338 citations · 1.4k across the 188 of their papers we have counts for
43 papers · 1 filter
Efficient Linear Bandits via Cluster-Aware Sketching
Hantao Yang, Hong Xie, Defu Lian
We study the problem of computational efficiency for linear bandits in high-dimensional settings with a finite arm set. In linear bandits, the increase in the dimension of the…
Support Selection Beyond Smooth DAG Exactness: Completion Geometry,Score Margins, and Selective Certificates
Rui Wu, Zongyuan Chen, Hong Xie +2
Smooth acyclicity constraints answer whether a weighted support is a DAG, whereas structure learning asks which support change should be made. Existing analyses establish degenerac…
CR: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse Autoencoders
Haoran Jin, Xiting Wang, Shijie Ren +2
Sparse Autoencoders (SAEs) are widely used to interpret large language models by decomposing activations into sparse, human-understandable features, but scaling to large dictionari…
RAVEN: A Regime-Aware Variable-context Expert Network for Financial Time Series Forecasting
Cheng He, Zhenyu Guan, Xijie Liang +6
Financial time series forecasting presents structural challenges absent from standard benchmarks. Log-returns are non-stationary, exhibit exceptionally low signal-to-noise (SNR) ra…
Learning Generated Controls under Fractured Geometry: Projective Residualization and Variation-Allocation Frontiers
Rui Wu, Zongyuan Chen, Hong Xie +2
Many two-stage estimators assess the first-stage learner by prediction error, even when the next stage uses its residual. In control-function instrumental variables, that residual…
Representation-Guided Discrete Molecular Graph Retrosynthesis
Jiahai Huang, Anjie Qiao, Zhen Wang +2
Stochastic process-based molecular graph generators have become the state of the art for template-free single-step retrosynthesis. However, these models are typically trained only…
CastFlow: Bridging Evidence Acquisition and Accurate Prediction in Agentic Time Series Forecasting
Bokai Pan, Mingyue Cheng, Zhiding Liu +6
Time series forecasting is a fundamental task in temporal data analytics, and large language model (LLM)-based agents offer a promising paradigm through autonomous tool interaction…
Scaling Federated Linear Contextual Bandits via Sketching
Hantao Yang, Hong Xie, Xutong Liu +1
In federated contextual linear bandits, high data dimensionality incurs prohibitive computation and communication costs: local agents perform -time determinant computation…
Beyond Surrogates: A Quantitative Analysis for Inter-Metric Relationships
Yuanhao Pu, Defu Lian, Enhong Chen
The Consistency property between surrogate losses and evaluation metrics has been extensively studied to ensure that minimizing a loss leads to metric optimality. However, the dire…
Is Softmax Loss All You Need? A Principled Analysis of Softmax-family Loss
Yuanhao Pu, Defu Lian, Enhong Chen
The Softmax loss is one of the most widely employed surrogate objectives for classification and ranking tasks. To elucidate its theoretical properties, the Fenchel-Young framework…
Demystifying Design Choices of Reinforcement Fine-tuning: A Batched Contextual Bandit Learning Perspective
Hong Xie, Xiao Hu, Tao Tan +5
The reinforcement fine-tuning area is undergoing an explosion papers largely on optimizing design choices. Though performance gains are often claimed, inconsistent conclusions also…
Rethinking Reinforcement fine-tuning of LLMs: A Multi-armed Bandit Learning Perspective
Xiao Hu, Hong Xie, Tao Tan +2
A large number of heuristics have been proposed to optimize the reinforcement fine-tuning of LLMs. However, inconsistent claims are made from time to time, making this area elusive…
PiXTime: A Model for Federated Time Series Forecasting with Heterogeneous Data across Nodes
Yiming Zhou, Jiahao Wang, Mingyue Cheng +3
While collaborative forecasting on distributed time series is highly desirable, directly pooling localized datasets is often impractical due to data sharing constraints. Federated…
A Unified Frequency Domain Decomposition Framework for Interpretable and Robust Time Series Forecasting
Cheng He, Xijie Liang, Zengrong Zheng +6
Current approaches for time series forecasting, whether in the time or frequency domain, predominantly use deep learning models based on linear layers or transformers. They often e…
Composable Score-based Graph Diffusion Model for Multi-Conditional Molecular Generation
Anjie Qiao, Zhen Wang, Chuan Chen +2
Controllable molecular graph generation is essential for material and drug discovery, where generated molecules must satisfy diverse property constraints. While recent advances in…
Efficient Machine Unlearning via Influence Approximation
Jiawei Liu, Chenwang Wu, Defu Lian +1
Due to growing privacy concerns, machine unlearning, which aims at enabling machine learning models to ``forget" specific training data, has received increasing attention. Among ex…
NDCG-Consistent Softmax Approximation with Accelerated Convergence
Yuanhao Pu, Defu Lian, Xiaolong Chen +3
Ranking tasks constitute fundamental components of extreme similarity learning frameworks, where extremely large corpora of objects are modeled through relative similarity relation…
How to Unlock Time Series Editing? Diffusion-Driven Approach with Multi-Grained Control
Hao Yu, Chu Xin Cheng, Runlong Yu +4
Recent advances in time series generation have shown promise, yet controlling properties in generated sequences remains challenging. Time Series Editing (TSE) - making precise modi…
Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning
Gangwei Jiang, Caigao Jiang, Zhaoyi Li +5
Catastrophic forgetting (CF) poses a significant challenge in machine learning, where a model forgets previously learned information upon learning new tasks. Despite the advanced c…
GTM: A General Time-series Model for Enhanced Representation Learning of Time-Series Data
Cheng He, Xu Huang, Gangwei Jiang +7
Despite recent progress in time-series foundation models, challenges persist in improving representation learning and adapting to diverse downstream tasks. We introduce a General T…
Adaptive Sampled Softmax with Inverted Multi-Index: Methods, Theory and Applications
Jin Chen, Jin Zhang, Xu huang +3
The softmax function is a cornerstone of multi-class classification, integral to a wide range of machine learning applications, from large-scale retrieval and ranking models to adv…
FilterNet: Harnessing Frequency Filters for Time Series Forecasting
Kun Yi, Jingru Fei, Qi Zhang +4
While numerous forecasters have been proposed using different network architectures, the Transformer-based models have state-of-the-art performance in time series forecasting. Howe…
Breaking Determinism: Fuzzy Modeling of Sequential Recommendation Using Discrete State Space Diffusion Model
Wenjia Xie, Hao Wang, Luankang Zhang +3
Sequential recommendation (SR) aims to predict items that users may be interested in based on their historical behavior sequences. We revisit SR from a novel information-theoretic…
ToolACE: Winning the Points of LLM Function Calling
Weiwen Liu, Xu Huang, Xingshan Zeng +24
Function calling significantly extends the application boundary of large language models, where high-quality and diverse training data is critical for unlocking this capability. Ho…