40 citations · 88 across the 20 of their papers we have counts for
30 papers
Dimension-Optimal Dynamic Regret in Exp-Concave Online Learning
Yanyi Li, Wendao Wu, Haihan Zhang +6
Tracking changing comparators is a central problem in online learning. For exp-concave losses, previous work established the dependence on the horizon and Eu…
Not All Criteria Matter: Importance-Aware Criteria Weighting for Rubric-Based LLM Evaluation
Haocheng Yang, Licheng Pan, Yiming Dong +7
Rubric-based evaluation assesses the responses of large language models (LLMs) by aggregating the verification results of explicit criteria, yet not all criteria matter equally. Ho…
Matching Randomized First-Order Bounds for Higher-Order Smooth Nonconvex Optimization
Haihan Zhang, Wendao Wu, Fangqing Zhang +5
Does randomization improve the worst-case first-order complexity of nonconvex optimization when the objective is very smooth? We prove that, for every fixed finite integer ,…
Matching Randomized Bounds for Finite-Sum Nonconvex-Concave Optimization
Wendao Wu, Haihan Zhang, Qian Chen +5
We characterize the randomized component-oracle complexity of finite-sum nonconvex-concave optimization with a bounded dual domain. For $Φ(x)=\max_{y\in Y}n^{-1}\sum_{i=1}^n f_i(x,…
Matching Complexity for Second-Order Stationary Point with Sample Reuse
Qian Chen, Wendao Wu, Haihan Zhang +5
We consider stochastic nonconvex optimization with sample-wise Lipschitz gradients and Hessians, and reusable opaque sample handles. Gradient and complete-Hessian evaluations are c…
Matching Full-Hessian Oracle Complexity for Nonconvex--Strongly-Concave Minimax Optimization
Fangqing Zhang, Haihan Zhang, Wendao Wu +5
We characterize the oracle complexity of finding first-order stationary points in smooth nonconvex--strongly-concave (NC--SC) minimax optimization when each query provides the full…
RubricArmor: Adversarial Evolution Improves LLM-Based Rubric Generation
Haocheng Yang, Yuchao Zhang, Licheng Pan +8
Rubric-based reinforcement learning (RL) provides interpretable rewards for aligning large language models (LLMs) by evaluating responses against query-specific evaluation criteria…
The Minimax Cost of Smoothness in Fully First-Order Stochastic Bilevel Optimization
Wendao Wu, Haihan Zhang, Chenheng Zhang +5
We study the sample complexity of finding a point with expected hypergradient norm at most in nonconvex--strongly-convex stochastic bilevel optimization using fresh, globally…
Closing the Accuracy Gap in Stochastic First-Order Bilevel Optimization
Haihan Zhang, Wendao Wu, Chenheng Zhang +5
We characterize the optimal accuracy dependence for smooth nonconvex--strongly-convex bilevel optimization with stochastic first-order oracles. For globally unbiased fresh-gradient…
A Self-Triggered Agentic Push Recommendation System
Zhao-Yu Zhang, Qingying Chen, Chunyuan Zheng +9
Push notification is a critical recommendation scenario on large-scale platforms, allowing the system to proactively reach users outside the application to improve long-term re-eng…
Beyond Independent Manipulation: Individual Fairness-aware Strategic Classification with Peer Imitation
Xinpeng Lv, Chunyuan Zheng, Yunxin Mao +9
Strategic classification (SC) investigates scenarios where agents manipulate their features to obtain favorable decisions from predictive models. Existing fairness-aware SC approac…
PAFO: Pareto Fairness Optimization for Personalized Reward Modeling
Xiaoyan Zhao, Haoting Ni, Yang Zhang +3
Large language models (LLMs) increasingly rely on reward models to align their outputs with diverse user preferences. While personalized reward models aim to capture such heterogen…
Beyond Rational Illusion: Behaviorally Realistic Strategic Classification
Xinpeng Lv, Yunxin Mao, Renzhe Xu +11
Strategic classification(SC) studies the interaction between decision models and agents who strategically manipulate their features for favorable outcomes. Existing SC frameworks t…
When Tabular Foundation Models Meet Strategic Tabular Data: A Prior Alignment Approach
Xinpeng Lv, Yunxin Mao, Renzhe Xu +13
Tabular foundation models based on pretrained prior-data fitted networks~(PFNs) have shown strong generalization on diverse tabular tasks, but they are typically designed for \emph…
Partial Fairness Awareness: Belief-Guided Strategic Mechanism for Strategic Agents
Xinpeng Lv, Chunyuan Zheng, Yunxin Mao +8
Strategic machine learning investigates scenarios where agents manipulate their features to receive favorable decisions from predictive models. To address fairness concerns intrins…
Deep Time-Series Forecasting in 10 Years: A Survey
Hao Wang, Licheng Pan, Qingsong Wen +12
Autocorrelation is a common property of time-series, where each observation is dependent on its predecessors. In deep time-series forecasting, it raises two central challenges: (1)…
CausalRM: Causal-Theoretic Reward Modeling for RLHF from Observational User Feedbacks
Hao Wang, Licheng Pan, Zhichao Chen +7
Despite the success of reinforcement learning from human feedback (RLHF) in aligning language models, current reward modeling heavily relies on experimental feedback data collected…
Rethinking Personalization in Large Language Models at the Token Level
Chenheng Zhang, Yijun Lu, Lizhe Fang +7
With large language models (LLMs) now performing strongly across diverse tasks, there is growing demand for them to personalize outputs for individual users. Personalization is typ…
Detecting Unobserved Confounders: A Kernelized Regression Approach
Yikai Chen, Yunxin Mao, Chunyuan Zheng +7
Detecting unobserved confounders is crucial for reliable causal inference in observational studies. Existing methods require either linearity assumptions or multiple heterogeneous…
Learning Counterfactual Outcomes Under Rank Preservation
Peng Wu, Haoxuan Li, Chunyuan Zheng +5
Counterfactual inference aims to estimate the counterfactual outcome at the individual level given knowledge of an observed treatment and the factual outcome, with broad applicatio…
A Partial Initialization Strategy to Mitigate the Overfitting Problem in CATE Estimation with Hidden Confounding
Chuan Zhou, Yaxuan Li, Chunyuan Zheng +3
Estimating the conditional average treatment effect (CATE) from observational data plays a crucial role in areas such as e-commerce, healthcare, and economics. Existing studies mai…
Decomposing and Fusing Intra- and Inter-Sensor Spatio-Temporal Signal for Multi-Sensor Wearable Human Activity Recognition
Haoyu Xie, Haoxuan Li, Chunyuan Zheng +4
Wearable Human Activity Recognition (WHAR) is a prominent research area within ubiquitous computing. Multi-sensor synchronous measurement has proven to be more effective for WHAR t…
Debiased Recommendation with Noisy Feedback
Haoxuan Li, Chunyuan Zheng, Wenjie Wang +3
Ratings of a user to most items in recommender systems are usually missing not at random (MNAR), largely because users are free to choose which items to rate. To achieve unbiased l…
Be Aware of the Neighborhood Effect: Modeling Selection Bias under Interference
Haoxuan Li, Chunyuan Zheng, Sihao Ding +4
Selection bias in recommender system arises from the recommendation process of system filtering and the interactive process of user selection. Many previous studies have focused on…