Shujie Ma

Xuewei Cheng, Ke Huang, Yi Zou et al.

Deep neural networks have played an important role in automatic sleep stage classification because of their strong representation and in-model feature transformation abilities. However, class imbalance and individual heterogeneity which typically exist in raw EEG signals of sleep data can significantly affect the classification performance of any machine learning algorithms. To solve these two problems, this paper develops a generative adversarial network (GAN)-powered ensemble deep learning model, named SleepEGAN, for the imbalanced classification of sleep stages. To alleviate class imbalance, we propose a new GAN (called EGAN) architecture adapted to the features of EEG signals for data augmentation. The generated samples for the minority classes are used in the training process. In addition, we design a cost-free ensemble learning strategy to reduce the model estimation variance caused by the heterogeneity between the validation and test sets, so as to enhance the accuracy and robustness of prediction performance. We show that the proposed method can improve classification accuracy compared to several existing state-of-the-art methods using three public sleep datasets.

Xinyi Wang, Jinyi Han, Zishang Jiang et al.

Reinforcement Learning (RL) has become a key driver for enhancing the long chain-of-thought (CoT) reasoning capabilities of Large Language Models (LLMs). However, prevalent methods like GRPO often fail when task difficulty exceeds the model's capacity, leading to reward sparsity and inefficient training. While prior work attempts to mitigate this using off-policy data, such as mixing RL with Supervised Fine-Tuning (SFT) or using hints, they often misguide policy updates In this work, we identify a core issue underlying these failures, which we term low training affinity. This condition arises from a large distributional mismatch between external guidance and the model's policy. To diagnose this, we introduce Affinity, the first quantitative metric for monitoring exploration efficiency and training stability. To improve Affinity, we propose HINT: Helping Ineffective rollouts Navigate Towards effectiveness, an adaptive hinting framework. Instead of providing direct answers, HINT supplies heuristic hints that guide the model to discover solutions on its own, preserving its autonomous reasoning capabilities. Extensive experiments on mathematical reasoning tasks show that HINT consistently outperforms existing methods, achieving state-of-the-art results with models of various scales, while also demonstrating significantly more stable learning and greater data efficiency.Code is available on Github.

Zishang Jiang, Jinyi Han, Tingyun Li et al.

Reinforcement Learning with Verifiable Rewards (RLVR) has become a widely adopted technique for enhancing the reasoning ability of Large Language Models (LLMs). However, the effectiveness of RLVR strongly depends on the capability of base models. This issue arises because it requires the model to have sufficient capability to perform high-quality exploration, which involves both effectiveness and diversity. Unfortunately, existing methods address this issue by imitating expert trajectories, which improve effectiveness but neglect diversity. To address this, we argue that the expert only needs to provide guidance only at critical decision points rather than the entire reasoning path. Based on this insight, we propose MENTOR: Mixed-policy Expert Navigation for Token-level Optimization of Reasoning, a framework that provides expert guidance only at critical decision points to perform effective and diverse exploration in RLVR. Extensive experiments show that MENTOR enables models capture the essence of expert strategies rather than surface imitation, thereby performing high-quality exploration and achieving superior overall performance. Our code is available online.

Xuewei Cheng, Ke Huang, Shujie Ma

Recurrent Neural Networks (RNNs) have achieved great success in the prediction of sequential data. However, their theoretical studies are still lagging behind because of their complex interconnected structures. In this paper, we establish a new generalization error bound for vanilla RNNs, and provide a unified framework to calculate the Rademacher complexity that can be applied to a variety of loss functions. When the ramp loss is used, we show that our bound is tighter than the existing bounds based on the same assumptions on the Frobenius and spectral norms of the weight matrices and a few mild conditions. Our numerical results show that our new generalization bound is the tightest among all existing bounds in three public datasets. Our bound improves the second tightest one by an average percentage of 13.80% and 3.01% when the $\tanh$ and ReLU activation functions are used, respectively. Moreover, we derive a sharp estimation error bound for RNN-based estimators obtained through empirical risk minimization (ERM) in multi-class classification problems when the loss function satisfies a Bernstein condition.

Xiaohong Chen, Ying Liu, Shujie Ma et al.

Semiparametric efficient estimation of various multi-valued causal effects, including quantile treatment effects, is important in economic, biomedical, and other social sciences. Under the unconfoundedness condition, adjustment for confounders requires estimating the nuisance functions relating outcome or treatment to confounders nonparametrically. This paper considers a generalized optimization framework for efficient estimation of general treatment effects using artificial neural networks (ANNs) to approximate the unknown nuisance function of growing-dimensional confounders. We establish a new approximation error bound for the ANNs to the nuisance function belonging to a mixed smoothness class without a known sparsity structure. We show that the ANNs can alleviate the "curse of dimensionality" under this circumstance. We establish the root-$n$ consistency and asymptotic normality of the proposed general treatment effects estimators, and apply a weighted bootstrap procedure for conducting inference. The proposed methods are illustrated via simulation studies and a real data application.

Xiaokang Liu, Shujie Ma, Kun Chen

We propose a nested reduced-rank regression (NRRR) approach in fitting regression model with multivariate functional responses and predictors, to achieve tailored dimension reduction and facilitate interpretation/visualization of the resulting functional model. Our approach is based on a two-level low-rank structure imposed on the functional regression surfaces. A global low-rank structure identifies a small set of latent principal functional responses and predictors that drives the underlying regression association. A local low-rank structure then controls the complexity and smoothness of the association between the principal functional responses and predictors. Through a basis expansion approach, the functional problem boils down to an interesting integrated matrix approximation task, where the blocks or submatrices of an integrated low-rank matrix share some common row space and/or column space. An iterative algorithm with convergence guarantee is developed. We establish the consistency of NRRR and also show through non-asymptotic analysis that it can achieve at least a comparable error rate to that of the reduced-rank regression. Simulation studies demonstrate the effectiveness of NRRR. We apply NRRR in an electricity demand problem, to relate the trajectories of the daily electricity consumption with those of the daily temperatures.