12 citations · 31 across the 20 of their papers we have counts for
21 papers
A Survey of Flow Matching in Reinforcement Learning
Nabuat Zaman Nahim, Fairoz Nower Khan, Peizhong Ju
Flow Matching (FM) has recently emerged as a principled and efficient generative modeling framework for reinforcement learning (RL), enabling expressive, multimodal policy paramete…
Flow Matching with Missing Data
Fairoz Nower Khan, Nabuat Zaman Nahim, Peizhong Ju
Flow matching assumes fully observed training data, which many real-world applications rarely provide. We study Missing-Data Flow Matching, which treats the missing coordinates of…
FoA-SR: Faithful or Aesthetic? Profile-Aware Preference Optimization for Real-World Image Super-Resolution
Amjad Mahdi Alqarni, Peizhong Ju
Real-world image super-resolution (SR) is often designed with a single restoration objective, despite the current capacity of generative models to produce multiple high-quality rec…
Discrete MeanFlow: One-Step Generation via Conditional Transition Kernels
Fairoz Nower Khan, Nabuat Zaman Nahim, Md Sajid Ahmed +2
MeanFlow enables one-step generation in continuous spaces by learning an average velocity over a time interval rather than the instantaneous velocity field of flow matching. Howeve…
Discrete Flow Matching for Offline-to-Online Reinforcement Learning
Fairoz Nower Khan, Nabuat Zaman Nahim, Peizhong Ju
Many reinforcement learning (RL) tasks have discrete action spaces, but most generative policy methods based on diffusion and flow matching are designed for continuous control. Mea…
Flow Matching for Offline Reinforcement Learning with Discrete Actions
Fairoz Nower Khan, Nabuat Zaman Nahim, Ruiquan Huang +2
Generative policies based on diffusion models and flow matching have shown strong promise for offline reinforcement learning (RL), but their applicability remains largely confined…
Optimal Parallel Scheduling under Concave Speedup Functions
Chengzhang Li, Peizhong Ju, Atilla Eryilmaz +1
Efficient scheduling of parallel computation resources across multiple jobs is a fundamental problem in modern cloud/edge computing systems for many AI-based applications. Allocati…
Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective
Junze Deng, Qinhang Wu, Peizhong Ju +3
Rehearsal-based methods have shown superior performance in addressing catastrophic forgetting in continual learning (CL) by storing and training on a subset of past data alongside…
BeST -- A Novel Source Selection Metric for Transfer Learning
Ashutosh Soni, Peizhong Ju, Atilla Eryilmaz +1
One of the most fundamental, and yet relatively less explored, goals in transfer learning is the efficient means of selecting top candidates from a large number of previously train…
How to Find the Exact Pareto Front for Multi-Objective MDPs?
Yining Li, Peizhong Ju, Ness B. Shroff
Multi-Objective Markov Decision Processes (MO-MDPs) are receiving increasing attention, as real-world decision-making problems often involve conflicting objectives that cannot be a…
Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers
Yuchen Liang, Peizhong Ju, Yingbin Liang +1
The denoising diffusion model has recently emerged as a powerful generative technique, capable of transforming noise into meaningful data. While theoretical convergence guarantees…
Can We Theoretically Quantify the Impacts of Local Updates on the Generalization Performance of Federated Learning?
Peizhong Ju, Haibo Yang, Jia Liu +2
Federated Learning (FL) has gained significant popularity due to its effectiveness in training machine learning models across diverse sites without requiring direct data sharing. W…
Broadening Target Distributions for Accelerated Diffusion Models via a Novel Analysis Approach
Yuchen Liang, Peizhong Ju, Yingbin Liang +1
Accelerated diffusion models hold the potential to significantly enhance the efficiency of standard diffusion processes. Theoretically, these models have been shown to achieve fast…
Achieving Sample and Computational Efficient Reinforcement Learning by Action Space Reduction via Grouping
Yining Li, Peizhong Ju, Ness Shroff
Reinforcement learning often needs to deal with the exponential growth of states and actions when exploring optimal control in high-dimensional spaces (often known as the curse of…
Generalization Performance of Transfer Learning: Overparameterized and Underparameterized Regimes
Peizhong Ju, Sen Lin, Mark S. Squillante +2
Transfer learning is a useful technique for achieving improved performance and reducing training costs by leveraging the knowledge gained from source tasks and applying it to targe…
Achieving Fairness in Multi-Agent Markov Decision Processes Using Reinforcement Learning
Peizhong Ju, Arnob Ghosh, Ness B. Shroff
Fairness plays a crucial role in various multi-agent systems (e.g., communication networks, financial markets, etc.). Many multi-agent dynamical interactions can be cast as Markov…
Theoretical Characterization of the Generalization Performance of Overfitted Meta-Learning
Peizhong Ju, Yingbin Liang, Ness B. Shroff
Meta-learning has arisen as a successful method for improving training performance by training over many similar tasks, especially with deep neural networks (DNNs). However, the th…
Theory on Forgetting and Generalization of Continual Learning
Sen Lin, Peizhong Ju, Yingbin Liang +1
Continual learning (CL), which aims to learn a sequence of tasks, has attracted significant recent attention. However, most work has focused on the experimental performance of CL,…
On the Generalization Power of the Overfitted Three-Layer Neural Tangent Kernel Model
Peizhong Ju, Xiaojun Lin, Ness B. Shroff
In this paper, we study the generalization performance of overparameterized 3-layer NTK models. We show that, for a specific set of ground-truth functions (which we refer to as the…
On the Generalization Power of Overfitted Two-Layer Neural Tangent Kernel Models
Peizhong Ju, Xiaojun Lin, Ness B. Shroff
In this paper, we study the generalization performance of min -norm overfitting solutions for the neural tangent kernel (NTK) model of a two-layer neural network with ReLU…
Overfitting Can Be Harmless for Basis Pursuit, But Only to a Degree
Peizhong Ju, Xiaojun Lin, Jia Liu
Recently, there have been significant interests in studying the so-called "double-descent" of the generalization error of linear regression models under the overparameterized and o…