5 citations · 8 across the 17 of their papers we have counts for
20 papers
BRIDGE: Bilevel Retrieval-Credit-Aware Agentic Reinforcement Learning
Quan Xiao, Mingda Liu, Gaowen Liu +2
Agentic reinforcement learning (ARL) with verifiable rewards improves the ability of large language models (LLMs) to tackle knowledge-intensive tasks by learning to interleave sear…
Optimization under Persistent State-Dependent Bias: Gradient-based Method and Complexity Analysis
Zhaoxian Wu, Quan Xiao, Tayfun Gokmen +1
This paper studies the convergence of stochastic gradient descent (SGD) when the implemented updates are subject to a persistent and state-dependent bias, in which the desired upda…
ARMOR: Adaptive Retriever Optimization for Low-Resource Telecom Question Answering
Heshan Fernando, Quan Xiao, Yan Xin +1
Telecom question answering (QA) is a challenging setting for retrieval-augmented generation (RAG): evidence is fragmented across standards, papers, encyclopedic resources, and web…
Ada2MS: A Hybrid Optimization Algorithm Based on Exponential Mixing of Elementwise and Global Second-Moment Estimates
Meng Zhu, Quan Xiao, Weidong Min
Optimization algorithms are core methods by which machine learning models iteratively minimize loss functions, update parameters, learn from data, and improve performance. Momentum…
Dynamic Symmetric Point Tracking: Tackling Non-ideal Reference in Analog In-memory Training
Quan Xiao, Jindan Li, Zhaoxian Wu +2
Analog in-memory computing (AIMC) performs computation directly within resistive crossbar arrays, offering an energy-efficient platform to scale large vision and language models. H…
Efficient Penalty-Based Bilevel Methods: Improved Analysis, Novel Updates, and Flatness Condition
Liuyuan Jiang, Quan Xiao, Lisha Chen +1
Penalty-based methods have become popular for solving bilevel optimization (BLO) problems, thanks to their effective first-order nature. However, they often require inner-loop iter…
Bilevel Data Curation for LLM Fine-tuning: Offline Selection and Online Self-Refining Generation
Quan Xiao, Yutong Xuan, Gaowen Liu +2
Supervised fine-tuning (SFT) datasets are critical to the downstream performance of large language models, yet they often contain low-quality or harmful question-response pairs. To…
AdamNX: An Adam improvement algorithm based on a novel exponential decay mechanism for the second-order moment estimate
Meng Zhu, Quan Xiao, Weidong Min
This paper studies the exponential decay mechanism of the second-moment estimate in Adam. We propose AdamNX and a time-varying second-moment decay rate that gradually weakens the c…
Balancing Multi-modal Sensor Learning via Multi-objective Optimization
Heshan Fernando, Quan Xiao, Parikshit Ram +4
Learning-enabled control systems increasingly rely on multiple sensing modalities (e.g., vision, audio, language, etc.) for perception and decision support. A key challenge is that…
Beyond Value Functions: Single-Loop Bilevel Optimization under Flatness Conditions
Liuyuan Jiang, Quan Xiao, Lisha Chen +1
Bilevel optimization, a hierarchical optimization paradigm, has gained significant attention in a wide range of practical applications, notably in the fine-tuning of generative mod…
The Consistency Hypothesis in Uncertainty Quantification for Large Language Models
Quan Xiao, Debarun Bhattacharjya, Balaji Ganesan +5
Estimating the confidence of large language model (LLM) outputs is essential for real-world applications requiring high user trust. Black-box uncertainty quantification (UQ) method…
Efficient First-Order Optimization on the Pareto Set for Multi-Objective Learning under Preference Guidance
Lisha Chen, Quan Xiao, Ellen Hidemi Fukuda +3
Multi-objective learning under user-specified preference is common in real-world problems such as multi-lingual speech recognition under fairness. In this work, we frame such a pro…
A First-order Generative Bilevel Optimization Framework for Diffusion Models
Quan Xiao, Hui Yuan, A F M Saif +4
Diffusion models, which iteratively denoise data samples to synthesize high-quality outputs, have achieved empirical success across domains. However, optimizing these models for do…
Analog In-memory Training on General Non-ideal Resistive Elements: The Impact of Response Functions
Zhaoxian Wu, Quan Xiao, Tayfun Gokmen +2
As the economic and environmental costs of training and deploying large vision or language models increase dramatically, analog in-memory computing (AIMC) emerges as a promising en…
On the Convergence Theory of Pipeline Gradient-based Analog In-memory Training
Zhaoxian Wu, Quan Xiao, Tayfun Gokmen +3
Aiming to accelerate the training of large deep neural networks (DNN) in an energy-efficient way, analog in-memory computing (AIMC) emerges as a solution with immense potential. AI…
Unlocking Global Optimality in Bilevel Optimization: A Pilot Study
Quan Xiao, Tianyi Chen
Bilevel optimization has witnessed a resurgence of interest, driven by its critical role in trustworthy and efficient AI applications. While many recent works have established conv…
A Primal-Dual-Assisted Penalty Approach to Bilevel Optimization with Coupled Constraints
Liuyuan Jiang, Quan Xiao, Victor M. Tenorio +3
Interest in bilevel optimization has grown in recent years, partially due to its applications to tackle challenging machine-learning problems. Several exciting recent works have be…
A Bilevel Optimization Method for Inverse Mean-Field Games
Jiajia Yu, Quan Xiao, Tianyi Chen +1
In this paper, we introduce a bilevel optimization framework for addressing inverse mean-field games, alongside an exploration of numerical methods tailored for this bilevel proble…
A Generalized Alternating Method for Bilevel Learning under the Polyak-Łojasiewicz Condition
Quan Xiao, Songtao Lu, Tianyi Chen
Bilevel optimization has recently regained interest owing to its applications in emerging machine learning fields such as hyperparameter optimization, meta-learning, and reinforcem…
On Penalty-based Bilevel Gradient Descent Method
Han Shen, Quan Xiao, Tianyi Chen
Bilevel optimization enjoys a wide range of applications in emerging machine learning and signal processing problems such as hyper-parameter optimization, image reconstruction, met…