ICML 2025 Papers

Class imbalance remains a major challenge in machine learning, especially in multi-class problems with long-tailed distributions. Existing methods, such as data resampling, cost-sensitive techniques, and logistic loss modifications, though popular and often effective, lack solid theoretical foundations. As an example, we demonstrate that cost-sensitive methods are not Bayes-consistent. This paper introduces a novel theoretical framework for analyzing generalization in imbalanced classification. We propose a new class-imbalanced margin loss function for both binary and multi-class settings, prove its strong $H$-consistency, and derive corresponding learning guarantees based on empirical loss and a new notion of class-sensitive Rademacher complexity. Leveraging these theoretical results, we devise novel and general learning algorithms, IMMAX (*Imbalanced Margin Maximization*), which incorporate confidence margins and are applicable to various hypothesis sets. While our focus is theoretical, we also present extensive empirical results demonstrating the effectiveness of our algorithms compared to existing baselines.

Kernel-based hypothesis tests offer a flexible, non-parametric tool to detect high-order interactions in multivariate data, beyond pairwise relationships. Yet the scalability of such tests is limited by the computationally demanding permutation schemes used to generate null approximations. Here we introduce a family of permutation-free high-order tests for joint independence and partial factorisations of $d$ variables. Our tests eliminate the need for permutation-based approximations by leveraging V-statistics and a novel cross-centring technique to yield test statistics with a standard normal limiting distribution under the null. We present implementations of the tests and showcase their efficacy and scalability through synthetic datasets. We also show applications inspired by causal discovery and feature selection, which highlight both the importance of high-order interactions in data and the need for efficient computational methods.

Continual Learning (CL) strives to learn incrementally across tasks while mitigating catastrophic forgetting. A key challenge in CL is balancing stability (retaining prior knowledge) and plasticity (learning new tasks). While representative gradient projection methods ensure stability, they often limit plasticity. Model merging techniques offer promising solutions, but prior methods typically rely on empirical assumptions and carefully selected hyperparameters. In this paper, we explore the potential of model merging to enhance the stability-plasticity trade-off, providing theoretical insights that underscore its benefits. Specifically, we reformulate the merging mechanism using Bayesian continual learning principles and derive a closed-form solution for the optimal merging coefficient that adapts to the diverse characteristics of tasks. To validate our approach, we introduce a two-stage framework named BECAME, which synergizes the expertise of gradient projection and adaptive merging. Extensive experiments show that our approach outperforms state-of-the-art CL methods and existing merging strategies https://github.com/limei0818/BECAME.

Selecting high-quality candidates from large datasets is critical in applications such as drug discovery, precision medicine, and alignment of large language models (LLMs). While Conformal Selection (CS) provides rigorous uncertainty quantification, it is limited to univariate responses and scalar criteria. To address this, we propose Multivariate Conformal Selection (mCS), a generalization of CS designed for multivariate response settings. Our method introduces regional monotonicity and employs multivariate nonconformity scores to construct conformal $p$-values, enabling finite-sample False Discovery Rate (FDR) control. We present two variants: $\texttt{mCS-dist}$, using distance-based scores, and $\texttt{mCS-learn}$, which learns optimal scores via differentiable optimization. Experiments on simulated and real-world datasets demonstrate that mCS significantly improves selection power while maintaining FDR control, establishing it as a robust framework for multivariate selection tasks.

In class-incremental learning (CIL), effective incremental learning strategies are essential to mitigate task confusion and catastrophic forgetting, especially as the number of tasks $t$ increases. Current exemplar replay strategies impose $\mathcal{O}(t)$ memory/compute complexities. We propose an autoencoder-based hybrid replay (AHR) strategy that leverages our new hybrid autoencoder (HAE) to function as a compressor to alleviate the requirement for large memory, achieving $\mathcal{O}(0.1 t)$ at the worst case with the computing complexity of $\mathcal{O}(t)$ while accomplishing state-of-the-art performance. The decoder later recovers the exemplar data stored in the latent space, rather than in raw format. Additionally, HAE is designed for both discriminative and generative modeling, enabling classification and replay capabilities, respectively. HAE adopts the charged particle system energy minimization equations and repulsive force algorithm for the incremental embedding and distribution of new class centroids in its latent space. Our results demonstrate that AHR consistently outperforms recent baselines across multiple benchmarks while operating with the same memory/compute budgets. The source code is included in the supplementary material and will be open-sourced upon publication.

Interference, a key concept in causal inference, extends the reward modeling process by accounting for the impact of one unit's actions on the rewards of others. In contextual bandit (CB) settings where multiple units are present in the same round, interference can significantly affect the estimation of expected rewards for different arms, thereby influencing the decision-making process. Although some prior work has explored multi-agent and adversarial bandits in interference-aware settings, how to model interference in CB remains significantly underexplored. In this paper, we introduce a systematic framework to address interference in Linear CB (LinCB), bridging the gap between causal inference and online decision-making. We propose a series of algorithms that explicitly quantify the interference effect in the reward modeling process and provide comprehensive theoretical guarantees, including sublinear regret bounds, finite sample upper bounds, and asymptotic properties. The effectiveness of our approach is demonstrated through simulations and a synthetic data generated based on MovieLens data.

Flow matching (FM) models extend ODE sampler based diffusion models into a general framework, significantly reducing sampling steps through learned vector fields. However, the theoretical understanding of FM models, particularly how their sample trajectories interact with underlying data geometry, remains underexplored. A rigorous theoretical analysis of FM ODE is essential for sample quality, stability, and broader applicability. In this paper, we advance the theory of FM models through a comprehensive analysis of sample trajectories. Central to our theory is the discovery that the denoiser, a key component of FM models, guides ODE dynamics through attracting and absorbing behaviors that adapt to the data geometry. We identify and analyze the three stages of ODE evolution: in the initial and intermediate stages, trajectories move toward the mean and local clusters of the data. At the terminal stage, we rigorously establish the convergence of FM ODE under weak assumptions, addressing scenarios where the data lie on a low-dimensional submanifold---cases that previous results could not handle. Our terminal stage analysis offers insights into the memorization phenomenon and establishes equivariance properties of FM ODEs. These findings bridge critical gaps in understanding flow matching models, with practical implications for optimizing sampling strategies and architectures guided by the intrinsic geometry of data.

We study the question of volume optimality in split conformal regression, a topic still poorly understood in comparison to coverage control. Using the fact that the calibration step can be seen as an empirical volume minimization problem, we first derive a finite-sample upper-bound on the excess volume loss of the interval returned by the classical split method. This important quantity measures the difference in length between the interval obtained with the split method and the shortest oracle prediction interval. Then, we introduce *EffOrt*, a methodology that modifies the learning step so that the base prediction function is selected in order to minimize the length of the returned intervals. In particular, our theoretical analysis of the excess volume loss of the prediction sets produced by *EffOrt* reveals the links between the learning and calibration steps, and notably the impact of the choice of the function class of the base predictor. We also introduce *Ad-EffOrt*, an extension of the previous method, which produces intervals whose size adapts to the value of the covariate. Finally, we evaluate the empirical performance and the robustness of our methodologies.

The Fourier transform is a fundamental tool in computer science and signal processing. In particular, when the signal is sparse in the frequency domain---having only $k$ distinct frequencies---sparse Fourier transform (SFT) algorithms can recover the signal in a sublinear time (proportional to the sparsity $k$). Most prior research focused on SFT for discrete signals, designing both randomized and deterministic algorithms for one-dimensional and high-dimensional discrete signals. However, SFT for continuous signals (i.e., $x^*(t)=\sum_{j=1}^k v_j e^{2\pi \mathbf{i} f_j t}$ for $t\in [0,T]$) is a more challenging task. The discrete SFT algorithms are not directly applicable to continuous signals due to the sparsity blow-up from the discretization. Prior to this work, there is a randomized algorithm that achieves an $\ell_2$ recovery guarantee in $\widetilde{O}(k\cdot \mathrm{polylog}(F/\eta))$ time, where $F$ is the band-limit of the frequencies and $\eta$ is the frequency gap. Nevertheless, whether we can solve this problem without using randomness remains open. In this work, we address this gap and introduce the first sublinear-time deterministic sparse Fourier transform algorithm in the continuous setting. Specifically, our algorithm uses $\widetilde{O}(k^2 \cdot \mathrm{polylog}(F/\eta))$ samples and $\widetilde{O}(k^2 \cdot \mathrm{polylog}(F/\eta))$ time to reconstruct the on-grid signal with arbitrary noise that satisfies a mild condition. This is the optimal recovery guarantee that can be achieved by any deterministic approach.

Trajectory representation learning aims to transform raw trajectory data into compact and low-dimensional vectors that are suitable for downstream analysis. However, most existing methods adopt either a free-space view or a road-network view during the learning process, which limits their ability to capture the complex, multi-view spatiotemporal features inherent in trajectory data. Moreover, these approaches rely on task-specific model training, restricting their generalizability and effectiveness for diverse analysis tasks. To this end, we propose GTR, a general, multi-view, and dynamic Trajectory Representation framework built on a pre-train and fine-tune architecture. Specifically, GTR introduces a multi-view encoder that captures the intrinsic multi-view spatiotemporal features. Based on the pre-train and fine-tune architecture, we provide the spatio-temporal fusion pre-training with a spatio-temporal mixture of experts to dynamically combine spatial and temporal features, enabling seamless adaptation to diverse trajectory analysis tasks. Furthermore, we propose an online frozen-hot updating strategy to efficiently update the representation model, accommodating the dynamic nature of trajectory data. Extensive experiments on two real-world datasets demonstrate that GTR consistently outperforms 15 state-of-the-art methods across 6 mainstream trajectory analysis tasks. All source code and data are available at https://github.com/ZJU-DAILY/GTR.

In this paper, we theoretically study the offline alignment of language models with human preference feedback, under both preference label corruption and privacy protections. To this end, we propose a variant of \texttt{$\chi$PO} -- \texttt{Square}\texttt{$\chi$PO}, which is a simple one-line change of \texttt{$\chi$PO} with the standard log-loss replaced by a new square loss over probability. Thanks to the inherent nice properties of this new loss, we have advanced the state-of-the-art of differentially private and robust alignment. Specifically, for the local model of label privacy, \texttt{Square}\texttt{$\chi$PO} is the first one that attains optimal rate based on single-policy concentrability even with general function approximations. It also gives the first result under the central model of privacy protection over both prompts (responses) and labels. On the robustness side against Huber label corruption, \texttt{Square}\texttt{$\chi$PO} is the first alignment method that has a meaningful theoretical guarantee under general function approximations. More importantly, \texttt{Square}\texttt{$\chi$PO} can address privacy protection and corruption \emph{simultaneously}, where an interesting separation is observed, implying that the order of privacy and corruption matters. Furthermore, we show that \texttt{Square}\texttt{$\chi$PO} can also be easily extended to handle the scenario of the general preference model with state-of-the-art guarantees under corruption and privacy. Last but not least, all of our theoretical guarantees enjoy a unified analysis, building upon a new result on the generalization error bounds of least-square regression under corruption and privacy constraints, which we believe is of independent interest to the community.

Recently, federated multi-view clustering (FedMVC) has gained attention for its ability to mine complementary clustering structures from multiple clients without exposing private data. Existing methods mainly focus on addressing the feature heterogeneity problem brought by views on different clients and mitigating it using shared client information. Although these methods have achieved performance improvements, the information they choose to share, such as model parameters or intermediate outputs, inevitably raises privacy concerns. In this paper, we propose an Effective and Secure Federated Multi-view Clustering method, ESFMC, to alleviate the dilemma between privacy protection and performance improvement. This method leverages the information-theoretic perspective to split the features extracted locally by clients, retaining sensitive information locally and only sharing features that are highly relevant to the task. This can be viewed as a form of privacy-preserving information sharing, reducing privacy risks for clients while ensuring that the server can mine high-quality global clustering structures. Theoretical analysis and extensive experiments demonstrate that the proposed method more effectively mitigates the trade-off between privacy protection and performance improvement compared to state-of-the-art methods.

Large output spaces, also referred to as Extreme multilabel classification (XMC), is a setting that arises, e.g., in large-scale tagging and product-to-product recommendation, and is characterized by the number of labels ranging from hundreds of thousands to millions. This means that the linear classification head, usually only a tiny fraction of the overall model, turns into the main driver for compute and memory demand. Current state-of-the-art XMC methods predominantly rely on FP16-FP32 mixed-precision training, which we show can be unstable, and inefficient in terms of memory usage and computational overhead. Meanwhile, existing low-precision methods typically retain higher precision for the classification layer. In this work, we propose ELMO, a pure low-precision training framework for XMC models using BFloat16 and Float8 data types. By leveraging Kahan summation and stochastic rounding, we demonstrate that XMC models can be effectively trained entirely in Float8, without relying on single-precision master weights or tensor scaling. Low-precision training, combined with our proposed memory optimizations---gradient fusion and chunking---enables significant reductions in GPU memory usage. For example, we train a 3-million-label XMC model with only 6.6 GiB of GPU memory, compared to the 39.7GiB required by the optimized SOTA method, Renee without compromising accuracy.

$Q$-learning is one of the most fundamental reinforcement learning algorithms. It is widely believed that $Q$-learning with linear function approximation (i.e., linear $Q$-learning) suffers from possible divergence until the recent work Meyn (2024) which establishes the ultimate almost sure boundedness of the iterates of linear $Q$-learning. Building on this success, this paper further establishes the first $L^2$ convergence rate of linear $Q$-learning iterates (to a bounded set). Similar to Meyn (2024), we do not make any modification to the original linear $Q$-learning algorithm, do not make any Bellman completeness assumption, and do not make any near-optimality assumption on the behavior policy. All we need is an $\epsilon$-softmax behavior policy with an adaptive temperature. The key to our analysis is the general result of stochastic approximations under Markovian noise with fast-changing transition functions. As a side product, we also use this general result to establish the $L^2$ convergence rate of tabular $Q$-learning with an $\epsilon$-softmax behavior policy, for which we rely on a novel pseudo-contraction property of the weighted Bellman optimality operator.

The in-context learning paradigm with LLMs has been instrumental in advancing a wide range of natural language processing tasks. The selection of few-shot examples (exemplars / demonstration samples) is essential for constructing effective prompts under context-length budget constraints. In this paper, we formulate the exemplar selection task as a top-m best arms identification problem. A key challenge in this setup is the exponentially large number of arms that need to be evaluated to identify the m-best arms. We propose CASE (Challenger Arm Sampling for Exemplar selection), a novel sample-efficient selective exploration strategy that maintains a shortlist of “challenger” arms, which are current candidates for the top-m arms. In each iteration, only one of the arms from this shortlist or the current top-m set is pulled, thereby reducing sample complexity and, consequently, the number of LLM evaluations. Furthermore, we model the scores of exemplar subsets (arms) using a parameterized linear scoring function, leading to stochastic linear bandits setting. CASE achieves remarkable efficiency gains of up to 7× speedup in runtime while requiring 7× fewer LLM calls (87% reduction) without sacrificing performance compared to state-of-the-art exemplar selection methods. We release our code and data (https://github.com/kiranpurohit/CASE).

Class distribution mismatch (CDM) refers to the discrepancy between class distributions in training data and target tasks. Previous methods address this by designing classifiers to categorize classes known during training, while grouping unknown or new classes into an "other" category. However, they focus on semi-supervised scenarios and heavily rely on labeled data, limiting their applicability and performance. To address this, we propose Unsupervised Learning for Class Distribution Mismatch (UCDM), which constructs positive-negative pairs from unlabeled data for classifier training. Our approach randomly samples images and uses a diffusion model to add or erase semantic classes, synthesizing diverse training pairs. Additionally, we introduce a confidence-based labeling mechanism that iteratively assigns pseudo-labels to valuable real-world data and incorporates them into the training process. Extensive experiments on three datasets demonstrate UCDM’s superiority over previous semi-supervised methods. Specifically, with a 60\% mismatch proportion on Tiny-ImageNet dataset, our approach, without relying on labeled data, surpasses OpenMatch (with 40 labels per class) by 35.1%, 63.7%, and 72.5% in classifying known, unknown, and new classes.

We are born with the ability to learn concepts by comparing diverse observations. This helps us to understand the new world in a compositional manner and facilitates extrapolation, as objects naturally consist of multiple concepts. In this work, we argue that the cognitive mechanism of comparison, fundamental to human learning, is also vital for machines to recover true concepts underlying the data. This offers correctness guarantees for the field of concept learning, which, despite its impressive empirical successes, still lacks general theoretical support. Specifically, we aim to develop a theoretical framework for the identifiability of concepts with multiple classes of observations. We show that with sufficient diversity across classes, hidden concepts can be identified without assuming specific concept types, functional relations, or parametric generative models. Interestingly, even when conditions are not globally satisfied, we can still provide alternative guarantees for as many concepts as possible based on local comparisons, thereby extending the applicability of our theory to more flexible scenarios. Moreover, the hidden structure between classes and concepts can also be identified nonparametrically. We validate our theoretical results in both synthetic and real-world settings.

Pre-trained Vision-Language Models (VLMs) are becoming increasingly popular across various visual tasks, and several open-sourced VLM variants have been released. However, selecting the best-performing pre-trained VLM for a specific downstream task is challenging since no single VLM can achieve promising performance on all downstream tasks, and evaluating all available VLMs is impossible due to time and data limitations. To address this problem, this paper proposes a novel paradigm to select and reuse VLM for downstream tasks, called **M**odel **L**abel **L**earning (**MLL**). The proposal contains three key modules: *model labeling*, which assigns labels to each VLM to describe their specialty and utility; *model selection*, which matches the requirements of the target task with model labels; and *model reuse*, which applies selected VLMs to the target task in an ensemble manner. The proposal is highly computationally efficient and growable since the model labeling process is completed target task independent and the ability could grow with the number of candidate VLMs. We also introduce a new benchmark for evaluating VLM selection methods, including 49 VLMs and 17 target task datasets. Experimental results clearly demonstrate the effectiveness of the proposed method for selecting and reusing VLMs.

We revisit the Follow the Regularized Leader (FTRL) framework for Online Convex Optimization (OCO) over compact sets, focusing on achieving dynamic regret guarantees. Prior work has highlighted the framework’s limitations in dynamic environments due to its tendency to produce "lazy" iterates. However, building on insights showing FTRL's ability to produce "agile" iterates, we show that it can indeed recover known dynamic regret bounds through optimistic composition of future costs and careful linearization of past costs, which can lead to pruning some of them. This new analysis of FTRL against dynamic comparators yields a principled way to interpolate between greedy and agile updates and offers several benefits, including refined control over regret terms, optimism without cyclic dependence, and the application of minimal recursive regularization akin to AdaFTRL. More broadly, we show that it is not the "lazy" projection style of FTRL that hinders (optimistic) dynamic regret, but the decoupling of the algorithm’s state (linearized history) from its iterates, allowing the state to grow arbitrarily. Instead, pruning synchronizes these two when necessary.