11 citations · 46 across the 19 of their papers we have counts for
19 papers
Heavy-Tailed Flow Matching via Random Clocks
Zhouhao Yang, Yezhen Wang, Kenji Kawaguchi +2
Heavy-tailed data arise in many domains where rare events carry disproportionate importance, such as imbalanced image datasets, financial returns, and weather extremes. Standard di…
Diffusion Models for Adaptive Sequential Data Generation
Haoyang Cao, Minshuo Chen, Yinbin Han +1
Generating realistic synthetic sequential data is critical in real-world applications across operations research, finance, healthcare, energy systems, and scientific computing, whe…
Sample Complexity of Transfer Learning: An Optimal Transport Approach
Haoyang Cao, Xin Guo, Wenpin Tang +1
Transfer learning is an essential technique for many machine learning/AI models of complex structures such as large language models and generative AI. The essence of transfer learn…
Scalable Bi-causal Optimal Transport via KL Relaxation and Policy Gradients
Haoyang Cao, Jesse Hoekstra, Renyuan Xu +2
Bi-causal optimal transport (OT) is a natural framework for comparing and coupling stochastic processes under nonanticipative information constraints, with important applications i…
Risk of Transfer Learning and its Applications in Finance
Haoyang Cao, Haotian Gu, Xin Guo +1
Transfer learning is an emerging and popular paradigm for utilizing existing knowledge from previous learning tasks to improve the performance of new ones. In this paper, we propos…
Transfer Learning for Portfolio Optimization
Haoyang Cao, Haotian Gu, Xin Guo +1
In this work, we explore the possibility of utilizing transfer learning techniques to address the financial portfolio optimization problem. We introduce a novel concept called "tra…
Feasibility of Transfer Learning: A Mathematical Framework
Haoyang Cao, Haotian Gu, Xin Guo
Transfer learning is a popular paradigm for utilizing existing knowledge from previous learning tasks to improve the performance of new ones. It has enjoyed numerous empirical succ…
Feasibility and Transferability of Transfer Learning: A Mathematical Framework
Haoyang Cao, Haotian Gu, Xin Guo +1
Transfer learning is an emerging and popular paradigm for utilizing existing knowledge from previous learning tasks to improve the performance of new ones. Despite its numerous emp…
Towards mapping the contemporary art world with ArtLM: an art-specific NLP model
Qinkai Chen, Mohamed El-Mennaoui, Antoine Fosset +6
With an increasing amount of data in the art world, discovering artists and artworks suitable to collectors' tastes becomes a challenge. It is no longer enough to use visual inform…
Meta-learning with GANs for anomaly detection, with deployment in high-speed rail inspection system
Haoyang Cao, Xin Guo, Guan Wang
Anomaly detection has been an active research area with a wide range of potential applications. Key challenges for anomaly detection in the AI era with big data include lack of pri…
Approximation of N-player stochastic games with singular controls by mean field games
Haoyang Cao, Xin Guo, Joon Seok Lee
This paper establishes that a class of -player stochastic games with singular controls, either of bounded velocity or of finite variation, can both be approximated by mean field…
Identifiability in inverse reinforcement learning
Haoyang Cao, Samuel N. Cohen, Lukasz Szpruch
Inverse reinforcement learning attempts to reconstruct the reward function in a Markov decision problem, using observations of agent actions. As already observed in Russell [1998]…
Stationary Discounted and Ergodic Mean Field Games of Singular Control
Haoyang Cao, Jodi Dianetti, Giorgio Ferrari
We study stationary mean field games with singular controls in which the representative player interacts with a long-time weighted average of the population through a discounted an…
Generative Adversarial Network: Some Analytical Perspectives
Haoyang Cao, Xin Guo
Ever since its debut, generative adversarial networks (GANs) have attracted tremendous amount of attention. Over the past years, different variations of GANs models have been devel…
SDE approximations of GANs training and its long-run behavior
Haoyang Cao, Xin Guo
This paper analyzes the training process of GANs via stochastic differential equations (SDEs). It first establishes SDE approximations for the training of GANs under stochastic gra…
Connecting GANs, MFGs, and OT
Haoyang Cao, Xin Guo, Mathieu Laurière
Generative adversarial networks (GANs) have enjoyed tremendous success in image generation and processing, and have recently attracted growing interests in financial modelings. Thi…
MFGs for partially reversible investment
Haoyang Cao, Xin Guo
This paper analyzes a class of infinite-time-horizon stochastic games with singular controls motivated from the partially reversible problem. It provides an explicit solution for t…
Nonzero-sum stochastic games and mean-field games with impulse controls
Matteo Basei, Haoyang Cao, Xin Guo
We consider a general class of nonzero-sum -player stochastic games with impulse controls, where players control the underlying dynamics with discrete interventions. We adopt a…
Approximation of Mean Field Games to N-Player Stochastic Games, with Singular Controls
Haoyang Cao, Xin Guo, Joon Seok Lee
This paper establishes that -player stochastic games with singular controls, either of bounded velocity or of finite variation, can both be approximated by mean field games (MFG…