12 papers · 1 filter
Probabilistic Multi-Source Data Selection via Learnable Categorical Priors: Variance Reduction and Guaranteed Derandomization
Shizhan Cai, Qixin Zhang, Siyuan Ma +3
Bilevel data selection is a fundamental task with numerous applications in machine learning and statistics. A common strategy for tackling this problem is to relax the original bil…
Restricted Eigenvalues Beyond Gaussian Width: Threshold Occupancy under Heavy Tails
Shi Fu, Huibo Xu, Qixin Zhang +1
Restricted eigenvalue (RE) bounds govern stable recovery by norm-regularized estimators. For isotropic sub-Gaussian measurements, the benchmark sample size is , where $w(…
Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine
Wei Huang, Andi Han, Mingyuan Bai +4
Diffusion models generate high-dimensional data with remarkable quality, yet how their training efficiently learns the score function, bypassing the curse of dimensionality when da…
Discovering Physical Directions in Weight Space: Composing Neural PDE Experts
Pengkai Wang, Pengwei Liu, Yuanyi Wang +7
Recent advances in neural operators have made partial differential equation (PDE) surrogate modeling increasingly scalable and transferable through large-scale pretraining and in-c…
CMKL: Modality-Aware Continual Learning for Evolving Biomedical Knowledge Graphs
Yousef A. Radwan, Yao Li, Qing Qing +5
Biomedical knowledge graphs are increasingly large, dynamic, and multimodal, driven by rapid advances in biotechnology such as high-throughput sequencing. Machine learning models c…
Learning Multi-Relational Graph Representations for DNA Methylation-Based Biological Age Estimation
Qing Qing, Xikun Zhang, Zhongyuan Zhang +7
Aging clocks aim to estimate biological age, a measure of physiological state distinct from chronological age, from observable biomarkers, and are widely used for health assessment…
Multinoulli Extension: A Lossless Continuous Relaxation for Partition-Constrained Subset Selection
Qixin Zhang, Wei Huang, Yan Sun +3
Identifying the most representative subset for a close-to-submodular objective while satisfying the predefined partition constraint is a fundamental task with numerous applications…
Near-Oracle KV Selection via Pre-hoc Sparsity for Long-Context Inference
Yifei Gao, Lei Wang, Rong-Cheng Tu +3
A core bottleneck in large language model (LLM) inference is the cost of attending over the ever-growing key-value (KV) cache. Although near-oracle top-k KV selection can preserve…
Efficient Differentiable Causal Discovery via Reliable Super-Structure Learning
Pingchuan Ma, Qixin Zhang, Shuai Wang +1
Recently, differentiable causal discovery has emerged as a promising approach to improve the accuracy and efficiency of existing methods. However, when applied to high-dimensional…
MaskPro: Linear-Space Probabilistic Learning for Strict (N:M)-Sparsity on LLMs
Yan Sun, Qixin Zhang, Zhiyuan Yu +3
The rapid scaling of large language models~(LLMs) has made inference efficiency a primary bottleneck in the practical deployment. To address this, semi-structured sparsity offers a…
Convergent Differential Privacy Analysis for General Federated Learning
Yan Sun, Qixin Zhang, Li Shen +1
The powerful cooperation of federated learning (FL) and differential privacy~(DP) provides a promising paradigm for the large-scale private clients. However, existing analyses in F…
Contextual Bandits for Unbounded Context Distributions
Puning Zhao, Rongfei Fan, Shaowei Wang +4
Nonparametric contextual bandit is an important model of sequential decision making problems. Under -Tsybakov margin condition, existing research has established a regret bound…