arXiv subjects

Jiali Ma

Publications and source records attributed to Jiali Ma.

4 recordsLinked to original sources

arXiv2025

Aligned Contrastive Loss for Long-Tailed Recognition

In this paper, we propose an Aligned Contrastive Learning (ACL) algorithm to address the long-tailed recognition problem. Our findings indicate that while multi-view training boosts the performance, contrastive learning does not consistently enhance model generalization as the number of views increases. Through theoretical gradient analysis of supervised contrastive learning (SCL), we identify gradient conflicts, and imbalanced attraction and repulsion gradients between positive and negative pairs as the underlying issues. Our ACL algorithm is designed to eliminate these problems and demonstrates strong performance across multiple benchmarks. We validate the effectiveness of ACL through experiments on long-tailed CIFAR, ImageNet, Places, and iNaturalist datasets. Results show that ACL achieves new state-of-the-art performance.

cs.CV↗

arXiv2023

Invariant Feature Regularization for Fair Face Recognition

Fair face recognition is all about learning invariant feature that generalizes to unseen faces in any demographic group. Unfortunately, face datasets inevitably capture the imbalanced demographic attributes that are ubiquitous in real-world observations, and the model learns biased feature that generalizes poorly in the minority group. We point out that the bias arises due to the confounding demographic attributes, which mislead the model to capture the spurious demographic-specific feature. The confounding effect can only be removed by causal intervention, which requires the confounder annotations. However, such annotations can be prohibitively expensive due to the diversity of the demographic attributes. To tackle this, we propose to generate diverse data partitions iteratively in an unsupervised fashion. Each data partition acts as a self-annotated confounder, enabling our Invariant Feature Regularization (INV-REG) to deconfound. INV-REG is orthogonal to existing methods, and combining INV-REG with two strong baselines (Arcface and CIFP) leads to new state-of-the-art that improves face recognition on a variety of demographic groups. Code is available at https://github.com/PanasonicConnect/InvReg.

cs.CV↗

arXiv2022

Optimal Systemic Risk Bailout: A PGO Approach Based on Neural Network

In the financial system, bailout strategies play a pivotal role in mitigating substantial losses resulting from systemic risk. However, the lack of a closed-form objective function to the optimal bailout problem poses significant challenges in its resolution. This paper conceptualizes the optimal bailout (capital injection) problem as a black-box optimization task, where the black box is modeled as a fixed-point system consistent with the E-N framework for measuring systemic risk in the financial system. To address this challenge, we propose a novel framework, "Prediction-Gradient-Optimization" (PGO). Within PGO, the Prediction employs a neural network to approximate and forecast the objective function implied by the black box, which can be completed offline; For the online usage, the Gradient step derives gradient information from this approximation, and the Optimization step uses a gradient projection algorithm to solve the problem effectively. Extensive numerical experiments highlight the effectiveness of the proposed approach in managing systemic risk.

q-fin.RM↗

arXiv2022

Systemic Risk of Optioned Portfolios: Controllability and Optimization

We investigate the portfolio selection problem against the systemic risk which is measured by CoVaR. We first demonstrate that the systemic risk of pure stock portfolios is essentially uncontrollable due to the contagion effect and the seesaw effect. Next, we prove that it is necessary and sufficient to introduce options to make the systemic risk controllable by the correlation hedging and the extreme loss hedging. In addition to systemic risk control, we show that using options can also enhance return-risk performance. Then, with a reasonable approximation of the conditional distribution of optioned portfolios, we show that the portfolio optimization problem can be formulated as a second-order cone program (SOCP) that allows for efficient computation. Finally, we carry out comprehensive simulations and empirical tests to illustrate the theoretical findings and the performance of our method.

q-fin.PM↗