ICML 2025 论文列表

Domain randomization in reinforcement learning is an established technique for increasing the robustness of control policies learned in simulation. By randomizing properties of the environment during training, the learned policy can be robust to uncertainty along the randomized dimensions. While the environment distribution is typically specified by hand, in this paper we investigate the problem of automatically discovering this sampling distribution via entropy-regularized reward maximization of a neural sampling distribution in the form of a normalizing flow. We show that this architecture is more flexible and results in better robustness than existing approaches to learning simple parameterized sampling distributions. We demonstrate that these policies can be used to learn robust policies for contact-rich assembly tasks. Additionally, we explore how these sampling distributions, in combination with a privileged value function, can be used for out-of-distribution detection in the context of an uncertainty-aware multi-step manipulation planner.

Safe offline reinforcement learning aims to develop policies that maximize cumulative rewards while satisfying safety constraints without the need for risky online interaction. However, existing methods often struggle with the out-of-distribution (OOD) problem, leading to potentially unsafe and suboptimal policies. To address this issue, we first propose Constrained Implicit Q-learning (CIQL), a novel algorithm designed to avoid the OOD problem. In particular, CIQL expands the implicit update of reward value functions to constrained settings and then estimates cost value functions under the same implicit policy. Despite its advantages, the further performance improvement of CIQL is still hindered by the inaccurate discounted approximations of constraints. Thus, we further propose Constraint-Conditioned Implicit Q-learning (C2IQL). Building upon CIQL, C2IQL employs a cost reconstruction model to derive non-discounted cumulative costs from discounted values and incorporates a flexible, constraint-conditioned mechanism to accommodate dynamic safety constraints. Experiment results on DSRL benchmarks demonstrate the superiority of C2IQL compared to baseline methods in achieving higher rewards while guaranteeing safety constraints under different threshold conditions.

Recent advances in bioengineering have enabled the creation of biological neural networks in vitro, significantly reducing the cost, ethical hurdles, and complexity of experimentation with genuine biological neural computation. In this position paper, we argue that this trend offers a unique and timely opportunity to put our understanding of neural computation to the test. By designing artificial neural networks that can interact and control living neural systems, it is becoming possible to validate computational models beyond simulation and gain empirical insights to help unlock more robust and energy-efficient next-generation AI systems. We provide an overview of key technologies, challenges, and principles behind this development and describe strategies and opportunities for novel machine learning research in this emerging field. We also discuss implications and fundamental questions that could be answered as this technology advances, exemplifying the longer-term impact of increasingly sophisticated in vitro neural networks.

In real-world crowdsourcing scenarios, most workers often annotate a few instances only, which results in a significantly sparse crowdsourced label matrix and subsequently harms the performance of label integration algorithms. Recent work called worker similarity-based label completion (WSLC) has been proven to be an effective algorithm to addressing this issue. However, WSLC considers solely the correlation of the labels annotated by different workers on per individual instance while totally ignoring the correlation of the labels annotated by different workers among similar instances. To fill this gap, we propose a novel label distribution propagation-based label completion (LDPLC) algorithm. At first, we use worker similarity weighted majority voting to initialize a label distribution for each missing label. Then, we design a label distribution propagation algorithm to enable each missing label of each instance to iteratively absorb its neighbors’ label distributions. Finally, we complete each missing label based on its converged label distribution. Experimental results on both real-world and simulated crowdsourced datasets show that LDPLC significantly outperforms WSLC in enhancing the performance of label integration algorithms. Our codes and datasets are available at https://github.com/jiangliangxiao/LDPLC.

Transformer language models (LMs) exhibit behaviors—from storytelling to code generation—that seem to require tracking the unobserved state of an evolving world. How do they do this? We study state tracking in LMs trained or fine-tuned to compose permutations (i.e., to compute the order of a set of objects after a sequence of swaps). Despite the simple algebraic structure of this problem, many other tasks (e.g., simulation of finite automata and evaluation of boolean expressions) can be reduced to permutation composition, making it a natural model for state tracking in general. We show that LMs consistently learn one of two state tracking mechanisms for this task. The first closely resembles the “associative scan” construction used in recent theoretical work by Liu et al. (2023) and Merrill et al. (2024). The second uses an easy-to-compute feature (permutation parity) to partially prune the space of outputs, and then refines this with an associative scan. LMs that learn the former algorithm tend to generalize better and converge faster, and we show how to steer LMs toward one or the other with intermediate training tasks that encourage or suppress the heuristics. Our results demonstrate that transformer LMs, whether pre-trained or fine-tuned, can learn to implement efficient and interpretable state-tracking mechanisms, and the emergence of these mechanisms can be predicted and controlled. Code and data are available at https://github.com/belindal/state-tracking

Federated learning (FL) presents a promising strategy for distributed and privacy-preserving learning, yet struggles with performance issues in the presence of heterogeneous data distributions. Recently, a series of works based on sharpness-aware minimization (SAM) have emerged to improve local learning generality, proving to be effective in mitigating data heterogeneity effects. However, most SAM-based methods do not directly consider the global objective and require two backward pass per iteration, resulting in diminished effectiveness. To overcome these two bottlenecks, we leverage the global model trajectory to directly measure sharpness for the global objective, requiring only a single backward pass. We further propose a novel and general algorithm FedGMT to overcome data heterogeneity and the pitfalls of previous SAM-based methods. We analyze the convergence of FedGMT and conduct extensive experiments on visual and text datasets in a variety of scenarios, demonstrating that FedGMT achieves competitive accuracy with state-of-the-art FL methods while minimizing computation and communication overhead. Code is available at https://github.com/harrylee999/FL-SAM.

Many production lines require active control mechanisms, such as adaptive routing, worker reallocation, and rescheduling, to maintain optimal performance. However, designing these control systems is challenging for various reasons, and while reinforcement learning (RL) has shown promise in addressing these challenges, a standardized and general framework is still lacking. In this work, we introduce LineFlow, an extensible, open-source Python framework for simulating production lines of arbitrary complexity and training RL agents to control them. To demonstrate the capabilities and to validate the underlying theoretical assumptions of LineFlow, we formulate core subproblems of active line control in ways that facilitate mathematical analysis. For each problem, we provide optimal solutions for comparison. We benchmark state-of-the-art RL algorithms and show that the learned policies approach optimal performance in well-understood scenarios. However, for more complex, industrial-scale production lines, RL still faces significant challenges, highlighting the need for further research in areas such as reward shaping, curriculum learning, and hierarchical control.

Subgraph representation learning has attracted growing interest due to its wide applications in various domains. However, existing methods primarily focus on local neighborhood structures while overlooking the significant impact of global structural information, in particular the influence of multi-hop neighbors beyond immediate neighborhoods. This presents two key challenges: how to effectively capture the structural relationships between distant nodes, and how to prevent excessive aggregation of global structural information from weakening the discriminative ability of subgraph representations. To address these challenges, we propose GPEN (Global Position Encoding Network). GPEN leverages a hierarchical tree structure to encode each node's global position based on its path distance to the root node, enabling a systematic way to capture relationships between distant nodes. Furthermore, we introduce a boundary-aware convolution module that selectively integrates global structural information while maintaining the unique structural patterns of each subgraph. Extensive experiments on eight public datasets identify that GPEN significantly outperforms state-of-the-art methods in subgraph representation learning.

*Diffusion-based purification* (DBP) methods aim to remove adversarial noise from the input sample by first injecting Gaussian noise through a forward diffusion process, and then recovering the clean example through a reverse generative process. In the above process, how much Gaussian noise is injected to the input sample is key to the success of DBP methods, which is controlled by a constant noise level $t*$ for all samples in existing methods. In this paper, we discover that an optimal $t*$ for each sample indeed could be different. Intuitively, the cleaner a sample is, the less the noise it should be injected, and vice versa. Motivated by this finding, we propose a new framework, called Sample-specific Score-aware Noise Injection (SSNI). Specifically, SSNI uses a pre-trained score network to estimate how much a data point deviates from the clean data distribution (i.e., score norms). Then, based on the magnitude of score norms, SSNI applies a reweighting function to adaptively adjust $t*$ for each sample, achieving sample-specific noise injections. Empirically, incorporating our framework with existing DBP methods results in a notable improvement in both accuracy and robustness on CIFAR-10 and ImageNet-1K, highlighting the necessity to allocate *distinct noise levels to different samples* in DBP methods. Our code is available at: https://github.com/tmlr-group/SSNI.

Identifying the most representative subset for a close-to-submodular objective while satisfying the predefined partition constraint is a fundamental task with numerous applications in machine learning. However, the existing distorted local-search methods are often hindered by their prohibitive query complexities and the rigid requirement for prior knowledge of difficult-to-obtain structural parameters. To overcome these limitations, we introduce a novel algorithm titled **Multinoulli-SCG**, which not only is parameter-free, but also can achieve the same approximation guarantees as the distorted local-search methods with significantly fewer function evaluations. The core of our **Multinoulli-SCG** algorithm is an innovative continuous-relaxation framework named Multinoulli Extension(***ME***), which can effectively convert the discrete subset selection problem subject to partition constraints into a solvable continuous maximization focused on learning the optimal multinoulli priors across the considered partition. In sharp contrast with the well-established multi-linear extension for submodular subset selection, a notable advantage of our proposed ***ME*** is its intrinsic capacity to provide a lossless rounding scheme for any set function. Finally, we validate the practical efficacy of our proposed algorithms by applying them to video summarization, bayesian A-optimal design and coverage maximization.

In recent years, the pursuit of higher expressive power in graph neural networks (GNNs) has often led to more complex aggregation mechanisms and deeper architectures. To address these issues, we have identified redundant structures in GNNs, and by pruning them, we propose Pruned MP-GNNs, K-Path GNNs, and K-Hop GNNs based on their original architectures. We show that 1) Although some structures are pruned in Pruned MP-GNNs and Pruned K-Path GNNs, their expressive power has not been compromised. 2) K-Hop MP-GNNs and their pruned architecture exhibit equivalent expressiveness on regular and strongly regular graphs. 3) The complexity of pruned K-Path GNNs and pruned K-Hop GNNs is lower than that of MP-GNNs, yet their expressive power is higher. Experimental results validate our refinements, demonstrating competitive performance across benchmark datasets with improved efficiency.

Latent diffusion models have recently demonstrated superior capabilities in many downstream image synthesis tasks. However, customization of latent diffusion models using unauthorized data can severely compromise the privacy and intellectual property rights of data owners. Adversarial examples as protective perturbations have been developed to defend against unauthorized data usage by introducing imperceptible noise to customization samples, preventing diffusion models from effectively learning them. In this paper, we first reveal that the primary reason adversarial examples are effective as protective perturbations in latent diffusion models is the distortion of their latent representations, as demonstrated through qualitative and quantitative experiments. We then propose the Contrastive Adversarial Training (CAT) utilizing lightweight adapters as an adaptive attack against these protection methods, highlighting their lack of robustness. Extensive experiments demonstrate that our CAT method significantly reduces the effectiveness of protective perturbations in customization, urging the community to reconsider and improve the robustness of existing protective perturbations. The code is available at \url{https://github.com/senp98/CAT}.

The Median of Means (MoM) is a mean estimator that has gained popularity in the context of heavy-tailed data. In this work, we analyze its performance in the task of simultaneously estimating the mean of each function in a class $\mathcal{F}$ when the data distribution possesses only the first $p$ moments for $p \in (1,2]$. We prove a new sample complexity bound using a novel symmetrization technique that may be of independent interest. Additionally, we present applications of our result to $k$-means clustering with unbounded inputs and linear regression with general losses, improving upon existing works.

Real-world time series inherently exhibit significant non-stationarity, posing substantial challenges for forecasting. To address this issue, this paper proposes a novel prediction framework, TimeStacker, designed to overcome the limitations of existing models in capturing the characteristics of non-stationary signals. By employing a unique stacking mechanism, TimeStacker effectively captures global signal features while thoroughly exploring local details. Furthermore, the framework integrates a frequency-based self-attention module, significantly enhancing its feature modeling capabilities. Experimental results demonstrate that TimeStacker achieves outstanding performance across multiple real-world datasets, including those from the energy, finance, and weather domains. It not only delivers superior predictive accuracy but also exhibits remarkable advantages with fewer parameters and higher computational efficiency.

Attention mechanisms are central to the success of large language models (LLMs), enabling them to capture intricate token dependencies and implicitly assign importance to each token. Recent studies have revealed the sink token, which receives disproportionately high attention despite their limited semantic role. In this paper, we first expand the relationship between the sink token and other tokens, moving beyond attention to explore their similarity in hidden states, considering the layer depth. We observe that as the layers get deeper, the cosine similarity between the normalized hidden states of the sink token and those of other tokens increases, and that the normalized hidden states of the sink token exhibit negligible changes. These imply that other tokens consistently are directed toward the sink token throughout the layers. Next, we propose a dynamic token selection method, called OrthoRank, using these findings to select important tokens. Specifically, in a certain layer, we define token importance by the speed at which the token moves toward the sink token. This is converted into orthogonality with the sink token, meaning that tokens that are more orthogonal to the sink token are assigned greater importance. Finally, through extensive experiments, we demonstrated that our method results in lower perplexity and higher zero-shot accuracy compared to layer pruning methods at the same sparsity ratio with comparable throughput, while also achieving superior performance on LongBench.

List learning is an important topic in both theoretical and empirical machine learning research, playing a key role in the recent breakthrough result of (Brukhim et al., 2022) on the characterization of multiclass PAC learnability, as well as addressing label ambiguity in computer vision classification tasks, among others. In this paper, we study the problem of list transductive online learning. In this framework, the learner outputs a list of multiple labels for each instance rather than just one, as in traditional multiclass classification. In the realizable setting, we demonstrate a trichotomy of possible rates of the minimax number of mistakes. In particular, if the learner plays for $\text{T} \in \mathbb{N}$ rounds, its minimax number of mistakes can only be of the orders $\Theta(\text{T})$, $\Theta(\log \text{T})$, or $\Theta(1)$. This resolves an open question raised by (Hanneke et al., 2024). On the other hand, in the agnostic setting, we characterize the learnability by constructively proving the $\widetilde{\mathcal{O}}(\sqrt{\text{T}})$ upper bound on the minimax expected regret. Along the way, we also answer another open question asked by (Moran et al., 2023). To establish these results, we introduce two new combinatorial complexity dimensions, called the Level-constrained $(\mathrm{L+1})$-Littlestone dimension and Level-constrained $(\mathrm{L+1})$-Branching dimension, if the list size is $\mathrm{L} \in \mathbb{N}$. Eventually, we conclude our work by raising an open question regarding eliminating the factor list size, which seems to be a crucial step, as it has consistently appeared in previous works on this subject.

A data analysis pipeline is a structured sequence of steps that transforms raw data into meaningful insights by integrating various analysis algorithms. In this paper, we propose a novel statistical test to assess the significance of data analysis pipelines. Our approach enables the systematic development of valid statistical tests applicable to any feature selection pipeline composed of predefined components. We develop this framework based on selective inference, a statistical technique that has recently gained attention for data-driven hypotheses. As a proof of concept, we focus on feature selection pipelines for linear models, composed of three missing value imputation algorithms, three outlier detection algorithms, and three feature selection algorithms. We theoretically prove that our statistical test can control the probability of false positive feature selection at any desired level, and demonstrate its validity and effectiveness through experiments on synthetic and real data. Additionally, we present an implementation framework that facilitates testing across any configuration of these feature selection pipelines without extra implementation costs.

This paper investigates the problem of certifying optimality for sparse generalized linear models (GLMs), where sparsity is enforced through an $\ell_0$ cardinality constraint. While branch-and-bound (BnB) frameworks can certify optimality by pruning nodes using dual bounds, existing methods for computing these bounds are either computationally intensive or exhibit slow convergence, limiting their scalability to large-scale problems. To address this challenge, we propose a first-order proximal gradient algorithm designed to solve the perspective relaxation of the problem within a BnB framework. Specifically, we formulate the relaxed problem as a composite optimization problem and demonstrate that the proximal operator of the non-smooth component can be computed exactly in log-linear time complexity, eliminating the need to solve a computationally expensive second-order cone program. Furthermore, we introduce a simple restart strategy that enhances convergence speed while maintaining low per-iteration complexity. Extensive experiments on synthetic and real-world datasets show that our approach significantly accelerates dual bound computations and is highly effective in providing optimality certificates for large-scale problems.