arXiv subjects

Juan Pablo Contreras

Publications and source records attributed to Juan Pablo Contreras.

5 recordsLinked to original sources

arXiv2025

Stochastic Halpern iteration in normed spaces and applications to reinforcement learning

We analyze the oracle complexity of the stochastic Halpern iteration with minibatch, where we aim to approximate fixed-points of nonexpansive and contractive operators in a normed finite-dimensional space. We show that if the underlying stochastic oracle has uniformly bounded variance, our method exhibits an overall oracle complexity of $\tilde{O}(\varepsilon^{-5})$, to obtain $\varepsilon$ expected fixed-point residual for nonexpansive operators, improving recent rates established for the stochastic Krasnoselskii-Mann iteration. Also, we establish a lower bound of $Ω(\varepsilon^{-3})$ which applies to a wide range of algorithms, including all averaged iterations even with minibatching. Using a suitable modification of our approach, we derive a $O(\varepsilon^{-2}(1-γ)^{-3})$ complexity bound in the case in which the operator is a $γ$-contraction to obtain an approximation of the fixed-point. As an application, we propose new model-free algorithms for average and discounted reward MDPs. For the average reward case, our method applies to weakly communicating MDPs without requiring prior parameter knowledge.

math.OC↗

arXiv2025

Non-Euclidean High-Order Smooth Convex Optimization

We develop algorithms for the optimization of convex objectives that have Hölder continuous $q$-th derivatives by using a $q$-th order oracle, for any $q \geq 1$. Our algorithms work for general norms under mild conditions, including the $\ell_p$-settings for $1\leq p\leq \infty$. We can also optimize structured functions that allow for inexactly implementing a non-Euclidean ball optimization oracle. We do this by developing a non-Euclidean inexact accelerated proximal point method that makes use of an \emph{inexact uniformly convex regularizer}. We show a lower bound for general norms that demonstrates our algorithms are nearly optimal in high-dimensions in the black-box oracle model for $\ell_p$-settings and all $q \geq 1$, even in randomized and parallel settings. This new lower bound, when applied to the first-order smooth case, resolves an open question in parallel convex optimization.

math.OC↗

arXiv2024

School Bus Routing Problem with Open Offer Policy: incentive pricing strategy for students that opt-out using school bus

This paper introduces the School Bus Routing Problem with Open Offer Policy (SBRP-OOP) that seeks to improve capacity usage and minimize the bus fleet by openly offering a monetary incentive to students willing to opt out of using a bus. We propose a mathematical formulation to determine a pricing strategy that balances the trade-off between incentive payments for students who choose not to use the bus with the expected savings obtained from operating fewer buses. To evaluate the effectiveness of the approach, we conducted simulations using both synthetic and real instances from a real operational context in the Williamsville Central School District (WCSD) of New York.

math.OC↗

arXiv2022

Accelerated Bregman Primal-Dual methods applied to Optimal Transport and Wasserstein Barycenter problems

This paper discusses the efficiency of Hybrid Primal-Dual (HPD) type algorithms to approximate solve discrete Optimal Transport (OT) and Wasserstein Barycenter (WB) problems, with and without entropic regularization. Our first contribution is an analysis showing that these methods yield state-of-the-art convergence rates, both theoretically and practically. Next, we extend the HPD algorithm with linesearch proposed by Malitsky and Pock in 2018 to the setting where the dual space has a Bregman divergence, and the dual function is relatively strongly convex to the Bregman's kernel. This extension yields a new method for OT and WB problems based on smoothing of the objective that also achieves state-of-the-art convergence rates. Finally, we introduce a new Bregman divergence based on a scaled entropy function that makes the algorithm numerically stable and reduces the smoothing, leading to sparse solutions of OT and WB problems. We complement our findings with numerical experiments and comparisons.

math.OC↗

arXiv2022

Optimal error bounds for nonexpansive fixed-point iterations in normed spaces

This paper investigates optimal error bounds and convergence rates for general Mann iterations for computing fixed-points of non-expansive maps. We look for iterations that achieve the smallest fixed-point residual after $n$ steps, by minimizing a worst-case bound $\|x^n-Tx^n\|\le R_n$ derived from a nested family of optimal transport problems. We prove that this bound is tight so that minimizing $R_n$ yields optimal iterations. Inspired from numerical results we identify iterations that attain the rate $R_n=O(1/n)$, which we also show to be the best possible. In particular, we prove that the classical Halpern iteration achieves this optimal rate for several alternative stepsizes, and we determine analytically the optimal stepsizes that attain the smallest worst-case residuals at every step $n$, with a tight bound $R_n\approx\frac{4}{n+4}$. We also determine the optimal Halpern stepsizes for affine non-expansive maps, for which we get exactly $R_n=\frac{1}{n+1}$. Finally, we show that the best rate for the classical Krasnosel'ski\uı-Mann iteration is $Ω(1/\sqrt{n})$, and present numerical evidence suggesting that even extended variants cannot reach a faster rate.

math.OC↗