Author name cluster

Qi Lei

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

34 papers

2 author rows

ICLR Conference 2025 Conference Paper

Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness

Qi Zhang 0067
Yifei Wang 0001
Jingyi Cui
Xiang Pan 0001
Qi Lei
Stefanie Jegelka
Yisen Wang 0001

Deep learning models often suffer from a lack of interpretability due to \emph{polysemanticity}, where individual neurons are activated by multiple unrelated semantics, resulting in unclear attributions of model behavior. Recent advances in \emph{monosemanticity}, where neurons correspond to consistent and distinct semantics, have significantly improved interpretability but are commonly believed to compromise accuracy. In this work, we challenge the prevailing belief of the accuracy-interpretability tradeoff, showing that monosemantic features not only enhance interpretability but also bring concrete gains in model performance of {\color{black} robustness-related tasks}. Across multiple robust learning scenarios—including input and label noise, few-shot learning, and out-of-domain generalization—our results show that models leveraging monosemantic features significantly outperform those relying on polysemantic features. Furthermore, we provide empirical and theoretical understandings on the robustness gains of feature monosemanticity. Our preliminary analysis suggests that monosemanticity, by promoting better separation of feature representations, leads to more robust decision boundaries {\color{black} under noise}. This diverse evidence highlights the \textbf{generality} of monosemanticity in improving model robustness. As a first step in this new direction, we embark on exploring the learning benefits of monosemanticity beyond interpretability, supporting the long-standing hypothesis of linking interpretability and robustness. Code is available at \url{https://github.com/PKU-ML/Monosemanticity-Robustness}.

Details

UAI Conference 2025 Conference Paper

Beyond Invisibility: Learning Robust Visible Watermarks for Stronger Copyright Protection

Tianci Liu 0003
Tong Yang
Quan Zhang
Qi Lei

As AI advances, copyrighted content faces growing risk of unauthorized use, whether through model training or direct misuse. Building upon invisible adversarial perturbation, recent works developed copyright protections against specific AI techniques such as unauthorized personalization through DreamBooth that are misused. However, these methods offer only short-term security, as they require retraining whenever the underlying model architectures change. To establish long-term protection aiming at better robustness, we go beyond invisible perturbation, and propose a universal approach that embeds \textit{visible} watermarks that are \textit{hard-to-remove} into images. Grounded in a new probabilistic and inverse problem-based formulation, our framework maximizes the discrepancy between the \textit{optimal} reconstruction and the original content. We develop an effective and efficient approximation algorithm to circumvent a intractable bi-level optimization. Experimental results demonstrate superiority of our approach across diverse scenarios.

Details

ICML Conference 2025 Conference Paper

Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension

Yijun Dong
Yicheng Li
Yunai Li
Jason D. Lee
Qi Lei

Weak-to-strong (W2S) generalization is a type of finetuning (FT) where a strong (large) student model is trained on pseudo-labels generated by a weak teacher. Surprisingly, W2S FT often outperforms the weak teacher. We seek to understand this phenomenon through the observation that FT often occurs in intrinsically low-dimensional spaces. Leveraging the low intrinsic dimensionality of FT, we analyze W2S in the ridgeless regression setting from a variance reduction perspective. For a strong student-weak teacher pair with sufficiently expressive low-dimensional feature subspaces $\mathcal{V}_s, \mathcal{V}_w$, we provide an exact characterization of the variance that dominates the generalization error of W2S. This unveils a virtue of discrepancy between the strong and weak models in W2S: the variance of the weak teacher is inherited by the strong student in $\mathcal{V}_s \cap \mathcal{V}_w$, while reduced by a factor of $\mathrm{dim}(\mathcal{V}_s)/N$ in the subspace of discrepancy $\mathcal{V}_w \setminus \mathcal{V}_s$ with $N$ pseudo-labels for W2S. Our analysis further casts light on the sample complexities and the scaling of performance gap recovery in W2S. The analysis is supported by experiments on synthetic regression problems, as well as real vision and NLP tasks.

Details

NeurIPS Conference 2025 Conference Paper

Hyperparameter Transfer Enables Consistent Gains of Matrix-Preconditioned Optimizers Across Scales

Shikai Qiu
Charlie Chen
Hoang Phan
Qi Lei
Andrew Wilson

Several recently introduced deep learning optimizers utilizing matrix-level preconditioning have shown promising speedups relative to the current dominant optimizer AdamW, particularly in relatively small-scale experiments. However, efforts to validate and replicate their successes have reported mixed results. To better understand the effectiveness of these optimizers at scale, in this work we investigate how to scale preconditioned optimizers via hyperparameter transfer, building on prior works such as $\mu$P. We study how the optimal learning rate and weight decay should scale with model width and depth for a wide range of optimizers, including Shampoo, SOAP, and Muon, accounting for the impact of commonly used techniques such as blocking and grafting. We find that scaling the learning rate according to $\mu$P improves transfer, but can still suffer from significant finite-width deviations that cause drifting optimal learning rates, which we show can be mitigated by blocking and explicit spectral normalization. For compute-optimal scaling, we find scaling independent weight decay as $1/\mathrm{width}$ is nearly optimal across optimizers. Applying these scaling rules, we show Muon, SOAP and Shampoo consistently achieve near $1. 4\times$ speedup over AdamW for training Llama-architecture language models of sizes ranging from $190$M to $1. 4$B, whereas the speedup vanishes rapidly with scale under incorrect scaling. Based on these results and further ablations, we argue that studying optimal hyperparameter transfer is essential for reliably comparing optimizers at scale given a realistic tuning budget.