Y. R. Hou

Yunlong Hou, Fengzhuo Zhang, Cunxiao Du et al.

Speculative decoding has emerged as a popular method to accelerate the inference of Large Language Models (LLMs) while retaining their superior text generation performance. Previous methods either adopt a fixed speculative decoding configuration regardless of the prefix tokens, or train draft models in an offline or online manner to align them with the context. This paper proposes a training-free online learning framework to adaptively choose the configuration of the hyperparameters for speculative decoding as text is being generated. We first formulate this hyperparameter selection problem as a Multi-Armed Bandit problem and provide a general speculative decoding framework BanditSpec. Furthermore, two bandit-based hyperparameter selection algorithms, UCBSpec and EXP3Spec, are designed and analyzed in terms of a novel quantity, the stopping time regret. We upper bound this regret under both stochastic and adversarial reward settings. By deriving an information-theoretic impossibility result, it is shown that the regret performance of UCBSpec is optimal up to universal constants. Finally, extensive empirical experiments with LLaMA3 and Qwen2 demonstrate that our algorithms are effective compared to existing methods, and the throughput is close to the oracle best hyperparameter in simulated real-life LLM serving scenarios with diverse input prompts.

Hoomaan Maskan, Yikun Hou, Suvrit Sra et al.

We introduce a new projection-free (Frank-Wolfe) method for optimizing structured nonconvex functions that are expressed as a difference of two convex functions. This problem class subsumes smooth nonconvex minimization, positioning our method as a promising alternative to the classical Frank-Wolfe algorithm. DC decompositions are not unique; by carefully selecting a decomposition, we can better exploit the problem structure, improve computational efficiency, and adapt to the underlying problem geometry to find better local solutions. We prove that the proposed method achieves a first-order stationary point in $O(1/ε^2)$ iterations, matching the complexity of the standard Frank-Wolfe algorithm for smooth nonconvex minimization in general. Specific decompositions can, for instance, yield a gradient-efficient variant that requires only $O(1/ε)$ calls to the gradient oracle. Finally, we present numerical experiments demonstrating the effectiveness of the proposed method compared to the standard Frank-Wolfe algorithm.

Ibna Kowsar, Shourav B. Rabbani, Yina Hou et al.

Missing values of varying patterns and rates in real-world tabular data pose a significant challenge in developing reliable data-driven models. The most commonly used statistical and machine learning methods for missing value imputation may be ineffective when the missing rate is high and not random. This paper explores row and column attention in tabular data as between-feature and between-sample attention in a novel framework to reconstruct missing values. The proposed method uses CutMix data augmentation within a contrastive learning framework to improve the uncertainty of missing value estimation. The performance and generalizability of trained imputation models are evaluated in set-aside test data folds with missing values. The proposed framework is compared with 11 state-of-the-art statistical, machine learning, and deep imputation methods using 12 diverse tabular data sets. The average performance rank of our proposed method demonstrates its superiority over the state-of-the-art methods for missing rates between 10% and 90% and three missing value types, especially when the missing values are not random. The quality of the imputed data using our proposed method is compared in a downstream patient classification task using real-world electronic health records. This paper highlights the heterogeneity of tabular data sets to recommend imputation methods based on missing value types and data characteristics.

Yongkang Hou, Jiarun Song

Image Quality Assessment (IQA) is a core task in computer vision. Multimodal methods based on vision-language models, such as CLIP, have demonstrated exceptional generalization capabilities in IQA tasks. To address the issues of excessive parameter burden and insufficient ability to identify local distorted features in CLIP for IQA, this study proposes a visual-language model knowledge distillation method aimed at guiding the training of models with architectural advantages using CLIP's IQA knowledge. First, quality-graded prompt templates were designed to guide CLIP to output quality scores. Then, CLIP is fine-tuned to enhance its capabilities in IQA tasks. Finally, a modality-adaptive knowledge distillation strategy is proposed to achieve guidance from the CLIP teacher model to the student model. Our experiments were conducted on multiple IQA datasets, and the results show that the proposed method significantly reduces model complexity while outperforming existing IQA methods, demonstrating strong potential for practical deployment.

Yina Hou, Shourav B. Rabbani, Liang Hong et al.

The importance of clinical variables in the prognosis of the disease is explained using statistical correlation or machine learning (ML). However, the predictive importance of these variables may not represent their causal relationships with diseases. This paper uses clinical variables from a heart failure (HF) patient cohort to investigate the causal explainability of important variables obtained in statistical and ML contexts. Due to inherent regression modeling, popular causal discovery methods strictly assume that the cause and effect variables are numerical and continuous. This paper proposes a new computational framework to enable causal structure discovery (CSD) and score the causal strength of mixed-type (categorical, numerical, binary) clinical variables for binary disease outcomes. In HF classification, we investigate the association between the importance rank order of three feature types: correlated features, features important for ML predictions, and causal features. Our results demonstrate that CSD modeling for nonlinear causal relationships is more meaningful than its linear counterparts. Feature importance obtained from nonlinear classifiers (e.g., gradient-boosting trees) strongly correlates with the causal strength of variables without differentiating cause and effect variables. Correlated variables can be causal for HF, but they are rarely identified as effect variables. These results can be used to add the causal explanation of variables important for ML-based prediction modeling.

Yikun Hou, Suvrit Sra, Alp Yurtsever

Gradient descent for matrix factorization exhibits an implicit bias toward approximately low-rank solutions. While existing theories often assume the boundedness of iterates, empirically the bias persists even with unbounded sequences. This reflects a dynamic where factors develop low-rank structure while their magnitudes increase, tending to align with certain directions. To capture this behavior in a stable way, we introduce a new factorization model: $X\approx UDV^\top$, where $U$ and $V$ are constrained within norm balls, while $D$ is a diagonal factor allowing the model to span the entire search space. Experiments show that this model consistently exhibits a strong implicit bias, yielding truly (rather than approximately) low-rank solutions. Extending the idea to neural networks, we introduce a new model featuring constrained layers and diagonal components that achieves competitive performance on various regression and classification tasks while producing lightweight, low-rank representations.