singularity under mean curvature flow. This contradicts a weaker version of the Thomas-Yau conjecture regarding long time existence and convergence of Lag…

I analyse the frequentist regret of the famous Gittins index strategy for multi-armed bandits with Gaussian noise and a finite horizon. Remarkably it turns out that this approach leads to finite-time regret guarantees comparable to those available for the popular UCB algorithm. Along the way I derive finite-time bounds…

We consider a distributed estimation method in a setting with heterogeneous streams of correlated data distributed across nodes in a network. In the considered approach, linear models are estimated locally (i.e., with only local data) subject to a network regularization term that penalizes a local model that differs fr…

The Kähler-Ricci flow's singularities are analyzed with bounds and convergence results.

Paper analyzes finite-time convergence of double Q-learning.

Finite-time queue peaks in stochastic networks have logarithmic scaling after geometric thresholds.

Theoretical justification for asymmetric actor-critic algorithms in reinforcement learning.