DZDifan Zou

Difan Zou

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Difan Zou has a total of 31 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • SMANet: Probabilistic Gating and Neighborhood Attention for Video Individual Counting

    by Pengqi Huang, Xinyan Liu, Difan Zou, Weidong Chen, Weigang Zhang, Qingming Huang, Antoni B. Chan

  • Open Access

    Wasserstein-Robust Training for One-Hidden-Layer ReLU Networks with Distributional Guarantees

    by Yang Wang, Difan Zou, Xiaona Liu

    Neural networks are vulnerable to adversarial perturbations, which motivates training procedures with formal robustness guarantees. In this paper, we study one-hidden-layer ReLU networks from the perspective of Wasserstein distributional robustness. Leveraging the network structure, we derive an upper bound for the intractable robust surrogate in the form of a tractable regularized empirical risk objective whose regularizer is computed through a low-rank optimization problem based on Burer–Monteiro factorization. This reformulation yields a distributional robustness certificate on the worst-case expected loss over a Wasserstein ball. The upper bound construction and distributional certificate are developed for the shallow fixed-output multiclass formulation, while the optimization analysis focuses on a binary specialization with margin loss and exact linear separability. We also analyze a modified stochastic gradient descent scheme for the resulting regularized problem in this binary linearly separable setting, and we establish a corresponding generalization bound. The experiments validate the proposed surrogate and training procedure on binary MNIST and CIFAR-10 tasks, and we added a 10-class MNIST experiment to further check the multiclass trainability of the surrogate.

  • Open Access

    The Implicit Bias of Steepest Descent with Mini-batch Stochastic Gradient

    by Jichu Li, Xuan Tang, Difan Zou

    A variety of widely used optimization methods like SignSGD and Muon can be interpreted as instances of steepest descent under different norm-induced geometries. In this work, we study the implicit bias of mini-batch stochastic steepest descent in multi-class classification, characterizing how batch size, momentum, and variance reduction shape the limiting max-margin behavior and convergence rates under general entry-wise and Schatten-$p$ norms. We show that without momentum, convergence only occurs with large batches, yielding a batch-dependent margin gap but the full-batch convergence rate. In contrast, momentum enables small-batch convergence through a batch-momentum trade-off, though it slows convergence. This approach provides fully explicit, dimension-free rates that improve upon prior results. Moreover, we prove that variance reduction can recover the exact full-batch implicit bias for any batch size, albeit at a slower convergence rate. Finally, we further investigate the batch-size-one steepest descent without momentum, and reveal its convergence to a fundamentally different bias via a concrete data example, which reveals a key limitation of purely stochastic updates. Overall, our unified analysis clarifies when stochastic optimization aligns with full-batch behavior, and paves the way for perform deeper explorations of the training behavior of stochastic gradient steepest descent algorithms.

  • Open Access

    DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders

    by Xu Wang, Bingqing Jiang, Yu Wan, Baosong Yang, Lingpeng Kong, Difan Zou

    Sparse autoencoders (SAEs) have become a standard tool for mechanistic interpretability in autoregressive large language models (LLMs), enabling researchers to extract sparse, human-interpretable features and intervene on model behavior. Recently, as diffusion language models (DLMs) have become an increasingly promising alternative to the autoregressive LLMs, it is essential to develop tailored mechanistic interpretability tools for this emerging class of models. In this work, we present DLM-Scope, the first SAE-based interpretability framework for DLMs, and demonstrate that trained Top-K SAEs can faithfully extract interpretable features. Notably, we find that inserting SAEs affects DLMs differently than autoregressive LLMs: while SAE insertion in LLMs typically incurs a loss penalty, in DLMs it can reduce cross-entropy loss when applied to early layers, a phenomenon absent or markedly weaker in LLMs. Additionally, SAE features in DLMs enable more effective diffusion-time interventions, often outperforming LLM steering. Moreover, we pioneer certain new SAE-based research directions for DLMs: we show that SAEs can provide useful signals for DLM decoding order; and the SAE features are stable during the post-training phase of DLMs. Our work establishes a foundation for mechanistic interpretability in DLMs and shows a great potential of applying SAEs to DLM-related tasks and algorithms.

  • Open Access

    How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?

    by Wei Huang, Andi Han, Yujin Song, Yilan Chen, Denny Wu, Difan Zou, Taiji Suzuki

    The capacity of deep learning models is often large enough to both learn the underlying statistical signal and overfit to noise in the training set. This noise memorization can be harmful especially for data with a low signal-to-noise ratio (SNR), leading to poor generalization. Inspired by prior observations that label noise provides implicit regularization that improves generalization, in this work, we investigate whether introducing label noise to the gradient updates can enhance the test performance of neural network (NN) in the low SNR regime. Specifically, we consider training a two-layer NN with a simple label noise gradient descent (GD) algorithm, in an idealized signal-noise data setting. We prove that adding label noise during training suppresses noise memorization, preventing it from dominating the learning process; consequently, label noise GD enjoys rapid signal growth while the overfitting remains controlled, thereby achieving good generalization despite the low SNR. In contrast, we also show that NN trained with standard GD tends to overfit to noise in the same low SNR setting and establish a non-vanishing lower bound on its test error, thus demonstrating the benefit of introducing label noise in gradient-based training.

  • Open Access

    Kernel Regression in Structured Non-IID Settings: Theory and Implications for Denoising Score Learning

    by Dechen Zhang, Zhenmei Shi, Yi Zhang, Yingyu Liang, Difan Zou

    Kernel ridge regression (KRR) is a foundational tool in machine learning, with recent work emphasizing its connections to neural networks. However, existing theory primarily addresses the i.i.d. setting, while real-world data often exhibits structured dependencies - particularly in applications like denoising score learning where multiple noisy observations derive from shared underlying signals. We present the first systematic study of KRR generalization for non-i.i.d. data with signal-noise causal structure, where observations represent different noisy views of common signals. By developing a novel blockwise decomposition method that enables precise concentration analysis for dependent data, we derive excess risk bounds for KRR that explicitly depend on: (1) the kernel spectrum, (2) causal structure parameters, and (3) sampling mechanisms (including relative sample sizes for signals and noises). We further apply our results to denoising score learning, establishing generalization guarantees and providing principled guidance for sampling noisy data points. This work advances KRR theory while providing practical tools for analyzing dependent data in modern machine learning applications.

  • Open Access

    Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks

    by Xuan Tang, Han Zhang, Yuan Cao, Difan Zou

    Adam is a popular and widely used adaptive gradient method in deep learning, which has also received tremendous focus in theoretical research. However, most existing theoretical work primarily analyzes its full-batch version, which differs fundamentally from the stochastic variant used in practice. Unlike SGD, stochastic Adam does not converge to its full-batch counterpart even with infinitesimal learning rates. We present the first theoretical characterization of how batch size affects Adam's generalization, analyzing two-layer over-parameterized CNNs on image data. Our results reveal that while both Adam and AdamW with proper weight decay $λ$ converge to poor test error solutions, their mini-batch variants can achieve near-zero test error. We further prove Adam has a strictly smaller effective weight decay bound than AdamW, theoretically explaining why Adam requires more sensitive $λ$ tuning. Extensive experiments validate our findings, demonstrating the critical role of batch size and weight decay in Adam's generalization performance.

  • Open Access

    STGAN: Spatial-temporal Graph Autoregression Network for Pavement Distress Deterioration Prediction

    by Shilin Tong, Difei Wu, Xiaona Liu, Le Zheng, Yuchuan Du, Difan Zou

    Pavement distress significantly compromises road integrity and poses risks to drivers. Accurate prediction of pavement distress deterioration is essential for effective road management, cost reduction in maintenance, and improvement of traffic safety. However, real-world data on pavement distress is usually collected irregularly, resulting in uneven, asynchronous, and sparse spatial-temporal datasets. This hinders the application of existing spatial-temporal models, such as DCRNN, since they are only applicable to regularly and synchronously collected data. To overcome these challenges, we propose the Spatial-Temporal Graph Autoregression Network (STGAN), a novel graph neural network model designed for accurately predicting irregular pavement distress deterioration using complex spatial-temporal data. Specifically, STGAN integrates the temporal domain into the spatial domain, creating a larger graph where nodes are represented by spatial-temporal tuples and edges are formed based on a similarity-based connection mechanism. Furthermore, based on the constructed spatiotemporal graph, we formulate pavement distress deterioration prediction as a graph autoregression task, i.e., the graph size increases incrementally and the prediction is performed sequentially. This is accomplished by a novel spatial-temporal attention mechanism deployed by STGAN. Utilizing the ConTrack dataset, which contains pavement distress records collected from different locations in Shanghai, we demonstrate the superior performance of STGAN in capturing spatial-temporal correlations and addressing the aforementioned challenges. Experimental results further show that STGAN outperforms baseline models, and ablation studies confirm the effectiveness of its novel modules. Our findings contribute to promoting proactive road maintenance decision-making and ultimately enhancing road safety and resilience.