1 citations · 1 across the 17 of their papers we have counts for
20 papers
PRIME: Towards Verifiable Evidence-Grounded Reasoning in LLM Agents
Hamed Khosravi, Xiaoming Huo
LLM agents are used to check records against an organization's requirements, for example whether a vulnerability report is ready for investigation. Requirements often allow several…
Certified Corruption Budgets: Anytime-Valid Leaderboard Claims under Adaptive Rigging
Hamed Khosravi, Xiaoming Huo
Public leaderboards for AI models are read continuously, and attackers can see every published standing. Vote rigging, selective disclosure of private variants, and benchmark conta…
Rank Confidence Sequences:Anytime-valid Leaderboards
Hamed Khosravi, Xiaoming Huo
Leaderboards rank models by their average scores on benchmark items, and they are consulted repeatedly while the evaluation is still running. Existing confidence intervals for a mo…
Beyond "AI Helps Humans": Decision-Targeted Evaluation Design for Human-Agent Teams in the Agentic Era
Hamed Khosravi, Xiaoming Huo
Wherever a coding agent works under engineer supervision, or a clinical model assists a radiologist, the deployment question is whether to keep the human-AI workflow or replace it…
Which LLM for Which Work? Budgeted Model Allocation under Uncertain Evaluation
Hamed Khosravi, Xiaoming Huo
A company with a fixed artificial intelligence (AI) budget must decide which large language model (LLM) handles each recurring workload. What it lacks is the quality table, how wel…
The Noise Premium in Adversarial Training for Kernel Regression
Yiling Xie, Xiaoming Huo
Adversarial training can improve the robustness of predictive models to bounded perturbations, often at the cost of statistical efficiency. We study this trade-off in kernel regres…
A Joint-Distribution Route to Fair Representations with Continuous Sensitive Attributes
Yijin Ni, Xiaoming Huo
Fair representation learning with a continuous sensitive attribute requires a representation that is statistically independent of . Existing criteria, including generali…
A Polyak-Ruppert Central Limit Theorem for SA-Adam with Momentum and Non-Convergent Adaptive Preconditioning
Sunyoung An, Xiaoming Huo
Adaptive optimizers combining preconditioning, momentum, and weight decay (Adam and AdamW) are, under Polyak-Ruppert averaging, candidate engines for one-pass inference. Does the a…
Matching Rates and Optimal Allocation for Federated Probe-Logit Distillation under Heterogeneous Bandwidth Budgets
Prasanjit Dubey, Xiaoming Huo
In federated language modeling, nodes each hold samples but cannot pool data or exchange full-precision gradients or weights. We study the minimax rate at which a condition…
Certified Adaptive Refresh: Anytime-Valid Monitoring for Federated Conformal RAG
Prasanjit Dubey, Xiaoming Huo
Question-answering services built on retrieval-augmented generation (RAG), in which a language model answers from retrieved documents, are inspected continuously and upgraded repea…
BOOST: Power-Optimal Strong-FWER Testing for Block-Structured Multiplicity
Prasanjit Dubey, Xiaoming Huo
Structured multiple-testing problems (gatekeeping trials, dose-finding, multi-tissue eQTL mapping, bundled-challenger A/B experiments) organize hypotheses into design-imposed block…
Federated Language Models Under Bandwidth Budgets: Distillation Rates and Conformal Coverage
Prasanjit Dubey, Xiaoming Huo
Hospitals, companies, and research consortia want language models that learn from, and answer questions over, data that must stay where it is held, over links with limited bandwidt…
Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMs
Hamed Khosravi, Xiaoming Huo
A local specialist LLM, fine-tuned with reinforcement learning from verifiable rewards (RLVR) on operator-local data, is installed in a regulated organization with per-deployment e…
Catching a Moving Subspace: Low-Rank Bandits Beyond Stationarity
Hamed Khosravi, Xiaoming Huo
Many bandit deployments (recommendation, clinical dosing, ad targeting) share two facts prior work handles only in isolation: rewards live on a low-dimensional latent subspace, and…
Kernel Selection is Model Selection: A Unified Complexity-Penalized Approach for MMD Two-Sample Tests
Yijin Ni, Xiaoming Huo
The Maximum Mean Discrepancy (MMD) is a cornerstone statistic for nonparametric two-sample testing, but its test power is dictated entirely by the chosen kernel. Because any fixed…
When Does Dynamic Preconditioning Preserve the Polyak-Ruppert CLT? A Stabilization Threshold
Sunyoung An, Xiaoming Huo
Polyak-Ruppert averaging yields an asymptotically normal estimator with sandwich covariance , the foundation of online inference. When the gradient step is precondit…
Towards Domain Adaptive Neural Contextual Bandits
Ziyan Wang, Xiaoming Huo, Hao Wang
Contextual bandit algorithms are essential for solving real-world decision making problems. In practice, collecting a contextual bandit's feedback from different domains may involv…
High-dimensional (Group) Adversarial Training in Linear Regression
Yiling Xie, Xiaoming Huo
Adversarial training can achieve robustness against adversarial perturbations and has been widely used in machine learning models. This paper delivers a non-asymptotic consistency…
Universal Consistency of Wide and Deep ReLU Neural Networks and Minimax Optimal Convergence Rates for Kolmogorov-Donoho Optimal Function Classes
Hyunouk Ko, Xiaoming Huo
In this paper, we prove the universal consistency of wide and deep ReLU neural network classifiers trained on the logistic loss. We also give sufficient conditions for a class of p…
Asymptotic Behavior of Adversarial Training Estimator under -Perturbation
Yiling Xie, Xiaoming Huo
Adversarial training has been proposed to protect machine learning models against adversarial attacks. This paper focuses on adversarial training under -perturbation,…