ICML 2025


1	On the Clean Generalization and Robust Overfitting in Adversarial Training from Two Theoretical Views: Representation Complexity and Training Dynamics	Benson Chen, Tomasz Danel, Gabriel H. S. Dreiman, Patrick J. McEnaney, Nikhil Jain, Kirill Novikov, Spurti Umesh Akki, Joshua L. Turnbull, Virja Atul Pandya, Boris P. Belotserkovskii, Jared Bryce Weaver, Ankita Biswas, Dat Nguyen, Kent Gorday, Mohammad Sultan, Nathaniel Stanley, Daniel M Whalen, Divya Kanichar, Christoph Klein, Emily Fox, et al. (1 additional authors not shown)	[link](https://openreview.net/forum?id=2GmXJnyNM4)	Spotlight	[2410.16247](https://huggingface.co/papers/2410.16247)	123	11	[link](https://www.microsoft.com/en-us/research/project/optiguide-genai-for-supply-chain-optimization/?msockid=1a1ccce4197d663e1c2bdd4318e1678d)	[link](https://github.com/KIT-MRT/future-motion?tab=readme-ov-file#words-in-motion-extracting-interpretable-control-vectors-for-motion-transformers)				16/21 ✅	Sharp generalization bound for neural networks trained by gradient descent (GD) is of central interest in statistical learning theory and deep learning. In this paper, we consider nonparametric regression by an over-parameterized two-layer NN trained by GD. We show that, if the neural network is trained by GD with early stopping, then the trained network renders a sharp rate of the nonparametric regression risk of $O(\epsilon_n^2)$, which is the same rate as that for the classical kernel regression trained by GD with early stopping, where $\epsilon_n$ is the critical population rate of the Neural Tangent Kernel (NTK) associated with the network and $n$ is the size of the training data. It is remarked that our result does not require distributional assumptions on the covariate as long as the covariate lies on the unit sphere, in a strong contrast with many existing results which rely on specific distributions such as the spherical uniform data distribution or distributions satisfying certain restrictive conditions. As a special case of our general result, when the eigenvalues of the associated NTK decay at a rate of $\lambda_j \asymp j^{-\frac{d}{d-1}}$ for $j \ge 1$ which happens under certain distributional assumption such as the training features follow the spherical uniform distribution, we immediately obtain the minimax optimal rate of $O(n^{-\frac{d}{2d-1}})$, which is the major results of several existing works in this direction. The neural network width in our general result is lower bounded by a function of only $d$ and $\epsilon_n$, and such width does not depend on the minimum eigenvalue of the empirical NTK matrix whose lower bound usually requires additional assumptions on the training data. Our results are built upon two significant technical results which are of independent interest. First, uniform convergence to the NTK is established during the training process by GD, so that we can have a nice decomposition of the neural network function at any step of the GD into a function in the Reproducing Kernel Hilbert Space associated with the NTK and an error function with a small $L^{\infty}$-norm. Second, local Rademacher complexity is employed to tightly bound the Rademacher complexity of the function class comprising all the possible neural network functions obtained by GD. Our result formally fills the gap between training a classical kernel regression model and training an over-parameterized but finite-width neural network by GD for nonparametric regression without distributional assumptions about the spherical covariate.	1000


1	Implicit Regularization for Tubal Tensor Factorizations via Gradient Descent	Santhosh Karnik, Anna Veselovska, Mark Iwen, Felix Krahmer	[link](https://openreview.net/forum?id=2GmXJnyNM4)	Oral	[2410.16247](https://huggingface.co/papers/2410.16247)	0	0	[link](https://github.com/AnnaVeselovskaUA/tubal-tensor-implicit-reg-GD)	0/4	We provide a rigorous analysis of implicit regularization in an overparametrized tensor factorization problem beyond the lazy training regime. For matrix factorization problems, this phenomenon has been studied in a number of works. A particular challenge has been to design universal initialization strategies which provably lead to implicit regularization in gradient-descent methods. At the same time, it has been argued by Cohen et. al. 2016 that more general classes of neural networks can be captured by considering tensor factorizations. However, in the tensor case, implicit regularization has only been rigorously established for gradient flow or in the lazy training regime. In this paper, we prove the first tensor result of its kind for gradient descent rather than gradient flow. We focus on the tubal tensor product and the associated notion of low tubal rank, encouraged by the relevance of this model for image data. We establish that gradient descent in an overparametrized tensor factorization model with a small random initialization exhibits an implicit bias towards solutions of low tubal rank. Our theoretical findings are illustrated in an extensive set of numerical simulations show-casing the dynamics predicted by our theory as well as the crucial role of using a small random initialization.	0
2	Algorithm Development in Neural Networks: Insights from the Streaming Parity Task	Loek van Rossem, Andrew M Saxe	[link](https://openreview.net/forum?id=3go0lhfxd0)	Oral	[2507.09897](https://huggingface.co/papers/2507.09897)	0	0		0/2	Even when massively overparameterized, deep neural networks show a remarkable ability to generalize. Research on this phenomenon has focused on generalization within distribution, via smooth interpolation. Yet in some settings neural networks also learn to extrapolate to data far beyond the bounds of the original training set, sometimes even allowing for infinite generalization, implying that an algorithm capable of solving the task has been learned. Here we undertake a case study of the learning dynamics of recurrent neural networks trained on the streaming parity task in order to develop an effective theory of algorithm development. The streaming parity task is a simple but nonlinear task defined on sequences up to arbitrary length. We show that, with sufficient finite training experience, RNNs exhibit a phase transition to perfect infinite generalization. Using an effective theory for the representational dynamics, we find an implicit representational merger effect which can be interpreted as the construction of a finite automaton that reproduces the task. Overall, our results disclose one mechanism by which neural networks can generalize infinitely from finite training experience.	1
3	Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection	Zhiyuan Yan, Jiangming Wang, Peng Jin, Ke-Yue Zhang, Chengchun Liu, Shen Chen, Taiping Yao, Shouhong Ding, Baoyuan Wu, Li Yuan	[link](https://openreview.net/forum?id=GFpjO8S8Po)	Oral	[2411.15633](https://huggingface.co/papers/2411.15633)	0	0	[link](https://github.com/YZY-stack/Effort-AIGI-Detection)	2/10 ✅	Detecting AI-generated images (AIGIs), such as natural images or face images, has become increasingly important yet challenging. In this paper, we start from a new perspective to excavate the reason behind the failure generalization in AIGI detection, named the asymmetry phenomenon, where a naively trained detector tends to favor overfitting to the limited and monotonous fake patterns, causing the feature space to become highly constrained and low-ranked, which is proved seriously limiting the expressivity and generalization. One potential remedy is incorporating the pre-trained knowledge within the vision foundation models (higher-ranked) to expand the feature space, alleviating the model's overfitting to fake. To this end, we employ Singular Value Decomposition (SVD) to decompose the original feature space into two orthogonal subspaces. By freezing the principal components and adapting only the remained components, we preserve the pre-trained knowledge while learning fake patterns. Compared to existing full-parameters and LoRA-based tuning methods, we explicitly ensure orthogonality, enabling the higher rank of the whole feature space, effectively minimizing overfitting and enhancing generalization. We finally identify a crucial insight: our method implicitly learns a vital prior that fakes are actually derived from the real, indicating a hierarchical relationship rather than independence. Modeling this prior, we believe, is essential for achieving superior generalization. Our codes are publicly available at https://github.com/YZY-stack/Effort-AIGI-Detection.	2
4	Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies	Nadav Timor, Jonathan Mamou, Daniel Korat, Moshe Berchansky, Gaurav Jain, Oren Pereg, Moshe Wasserblat, David Harel	[link](https://openreview.net/forum?id=vQubr1uBUw)	Oral	[2502.05202](https://huggingface.co/papers/2502.05202)	0	0	[link](https://github.com/keyboardAnt/hf-bench)	0/8	Accelerating the inference of large language models (LLMs) is a critical challenge in generative AI. Speculative decoding (SD) methods offer substantial efficiency gains by generating multiple tokens using a single target forward pass. However, existing SD approaches require the drafter and target models to share the same vocabulary, thus limiting the pool of possible drafters, often necessitating the training of a drafter from scratch. We present three new SD methods that remove this shared-vocabulary constraint. All three methods preserve the target distribution (i.e., they are lossless) and work with off-the-shelf models without requiring additional training or modifications. Empirically, on summarization, programming, and long-context tasks, our algorithms demonstrate significant speedups of up to 2.8x over standard autoregressive decoding. By enabling any off-the-shelf model to serve as a drafter and requiring no retraining, this work substantially broadens the applicability of the SD framework in practice.	3
5	LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models	Parshin Shojaee, Ngoc-Hieu Nguyen, Kazem Meidani, Amir Barati Farimani, Khoa D Doan, Chandan K. Reddy	[link](https://openreview.net/forum?id=SyQPiZJVWY)	Oral		0	0	[link](https://github.com/deep-symbolic-mathematics/llm-srbench)		Scientific equation discovery is a fundamental task in the history of scientific progress, enabling the derivation of laws governing natural phenomena. Recently, Large Language Models (LLMs) have gained interest for this task due to their potential to leverage embedded scientific knowledge for hypothesis generation. However, evaluating the true discovery capabilities of these methods remains challenging, as existing benchmarks often rely on common equations that are susceptible to memorization by LLMs, leading to inflated performance metrics that do not reflect actual discovery. In this paper, we introduce LLM-SRBench, a comprehensive benchmark with 239 challenging problems across four scientific domains specifically designed to evaluate LLM-based scientific equation discovery methods while preventing trivial memorization. Our benchmark comprises two main categories: LSR-Transform, which transforms common physical models into less common mathematical representations to test reasoning beyond memorization, and LSR-Synth, which introduces synthetic, discovery-driven problems requiring data-driven reasoning. Through extensive evaluation of several state-of-the-art methods on LLM-SRBench, using both open and closed LLMs, we find that the best-performing system so far achieves only 31.5% symbolic accuracy. These findings highlight the challenges of scientific equation discovery, positioning LLM-SRBench as a valuable resource for future research.	4
6	ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features	Alec Helbling, Tuna Han Salih Meral, Benjamin Hoover, Pinar Yanardag, Duen Horng Chau	[link](https://openreview.net/forum?id=Rc7y9HFC34)	Oral	[2502.04320](https://huggingface.co/papers/2502.04320)	38	3	[link](https://github.com/helblazer811/ConceptAttention)	3/5 ✅	Do the rich representations of multi-modal diffusion transformers (DiTs) exhibit unique properties that enhance their interpretability? We introduce ConceptAttention, a novel method that leverages the expressive power of DiT attention layers to generate high-quality saliency maps that precisely locate textual concepts within images. Without requiring additional training, ConceptAttention repurposes the parameters of DiT attention layers to produce highly contextualized concept embeddings, contributing the major discovery that performing linear projections in the output space of DiT attention layers yields significantly sharper saliency maps compared to commonly used cross-attention maps. ConceptAttention even achieves state-of-the-art performance on zero-shot image segmentation benchmarks, outperforming 15 other zero-shot interpretability methods on the ImageNet-Segmentation dataset. ConceptAttention works for popular image models and even seamlessly generalizes to video generation. Our work contributes the first evidence that the representations of multi-modal DiTs are highly transferable to vision tasks like segmentation.	5