ICML 2025 论文列表

Lipschitz neural networks are well-known for providing certified robustness in deep learning. In this paper, we present a novel, efficient Block Reflector Orthogonal (BRO) layer that enhances the capability of orthogonal layers on constructing more expressive Lipschitz neural architectures. In addition, by theoretically analyzing the nature of Lipschitz neural networks, we introduce a new loss function that employs an annealing mechanism to increase margin for most data points. This enables Lipschitz models to provide better certified robustness. By employing our BRO layer and loss function, we design BRONet — a simple yet effective Lipschitz neural network that achieves state-of-the-art certified robustness. Extensive experiments and empirical analysis on CIFAR-10/100, Tiny-ImageNet, and ImageNet validate that our method outperforms existing baselines. The implementation is available at [GitHub Link](https://github.com/ntuaislab/BRONet).

A _combinatorial intervention_, consisting of multiple treatments applied to a single unit with potential interactive effects, has substantial applications in fields such as biomedicine, engineering, and beyond. Given $p$ possible treatments, conducting all possible $2^p$ combinatorial interventions can be laborious and quickly becomes infeasible as $p$ increases. Here we introduce the _probabilistic factorial experimental design_, formalized from how scientists perform lab experiments. In this framework, the experimenter selects a dosage for each possible treatment and applies it to a group of units. Each unit independently receives a random combination of treatments, sampled from a product Bernoulli distribution determined by the dosages. Additionally, the experimenter can carry out such experiments over multiple rounds, adapting the design in an active manner. We address the optimal experimental design problem within a novel intervention model that imposes bounded-degree interactions between treatments. In the passive setting, we provide a closed-form solution for the near-optimal design. Our results prove that a dosage of $\frac{1}{2}$ for each treatment is optimal up to a factor of $1+O(\frac{\ln(n)}{n})$ for estimating any $k$-way interaction model, regardless of $k$, and imply that $O\big(kp^{3k}\ln(p)\big)$ observations are required to accurately estimate this model. For the multi-round setting, we provide a near-optimal acquisition function that can be numerically optimized. We also explore several extensions of the design problem and finally validate our findings through simulations.

We study the out-of-sample performance of multi-pass stochastic gradient descent (SGD) in the fundamental stochastic convex optimization (SCO) model. While one-pass SGD is known to achieve an optimal $\Theta(1/\sqrt{n})$ excess population loss given a sample of size $n$, much less is understood about the multi-pass version of the algorithm which is widely used in practice. Somewhat surprisingly, we show that in the general non-smooth case of SCO, just a few epochs of SGD can already hurt its out-of-sample performance significantly and lead to overfitting. In particular, using a step size $\eta = \Theta(1/\sqrt{n})$, which gives the optimal rate after one pass, can lead to population loss as large as $\Omega(1)$ after just one additional pass. More generally, we show that the population loss from the second pass onward is of the order $\Theta(1/(\eta T) + \eta \sqrt{T})$, where $T$ is the total number of steps. These results reveal a certain phase-transition in the out-of-sample behavior of SGD after the first epoch, as well as a sharp separation between the rates of overfitting in the smooth and non-smooth cases of SCO. Additionally, we extend our results to with-replacement SGD, proving that the same asymptotic bounds hold after $O(n \log n)$ steps. Finally, we also prove a lower bound of $\Omega(\eta \sqrt{n})$ on the generalization gap of one-pass SGD in dimension $d = {\widetilde O}(n)$, improving on recent results of Koren et al. (2022) and Schliserman et al. (2024).

Large Language Models (LLMs) have demonstrated impressive real-world utility, exemplifying artificial useful intelligence (AUI). However, their ability to reason adaptively and robustly -- the hallmarks of artificial general intelligence (AGI) -- remains fragile. While LLMs seemingly succeed in commonsense reasoning, programming, and mathematics, they struggle to generalize algorithmic understanding across novel contexts. Our experiments with algorithmic tasks in esoteric programming languages reveal that LLM's reasoning overfits to the training data and is limited in its transferability. We hypothesize that the core issue underlying such limited transferability is the coupling of reasoning and knowledge in LLMs. To transition from AUI to AGI, we propose disentangling knowledge and reasoning through three key directions: (1) pretaining to reason using RL from scratch as an alternative to the widely used next-token prediction pretraining, (2) using a curriculum of synthetic tasks to ease the learning of a \textit{reasoning prior} for RL that can then be transferred to natural language tasks, and (3) learning more generalizable reasoning functions using a small context window to reduce exploiting spurious correlations between tokens. Such a reasoning system coupled with a trained retrieval system and a large external memory bank as a knowledge store can overcome several limitations of existing architectures at learning to reason in novel scenarios.

This paper formalizes an emerging learning paradigm that uses a trained model as a reference to guide and enhance the training of a target model through strategic data selection or weighting, named **model steering**. While ad-hoc methods have been used in various contexts, including the training of large foundation models, its underlying principles remain insufficiently understood, leading to sub-optimal performance. In this work, we propose a theory-driven framework for model steering called **DRRho risk minimization**, which is rooted in Distributionally Robust Optimization (DRO). Through a generalization analysis, we provide theoretical insights into why this approach improves generalization and data efficiency compared to training without a reference model. To the best of our knowledge, this is the first time such theoretical insights are provided for the new learning paradigm, which significantly enhance our understanding and practice of model steering. Building on these insights and the connection between contrastive learning and DRO, we introduce a novel method for Contrastive Language-Image Pretraining (CLIP) with a reference model, termed DRRho-CLIP. Extensive experiments validate the theoretical insights, reveal a superior scaling law compared to CLIP without a reference model, and demonstrate its strength over existing heuristic approaches. Code is released at [github.com/Optimization-AI/DRRho-CLIP](https://github.com/Optimization-AI/DRRho-CLIP)

Discovering regularities from spatiotemporal systems can benefit various scientific and social planning. Current spatiotemporal learners usually train an independent model from a specific source data that leads to limited transferability among sources, where even correlated tasks requires new design and training. The key towards increasing cross-domain knowledge is to enable collective intelligence and model evolution. In this paper, inspired by neuroscience theories, we theoretically derive the increased information boundary via learning cross-domain collective intelligence and propose a Synaptic EVOlutional spatiotemporal network, SynEVO, where SynEVO breaks the model independence and enables cross-domain knowledge to be shared and aggregated. Specifically, we first re-order the sample groups to imitate the human curriculum learning, and devise two complementary learners, elastic common container and task-independent extractor to allow model growth and task-wise commonality and personality disentanglement. Then an adaptive dynamic coupler with a new difference metric determines whether the new sample group should be incorporated into common container to achieve model evolution under various domains. Experiments show that SynEVO improves the generalization capacity by at most 42\% under cross-domain scenarios and SynEVO provides a paradigm of NeuroAI for knowledge transfer and adaptation. Code available at [https://github.com/Rodger-Lau/SynEVO](https://github.com/Rodger-Lau/SynEVO).

Large language models (LLMs) deployed as agents solve user-specified tasks over multiple steps while keeping the required manual engagement to a minimum. Crucially, such LLMs need to ground their generations in any feedback obtained to reliably achieve the desired outcomes. We propose an end-to-end reinforcement learning method for teaching models to leverage execution feedback in the realm of code synthesis, where state-of-the-art LLMs struggle to improve code iteratively compared to independent sampling. We benchmark on competitive programming tasks and achieve large performance gains with both small (8B parameters) and large (70B) models, outperforming previous work while reducing the number of samples required by an order of magnitude. Our analysis of inference-time behavior demonstrates that our method produces LLMs that effectively leverage automatic feedback over multiple steps.

Sparse variational Gaussian processes (GPs) construct tractable posterior approximations to GP models. At the core of these methods is the assumption that the true posterior distribution over training function values ${\bf f}$ and inducing variables ${\bf u}$ is approximated by a variational distribution that incorporates the conditional GP prior $p({\bf f} | {\bf u})$ in its factorization. While this assumption is considered as fundamental, we show that for model training we can relax it through the use of a more general variational distribution $q({\bf f} | {\bf u} )$ that depends on $N$ extra parameters, where $N$ is the number of training examples. In GP regression, we can analytically optimize the evidence lower bound over the extra parameters and express a tractable collapsed bound that is tighter than the previous bound. The new bound is also amenable to stochastic optimization and its implementation requires minor modifications to existing sparse GP code. Further, we also describe extensions to non-Gaussian likelihoods. On several datasets we demonstrate that our method can reduce bias when learning the hyperparameters and can lead to better predictive performance.

Cross-domain few-shot segmentation (CD-FSS) is proposed to first pre-train the model on a source-domain dataset with sufficient samples, and then transfer the model to target-domain datasets where only a few training samples are available for efficient finetuning. There are majorly two challenges in this task: (1) the domain gap and (2) finetuning with scarce data. To solve these challenges, we revisit the adapter-based methods, and discover an intriguing insight not explored in previous works: the adapter not only helps the fine-tuning of downstream tasks but also naturally serves as a domain information decoupler. Then, we delve into this finding for an interpretation, and we find the model's inherent structure could lead to a natural decoupling of domain information. Building upon this insight, we propose the Domain Feature Navigator (DFN), which is a structure-based decoupler instead of loss-based ones like current works, to capture domain-specific information, thereby directing the model's attention towards domain-agnostic knowledge. Moreover, to prevent the potential excessive overfitting of DFN during the source-domain training, we further design the SAM-SVN method to constrain DFN from learning sample-specific knowledge. On target domains, we freeze the model and fine-tune the DFN to learn knowledge specific to target domains. Extensive experiments demonstrate that our method surpasses the state-of-the-art method in CD-FSS significantly by 2.69% and 4.68% average MIoU in 1-shot and 5-shot scenarios, respectively.

Multi-objective learning under user-specified preference is common in real-world problems such as multi-lingual speech recognition under fairness. In this work, we frame such a problem as a semivectorial bilevel optimization problem, whose goal is to optimize a pre-defined preference function, subject to the constraint that the model parameters are weakly Pareto optimal. To solve this problem, we convert the multi-objective constraints to a single-objective constraint through a merit function with an easy-to-evaluate gradient, and then, we use a penalty-based reformulation of the bilevel optimization problem. We theoretically establish the properties of the merit function, and the relations of solutions for the penalty reformulation and the constrained formulation. Then we propose algorithms to solve the reformulated single-level problem, and establish its convergence guarantees. We test the method on various synthetic and real-world problems. The results demonstrate the effectiveness of the proposed method in finding preference-guided optimal solutions to the multi-objective problem.

Spatial transcriptomics (ST) has emerged as a powerful technology for bridging histology imaging with gene expression profiling. However, its application has been limited by low throughput and the need for specialized experimental facilities. Prior works sought to predict ST from whole-slide histology images to accelerate this process, but they suffer from two major limitations. First, they do not explicitly model cell-cell interaction as they factorize the joint distribution of whole-slide ST data and predict the gene expression of each spot independently. Second, their encoders struggle with memory constraints due to the large number of spots (often exceeding 10,000) in typical ST datasets. Herein, we propose STFlow, a flow matching generative model that considers cell-cell interaction by modeling the joint distribution of gene expression of an entire slide. It also employs an efficient slide-level encoder with local spatial attention, enabling whole-slide processing without excessive memory overhead. On the recently curated HEST-1k and STImage-1K4M benchmarks, STFlow substantially outperforms state-of-the-art baselines and achieves over 18% relative improvements over the pathology foundation models.

Vision Transformer (ViT) has achieved remarkable success due to its large-scale pretraining on general domains, but it still faces challenges when applying it to downstream distant domains that have only scarce training data, which gives rise to the Cross-Domain Few-Shot Learning (CDFSL) task. Inspired by Self-Attention's insensitivity to token orders, we find an interesting phenomenon neglected in current works: disrupting the continuity of image tokens (i.e., making pixels not smoothly transited across patches) in ViT leads to a noticeable performance decline in the general (source) domain but only a marginal decrease in downstream target domains. This questions the role of image tokens' continuity in ViT's generalization under large domain gaps. In this paper, we delve into this phenomenon for an interpretation. We find continuity aids ViT in learning larger spatial patterns, which are harder to transfer than smaller ones, enlarging domain distances. Meanwhile, it implies that only smaller patterns within each patch could be transferred under extreme domain gaps. Based on this interpretation, we further propose a simple yet effective method for CDFSL that better disrupts the continuity of image tokens, encouraging the model to rely less on large patterns and more on smaller ones. Extensive experiments show the effectiveness of our method in reducing domain gaps and outperforming state-of-the-art works. Codes and models are available at https://github.com/shuaiyi308/ReCIT.

The field of *algorithms with predictions* incorporates machine learning advice in the design of online algorithms to improve real-world performance. A central consideration is the extent to which predictions can be trusted—while existing approaches often require users to specify an aggregate trust level, modern machine learning models can provide estimates of prediction-level uncertainty. In this paper, we propose *calibration* as a principled and practical tool to bridge this gap, demonstrating the benefits of calibrated advice through two case studies: the *ski rental* and *online job scheduling* problems. For ski rental, we design an algorithm that achieves near-optimal prediction-dependent performance and prove that, in high-variance settings, calibrated advice offers more effective guidance than alternative methods for uncertainty quantification. For job scheduling, we demonstrate that using a calibrated predictor leads to significant performance improvements over existing methods. Evaluations on real-world data validate our theoretical findings, highlighting the practical impact of calibration for algorithms with predictions.

While likelihood-based generative models, particularly diffusion and autoregressive models, have achieved remarkable fidelity in visual generation, the maximum likelihood estimation (MLE) objective, which minimizes the forward KL divergence, inherently suffers from a mode-covering tendency that limits the generation quality under limited model capacity. In this work, we propose Direct Discriminative Optimization (DDO) as a unified framework that integrates likelihood-based generative training and GAN-type discrimination to bypass this fundamental constraint by exploiting reverse KL and self-generated negative signals. Our key insight is to parameterize a discriminator implicitly using the likelihood ratio between a learnable target model and a fixed reference model, drawing parallels with the philosophy of Direct Preference Optimization (DPO). Unlike GANs, this parameterization eliminates the need for joint training of generator and discriminator networks, allowing for direct, efficient, and effective finetuning of a well-trained model to its full potential beyond the limits of MLE. DDO can be performed iteratively in a self-play manner for progressive model refinement, with each round requiring less than 1\% of pretraining epochs. Our experiments demonstrate the effectiveness of DDO by significantly advancing the previous SOTA diffusion model EDM, reducing FID scores from 1.79/1.58/1.96 to new records of 1.30/0.97/1.26 on CIFAR-10/ImageNet-64/ImageNet 512$\times$512 datasets without any guidance mechanisms, and by consistently improving both guidance-free and CFG-enhanced FIDs of visual autoregressive models on ImageNet 256$\times$256.

We tackle the problem of identifying whether a variable is the cause of a specified target using observational data. State-of-the-art causal learning algorithms that handle latent variables typically rely on identifying the global causal structure, often represented as a partial ancestral graph (PAG), to infer causal relationships. Although effective, these approaches are often redundant and computationally expensive when the focus is limited to a specific causal relationship. In this work, we introduce novel local characterizations that are necessary and sufficient for various types of causal relationships between two variables, enabling us to bypass the need for global structure learning. Leveraging these local insights, we develop efficient and fully localized algorithms that accurately identify causal relationships from observational data. We theoretically demonstrate the soundness and completeness of our approach. Extensive experiments on benchmark networks and real-world datasets further validate the effectiveness and efficiency of our method.

Effective modelling of large-scale spatio-temporal datasets is essential for many domains, yet existing approaches often impose rigid constraints on the input data, such as requiring them to lie on fixed-resolution grids. With the rise of foundation models, the ability to process diverse, heterogeneous data structures is becoming increasingly important. Neural processes (NPs), particularly transformer neural processes (TNPs), offer a promising framework for such tasks, but struggle to scale to large spatio-temporal datasets due to the lack of an efficient attention mechanism. To address this, we introduce gridded pseudo-token TNPs which employ specialised encoders and decoders to handle unstructured data and utilise a processor comprising gridded pseudo-tokens with efficient attention mechanisms. Furthermore, we develop equivariant gridded TNPs for applications where exact or approximate translation equivariance is a useful inductive bias, improving accuracy and training efficiency. Our method consistently outperforms a range of strong baselines in various synthetic and real-world regression tasks involving large-scale data, while maintaining competitive computational efficiency. Experiments with weather data highlight the potential of gridded TNPs and serve as just one example of a domain where they can have a significant impact.

With the advent of automatic vectorization tools (e.g., JAX's vmap), writing multi-chain MCMC algorithms is often now as simple as invoking those tools on single-chain code. Whilst convenient, for various MCMC algorithms this results in a synchronization problem---loosely speaking, at each iteration all chains running in parallel must wait until the last chain has finished drawing its sample. In this work, we show how to design single-chain MCMC algorithms in a way that avoids synchronization overheads when vectorizing with tools like vmap, by using the framework of finite state machines (FSMs). Using a simplified model, we derive an exact theoretical form of the obtainable speed-ups using our approach, and use it to make principled recommendations for optimal algorithm design. We implement several popular MCMC algorithms as FSMs, including Elliptical Slice Sampling, HMC-NUTS, and Delayed Rejection, demonstrating speed-ups of up to an order of magnitude in experiments.

In the Correlation Clustering problem, we are given an undirected graph and are tasked with computing a clustering (partition of the nodes) that minimizes the sum of the number of edges across different clusters and the number of non-edges within clusters. In the constrained version of this problem, the goal is to compute a clustering that satisfies additional hard constraints mandating certain pairs to be in the same cluster and certain pairs to be in different clusters. Constrained Correlation Clustering is APX-Hard, and the best known approximation factor is 3 (van Zuylen et al. [SODA '07]). In this work, we show that in order to obtain a better-than-2 approximation, solving the (exponentially large) Constrained Cluster LP would be sufficient. [The peer-reviewed version of this article claimed an efficient algorithm for solving the Constrained Cluster LP. An error in the proof, that the authors discovered after the review process, led them to revise the results to be conditional on the existence of a valid LP solution.]

Given two weighted graphs $G = (V, E, w_G)$ and $H = (V, F, w_H)$ defined on the same vertex set, the constrained clustering problem seeks to find a subset $S \subset V$ that minimises the cut ratio between $w_G(S, V \setminus S)$ and $w_H(S, V \setminus S)$. In this work, we establish a Cheeger-type inequality that relates the solution of the constrained clustering problem to the spectral properties of $ G$ and $H$. To reduce computational complexity, we utilise the signed Laplacian of $H$, streamlining calculations while maintaining accuracy. By solving a generalised eigenvalue problem, our proposed algorithm achieves notable performance improvements, particularly in challenging scenarios where traditional spectral clustering methods struggle. We demonstrate its practical effectiveness through experiments on both synthetic and real-world datasets.