arXiv subjects

Pablo Barros

Publications and source records attributed to Pablo Barros.

At least 19 recordsLinked to original sources

arXiv2026

Bidirectional SDDP with dimension-free complexity for solving strongly convex stochastic dynamic programming equations

We analyze the complexity of Bidirectional Stochastic Dual Dynamic Programming (BSDDP) algorithm applied to multistage stochastic optimization problems with strongly convex cost functions. Under standard regularity assumptions and without discount factor, we establish an explicit complexity bound on the expected number of iterations needed to obtain an epsilon-optimal policy. Our bound depends on the strong convexity constants and Lipschitz constants of the stagewise cost functions but is independent of the dimensionality of the state space. This improves upon the complexity of SDDP for convex problems from (Lan, 2020), particularly when the number of stages is moderate and the state dimension is large. The analysis further reveals that the complexity decreases as the strong convexity of the cost functions increases, highlighting the algorithm efficiency in structured problem instances.

math.OC↗

arXiv2026

Dimension-Free Complexity Guarantees for Dual Dynamic Programming

This paper studies the complexity of a dual dynamic programming (DDP) method for solving a class of convex optimization problems with linear coupling constraints. Existing complexity results based on DDP depend on the dimensions of the state vectors and, in particular, grow exponentially with dimension. The goal of this paper is to establish a complexity bound that is independent of the dimension. Our approach first studies an unconstrained strongly convex problem and develops a flexible framework for DDP, called FDDP, for solving the associated dynamic programming equations, and establishes an iteration-complexity bound for it that is independent of the dimension. A dimension-independent complexity bound for the original linearly constrained problem is then obtained by applying FDDP to a corresponding unconstrained strongly convex problem obtained via smoothing and penalization. Inspired by the literature on bundle methods, FDDP updates lower approximations of cost-to-go functions through a generic procedure that includes both the classical multi-cut DDP and a new two-cut DDP variant as special cases. The two-cut variant maintains only two affine cuts per stage at each iteration, making it more memory-efficient while retaining the same theoretical guarantees. Finally, numerical experiments illustrate the practical behavior of multi-cut and two-cut DDP, including their dependence on problem parameters and their performance relative to a direct quadratic constraint reformulation.

math.OC↗

arXiv2026

BROTHER: Behavioral Recognition Optimized Through Heterogeneous Ensemble Regularization for Ambivalence and Hesitancy

Recognizing complex behavioral states such as Ambivalence and Hesitancy (A/H) in naturalistic video settings remains a significant challenge in affective computing. Unlike basic facial expressions, A/H manifests as subtle, multimodal conflicts that require deep contextual and temporal understanding. In this paper, we propose a highly regularized, multimodal fusion pipeline to predict A/H at the video level. We extract robust unimodal features from visual, acoustic, and linguistic data, introducing a specialized statistical text modality explicitly designed to capture temporal speech variations and behavioral cues. To identify the most effective representations, we evaluate 15 distinct modality combinations across a committee of machine learning classifiers (MLP, Random Forest, and GBDT), selecting the most well-calibrated models based on validation Binary Cross-Entropy (BCE) loss. Furthermore, to optimally fuse these heterogeneous models without overfitting to the training distribution, we implement a Particle Swarm Optimization (PSO) hard-voting ensemble. The PSO fitness function dynamically incorporates a train-validation gap penalty (lambda) to actively suppress redundant or overfitted classifiers. Our comprehensive evaluation demonstrates that while linguistic features serve as the strongest independent predictor of A/H, our heavily regularized PSO ensemble (lambda = 0.2) effectively harnesses multimodal synergies, achieving a peak Macro F1-score of 0.7465 on the unseen test set. These results emphasize that treating ambivalence and hesitancy as a multimodal conflict, evaluated through an intelligently weighted committee, provides a robust framework for in-the-wild behavioral analysis.

cs.CV↗

arXiv2026

New operator designs for Halpern iterations with explicit rates under H\"older error bounds

We investigate the asymptotic behavior of Halpern-type iterations applied to quasi-nonexpansive operators arising in best approximation problems over the intersection of finitely many closed convex sets in $\mathbb{R}^n$. Assuming a local decrease condition for the underlying operator and standard requirements on the stepsizes $(\alpha_k) \subset (0,1)$, we first prove strong convergence of the Halpern sequence $x_{k+1} = \alpha_k x_0 + (1-\alpha_k) T x_k$ to the best approximation point $x^\star$ in the intersection set, that is, the metric projection of $x_0$ onto that set. Under the additional assumption that the intersection satisfies a H\"older-type error bound with exponent $\gamma \in (0,1]$, we then derive explicit convergence rates for both feasibility and norm error: the distance from $x_k$ to the intersection set decays like $\mathcal O(\alpha_k^{\gamma/(2-\gamma)})$, while the norm error $\|x_k - x^\star\|$ decays like $\mathcal O(\alpha_k^{\gamma/(4-2\gamma)})$. These results apply to most projection-type operators used in convex feasibility problems (including MAP, CRM/SCCRM, Cimmino and 3PM/A3PM) and extend classical convergence analyses of the Halpern-type iterations by providing explicit, geometry-dependent rates governed by H\"older-type error bounds. Our numerical experiments show that Halpern-type iterations combined with most of these projection-type operators are quicker than Dykstra's algorithm to find the projection of a point in an intersection of ellipsoids or in an intersection of polyhedrons.

math.OC↗

arXiv2025

Deep Centralization for the Circumcentered Reflection Method

We introduce the extended centralized circumcentered reflection method (ecCRM), a framework for two-set convex feasibility that encompasses the classical centralized CRM (cCRM) of Behling, Bello-Cruz, Iusem and Santos as a special case. Our method replaces the fixed centralization step of cCRM with an admissible operator $T$ and a parameter $\alpha$, allowing control over computational cost and step quality. We show that ecCRM retains global convergence, linear rates under mild regularity, and superlinearity for smooth manifolds. Numerical experiments on large-scale matrix completion indicate that deeper operators can dramatically reduce overall runtime, and tests on high-dimensional ellipsoids show that vanishing step sizes can yield significant acceleration, validating the practical utility of both algorithmic components of ecCRM.

math.OC↗

arXiv2025

Parallel Polyhedral Projection Method for the Convex Feasibility Problem

In this paper, we introduce and study the Parallel Polyhedral Projection Method (3PM) and the Approximate Parallel Polyhedral Projection Method (A3PM) for finding a point in the intersection of finitely many closed convex sets. Each iteration has two phases: parallel projections onto the target sets (exact in 3PM, approximate in A3PM), followed by an exact or approximate projection onto a polyhedron defined by supporting half-spaces. These strategies appear novel, as existing methods largely focus on parallel schemes like Cimmino's method. Numerical experiments demonstrate that A3PM often outperforms both classical and recent projection-based methods when the number of sets is greater than two. Theoretically, we establish global convergence for both 3PM and A3PM without regularity assumptions. Under a Slater condition or error bound, we prove linear convergence, even with inexact projections. Additionally, we show that 3PM achieves superlinear convergence under suitable geometric assumptions.

math.OC↗

arXiv2025

Parallelizing the Circumcentered-Reflection Method

This paper introduces the Parallelized Circumcentered Reflection Method (P-CRM), a circumcentric approach that parallelizes the Circumcentered Reflection Method (CRM) for solving Convex Feasibility Problems in affine settings. Beyond feasibility, P-CRM solves the best approximation problem for any finite collection of affine subspaces; that is, it not only finds a feasible point but directly computes the projection of an initial point onto the intersection. Within a fully self-contained scheme, we also introduce the Framework for the Simultaneous Projection Method (F-SPM) which includes Cimmino's method as a special case. Theoretical results show that both P-CRM and F-SPM achieve linear convergence. Moreover, P-CRM converges at a rate that is at least as fast as, and potentially superior to, the best convergence rate of F-SPM. As a byproduct, this also yields a new and simplified convergence proof for Cimmino's method. Numerical experiments show that P-CRM is competitive compared to CRM and indicate that it offers a scalable and flexible alternative, particularly suited for large-scale problems and modern computing environments.

math.OC↗

arXiv2023

All by Myself: Learning Individualized Competitive Behaviour with a Contrastive Reinforcement Learning optimization

In a competitive game scenario, a set of agents have to learn decisions that maximize their goals and minimize their adversaries' goals at the same time. Besides dealing with the increased dynamics of the scenarios due to the opponents' actions, they usually have to understand how to overcome the opponent's strategies. Most of the common solutions, usually based on continual learning or centralized multi-agent experiences, however, do not allow the development of personalized strategies to face individual opponents. In this paper, we propose a novel model composed of three neural layers that learn a representation of a competitive game, learn how to map the strategy of specific opponents, and how to disrupt them. The entire model is trained online, using a composed loss based on a contrastive optimization, to learn competitive and multiplayer games. We evaluate our model on a pokemon duel scenario and the four-player competitive Chef's Hat card game. Our experiments demonstrate that our model achieves better performance when playing against offline, online, and competitive-specific models, in particular when playing against the same opponent multiple times. We also present a discussion on the impact of our model, in particular on how well it deals with on specific strategy learning for each of the two scenarios.

cs.AI↗

arXiv2022

I am Only Happy When There is Light: The Impact of Environmental Changes on Affective Facial Expressions Recognition

Human-robot interaction (HRI) benefits greatly from advances in the machine learning field as it allows researchers to employ high-performance models for perceptual tasks like detection and recognition. Especially deep learning models, either pre-trained for feature extraction or used for classification, are now established methods to characterize human behaviors in HRI scenarios and to have social robots that understand better those behaviors. As HRI experiments are usually small-scale and constrained to particular lab environments, the questions are how well can deep learning models generalize to specific interaction scenarios, and further, how good is their robustness towards environmental changes? These questions are important to address if the HRI field wishes to put social robotic companions into real environments acting consistently, i.e. changing lighting conditions or moving people should still produce the same recognition results. In this paper, we study the impact of different image conditions on the recognition of arousal and valence from human facial expressions using the FaceChannel framework \cite{Barro20}. Our results show how the interpretation of human affective states can differ greatly in either the positive or negative direction even when changing only slightly the image properties. We conclude the paper with important points to consider when employing deep learning models to ensure sound interpretation of HRI experiments.

cs.CV↗

arXiv2022

Incorporating Rivalry in Reinforcement Learning for a Competitive Game

Recent advances in reinforcement learning with social agents have allowed such models to achieve human-level performance on specific interaction tasks. However, most interactive scenarios do not have a version alone as an end goal; instead, the social impact of these agents when interacting with humans is as important and largely unexplored. In this regard, this work proposes a novel reinforcement learning mechanism based on the social impact of rivalry behavior. Our proposed model aggregates objective and social perception mechanisms to derive a rivalry score that is used to modulate the learning of artificial agents. To investigate our proposed model, we design an interactive game scenario, using the Chef's Hat Card Game, and examine how the rivalry modulation changes the agent's playing style, and how this impacts the experience of human players in the game. Our results show that humans can detect specific social characteristics when playing against rival agents when compared to common agents, which directly affects the performance of the human players in subsequent games. We conclude our work by discussing how the different social and objective features that compose the artificial rivalry score contribute to our results.

cs.AI↗

arXiv2022

CIAO! A Contrastive Adaptation Mechanism for Non-Universal Facial Expression Recognition

Current facial expression recognition systems demand an expensive re-training routine when deployed to different scenarios than they were trained for. Biasing them towards learning specific facial characteristics, instead of performing typical transfer learning methods, might help these systems to maintain high performance in different tasks, but with a reduced training effort. In this paper, we propose Contrastive Inhibitory Adaptati On (CIAO), a mechanism that adapts the last layer of facial encoders to depict specific affective characteristics on different datasets. CIAO presents an improvement in facial expression recognition performance over six different datasets with very unique affective representations, in particular when compared with state-of-the-art models. In our discussions, we make an in-depth analysis of how the learned high-level facial features are represented, and how they contribute to each individual dataset's characteristics. We finalize our study by discussing how CIAO positions itself within the range of recent findings on non-universal facial expressions perception, and its impact on facial expression recognition research.

cs.CV↗

arXiv2021

Generating Data Augmentation samples for Semantic Segmentation of Salt Bodies in a Synthetic Seismic Image Dataset

Nowadays, subsurface salt body localization and delineation, also called semantic segmentation of salt bodies, are among the most challenging geophysicist tasks. Thus, identifying large salt bodies is notoriously tricky and is crucial for identifying hydrocarbon reservoirs and drill path planning. This work proposes a Data Augmentation method based on training two generative models to augment the number of samples in a seismic image dataset for the semantic segmentation of salt bodies. Our method uses deep learning models to generate pairs of seismic image patches and their respective salt masks for the Data Augmentation. The first model is a Variational Autoencoder and is responsible for generating patches of salt body masks. The second is a Conditional Normalizing Flow model, which receives the generated masks as inputs and generates the associated seismic image patches. We evaluate the proposed method by comparing the performance of ten distinct state-of-the-art models for semantic segmentation, trained with and without the generated augmentations, in a dataset from two synthetic seismic images. The proposed methodology yields an average improvement of 8.57% in the IoU metric across all compared models. The best result is achieved by a DeeplabV3+ model variant, which presents an IoU score of 95.17% when trained with our augmentations. Additionally, our proposal outperformed six selected data augmentation methods, and the most significant improvement in the comparison, of 9.77%, is achieved by composing our DA with augmentations from an elastic transformation. At last, we show that the proposed method is adaptable for a larger context size by achieving results comparable to the obtained on the smaller context size.

cs.CV↗

arXiv2021

I Only Have Eyes for You: The Impact of Masks On Convolutional-Based Facial Expression Recognition

The current COVID-19 pandemic has shown us that we are still facing unpredictable challenges in our society. The necessary constrain on social interactions affected heavily how we envision and prepare the future of social robots and artificial agents in general. Adapting current affective perception models towards constrained perception based on the hard separation between facial perception and affective understanding would help us to provide robust systems. In this paper, we perform an in-depth analysis of how recognizing affect from persons with masks differs from general facial expression perception. We evaluate how the recently proposed FaceChannel adapts towards recognizing facial expressions from persons with masks. In Our analysis, we evaluate different training and fine-tuning schemes to understand better the impact of masked facial expressions. We also perform specific feature-level visualization to demonstrate how the inherent capabilities of the FaceChannel to learn and combine facial features change when in a constrained social interaction scenario.

cs.CV↗

arXiv2021

A Sub-Layered Hierarchical Pyramidal Neural Architecture for Facial Expression Recognition

In domains where computational resources and labeled data are limited, such as in robotics, deep networks with millions of weights might not be the optimal solution. In this paper, we introduce a connectivity scheme for pyramidal architectures to increase their capacity for learning features. Experiments on facial expression recognition of unseen people demonstrate that our approach is a potential candidate for applications with restricted resources, due to good generalization performance and low computational cost. We show that our approach generalizes as well as convolutional architectures in this task but uses fewer trainable parameters and is more robust for low-resolution faces.

cs.CV↗

arXiv2021

An Ensemble with Shared Representations Based on Convolutional Networks for Continually Learning Facial Expressions

Social robots able to continually learn facial expressions could progressively improve their emotion recognition capability towards people interacting with them. Semi-supervised learning through ensemble predictions is an efficient strategy to leverage the high exposure of unlabelled facial expressions during human-robot interactions. Traditional ensemble-based systems, however, are composed of several independent classifiers leading to a high degree of redundancy, and unnecessary allocation of computational resources. In this paper, we proposed an ensemble based on convolutional networks where the early layers are strong low-level feature extractors, and their representations shared with an ensemble of convolutional branches. This results in a significant drop in redundancy of low-level features processing. Training in a semi-supervised setting, we show that our approach is able to continually learn facial expressions through ensemble predictions using unlabelled samples from different data distributions.

cs.CV↗

arXiv2021

Disambiguating Affective Stimulus Associations for Robot Perception and Dialogue

Effectively recognising and applying emotions to interactions is a highly desirable trait for social robots. Implicitly understanding how subjects experience different kinds of actions and objects in the world is crucial for natural HRI interactions, with the possibility to perform positive actions and avoid negative actions. In this paper, we utilize the NICO robot's appearance and capabilities to give the NICO the ability to model a coherent affective association between a perceived auditory stimulus and a temporally asynchronous emotion expression. This is done by combining evaluations of emotional valence from vision and language. NICO uses this information to make decisions about when to extend conversations in order to accrue more affective information if the representation of the association is not coherent. Our primary contribution is providing a NICO robot with the ability to learn the affective associations between a perceived auditory stimulus and an emotional expression. NICO is able to do this for both individual subjects and specific stimuli, with the aid of an emotion-driven dialogue system that rectifies emotional expression incoherences. The robot is then able to use this information to determine a subject's enjoyment of perceived auditory stimuli in a real HRI scenario.

cs.RO↗

arXiv2020

Incorporating Rivalry in Reinforcement Learning for a Competitive Game

Recent advances in reinforcement learning with social agents have allowed us to achieve human-level performance on some interaction tasks. However, most interactive scenarios do not have as end-goal performance alone; instead, the social impact of these agents when interacting with humans is as important and, in most cases, never explored properly. This preregistration study focuses on providing a novel learning mechanism based on a rivalry social impact. Our scenario explored different reinforcement learning-based agents playing a competitive card game against human players. Based on the concept of competitive rivalry, our analysis aims to investigate if we can change the assessment of these agents from a human perspective.

cs.AI↗

arXiv2020

Affect-Driven Modelling of Robot Personality for Collaborative Human-Robot Interactions

Collaborative interactions require social robots to adapt to the dynamics of human affective behaviour. Yet, current approaches for affective behaviour generation in robots focus on instantaneous perception to generate a one-to-one mapping between observed human expressions and static robot actions. In this paper, we propose a novel framework for personality-driven behaviour generation in social robots. The framework consists of (i) a hybrid neural model for evaluating facial expressions and speech, forming intrinsic affective representations in the robot, (ii) an Affective Core, that employs self-organising neural models to embed robot personality traits like patience and emotional actuation, and (iii) a Reinforcement Learning model that uses the robot's affective appraisal to learn interaction behaviour. For evaluation, we conduct a user study (n = 31) where the NICO robot acts as a proposer in the Ultimatum Game. The effect of robot personality on its negotiation strategy is witnessed by participants, who rank a patient robot with high emotional actuation higher on persistence, while an inert and impatient robot higher on its generosity and altruistic behaviour.

cs.RO↗