Santiago Paternain

Santiago Paternain

Auto-generated profile, based on publicly available information

Santiago Paternain

Department of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute, Troy, NY, USA

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 July 2020 in Proceedings of the IEEE
Verified
Journal Article
Closed access
ASAndrea Simonetto
Andrea Simonetto
EDEmiliano Dall'ANese
Emiliano Dall'ANese
SPSantiago Paternain
Santiago Paternain
GLGeert Leus
Geert Leus
GGGeorgios B. Giannakis
Georgios B. Giannakis
Optimization underpins many of the challenges that science and technology face on a daily basis. Recent years have witnessed a major shift from traditional optimization paradigms grounded on batch algorithms for medium-scale problems to challenging dynamic, time-varying, and even huge-size settings. This is driven by technological transformations that converted infrastructural and social platforms into complex and dynamic networked systems with even pervasive sensing and computing capabilities. This article reviews a broad class of state-of-the-art algorithms for time-varying optimization, with an eye to performing both algorithmic development and performance analysis. It offers a comprehensive overview of available tools and methods and unveils open challenges in application domains of broad range of interest. The real-world examples presented include smart power systems, robotics, machine learning, and data analytics, highlighting domain-specific issues and solutions. The ultimate goal is to exemplify wide engineering relevance of analytical tools and pertinent theoretical foundations.

9 October 2017 in IEEE Transactions on Automatic Control
Verified
Journal Article
Closed access
MFMahyar Fazlyab
Mahyar Fazlyab
SPSantiago Paternain
Santiago Paternain
VPVictor M. Preciado
Victor M. Preciado
ARAlejandro Ribeiro
Alejandro Ribeiro
In this paper, we develop an interior-point method for solving a class of convex optimization problems with time-varying objective and constraint functions. Using log-barrier penalty functions, we propose a continuous-time dynamical system for tracking the (time-varying) optimal solution with an asymptotically vanishing error. This dynamical system is composed of two terms: (i) a correction term consisting of a continuous-time version of Newton's method, and (ii) a prediction term able to track the drift of the optimal solution by taking into account the time-varying nature of the objective and constraint functions. Using appropriately chosen time-varying slack and barrier parameters, we ensure that the solution to this dynamical system globally asymptotically converges to the optimal solution at an exponential rate. We illustrate the applicability of the proposed method in two applications: a sparsity promoting least squares problem and a collision-free robot navigation problem.

22 February 2022 in IEEE Transactions on Automatic Control
Verified
Journal Article
Closed access
SPSantiago Paternain
Santiago Paternain
MCMiguel Calvo-Fullana
Miguel Calvo-Fullana
LCLuiz F. O. Chamon
Luiz F. O. Chamon
ARAlejandro Ribeiro
Alejandro Ribeiro
In this paper, we study the design of controllers in the context of stochastic optimal control under the assumption that the model of the system is not available. This is, we aim to control a Markov Decision Process (MDP) of which we do not know the transition probabilities, but we have access to sample trajectories through experience. We define safety as the agent remaining in a desired safe set with high probability during the operation time. The drawbacks of this formulation are twofold. The problem is non-convex and computing the gradients of the constraints with respect to the policies is prohibitive. Hence, we propose an ergodic relaxation of the constraints with the following advantages. (i) The safety guarantees are maintained in the case of episodic tasks and they hold until a given time horizon for continuing tasks. (ii) The constrained optimization problem despite its non-convexity has arbitrarily small duality gap if the parametrization of the controller is rich enough. (iii) The gradients of the Lagrangian associated to the safe learning problem can be computed using standard Reinforcement Learning (RL) results and stochastic approximation tools. Leveraging these adv

17 November 2017 in IEEE Transactions on Automatic Control
Verified
Journal Article
Closed access
SPSantiago Paternain
Santiago Paternain
DKDaniel E. Koditschek
Daniel E. Koditschek
ARAlejandro Ribeiro
Alejandro Ribeiro
Given a convex potential in a space with convex obstacles, an artificial potential is used to navigate to the minimum of the natural potential while avoiding collisions. The artificial potential combines the natural potential with potentials that repel the agent from the border of the obstacles. This is a popular approach to navigation problems because it can be implemented with spatially local information that is acquired during operation time. Artificial potentials can, however, have local minima that prevent navigation to the minimum of the natural potential. This paper derives conditions that guarantee artificial potentials have a single minimum that is arbitrarily close to the minimum of the natural potential. The qualitative implication is that artificial potentials succeed when either the condition number-- the ratio of the maximum over the minimum eigenvalue-- of the Hessian of the natural potential is not large and the obstacles are not too flat or when the destination is not close to the border of an obstacle. Numerical analyses explore the practical value of these theoretical conclusions.

27 April 2018 in IEEE Transactions on Signal Processing
Verified
Journal Article
Closed access
AKAlec Koppel
Alec Koppel
SPSantiago Paternain
Santiago Paternain
CRCedric Richard
Cedric Richard
ARAlejandro R. Ribeiro
Alejandro R. Ribeiro
We consider multi-agent stochastic optimization problems over reproducing kernel Hilbert spaces (RKHS). In this setting, a network of interconnected agents aims to learn decision functions, i.e., nonlinear statistical models, that are optimal in terms of a global convex functional that aggregates data across the network, with only access to locally and sequentially observed samples. We propose solving this problem by allowing each agent to learn a local regression function while enforcing consensus constraints. We use a penalized variant of functional stochastic gradient descent operating simultaneously with low-dimensional subspace projections. These subspaces are constructed greed- ily by applying orthogonal matching pursuit to the sequence of kernel dictionaries and weights. By tuning the projection- induced bias, we propose an algorithm that allows for each individual agent to learn, based upon its locally observed data stream and message passing with its neighbors only, a regression function that is close to the globally optimal regression function. That is, we establish that with constant step-size selections agents' functions converge to a neighborhood of the globally optimal one while satisfying the consensus constraints as the penalty parameter is increased. Moreover, the complexity of the learned regression functions is guaranteed to remain finite. On both multi-class kernel logistic regression and multi-class kernel support vector classification with data generated from class- dependent Gaussian mixture models, we observe stable function estimation and state of the art performance for distributed online multi-class classification. Experiments on the Brodatz textures further substantiate the empirical validity of this approach.

25 September 2023 in IEEE Transactions on Automatic Control
Verified
Journal Article
Closed access
MCMiguel Calvo-Fullana
Miguel Calvo-Fullana
SPSantiago Paternain
Santiago Paternain
LCLuiz F. O. Chamon
Luiz F. O. Chamon
ARAlejandro Ribeiro
Alejandro Ribeiro
A common formulation of constrained reinforcement learning involves multiple rewards that must individually accumulate to given thresholds. In this class of problems, we show a simple example in which the desired optimal policy cannot be induced by any weighted linear combination of rewards. Hence, there exist constrained reinforcement learning problems for which neither regularized nor classical primal-dual methods yield optimal policies. This work addresses this shortcoming by augmenting the state with Lagrange multipliers and reinterpreting primal-dual methods as the portion of the dynamics that drives the multipliers evolution. This approach provides a systematic state augmentation procedure that is guaranteed to solve reinforcement learning problems with constraints. Thus, as we illustrate by an example, while previous methods can fail at finding optimal policies, running the dual dynamics while executing the augmented policy yields an algorithm that provably samples actions from the optimal policy.