ICML 2025 Papers

Non-stationary online learning has drawn much attention in recent years. Despite considerable progress, dynamic regret minimization has primarily focused on convex functions, leaving the functions with stronger curvature (e.g., squared or logistic loss) underexplored. In this work, we address this gap by showing that the regret can be substantially improved by leveraging the concept of mixability, a property that generalizes exp-concavity to effectively capture loss curvature. Let $d$ denote the dimensionality and $P_T$ the path length of comparators that reflects the environmental non-stationarity. We demonstrate that an exponential-weight method with fixed-share updates achieves an $\mathcal{O}(d T^{1/3} P_T^{2/3} \log T)$ dynamic regret for mixable losses, improving upon the best-known $\mathcal{O}(d^{10/3} T^{1/3} P_T^{2/3} \log T)$ result (Baby & Wang, 2021) in $d$. More importantly, this improvement arises from a simple yet powerful analytical framework that exploits the mixability, which avoids the Karush–Kuhn–Tucker-based analysis required by existing work.

We study *online multicalibration*, a framework for ensuring calibrated predictions across multiple groups in adversarial settings, across $T$ rounds. Although online calibration is typically studied in the $\ell_1$ norm, prior approaches to online multicalibration have taken the indirect approach of obtaining rates in other norms (such as $\ell_2$ and $\ell_{\infty}$) and then transferred these guarantees to $\ell_1$ at additional loss. In contrast, we propose a direct method that achieves improved and oracle-efficient rates of $\widetilde{\mathcal{O}}(T^{-1/3})$ and $\widetilde{\mathcal{O}}(T^{-1/4})$ respectively, for online $\ell_1$-multicalibration. Our key insight is a novel reduction of online $\ell_1$-multicalibration to an online learning problem with product-based rewards, which we refer to as *online linear-product optimization* ($\mathtt{OLPO}$). To obtain the improved rate of $\widetilde{\mathcal{O}}(T^{-1/3})$, we introduce a linearization of $\mathtt{OLPO}$ and design a no-regret algorithm for this linearized problem. Although this method guarantees the desired sublinear rate (nearly matching the best rate for online calibration), it is computationally expensive when the group family $\mathcal{H}$ is large or infinite, since it enumerates all possible groups. To address scalability, we propose a second approach to $\mathtt{OLPO}$ that makes only a polynomial number of calls to an offline optimization (*multicalibration evaluation*) oracle, resulting in *oracle-efficient* online $\ell_1$-multicalibration with a corresponding rate of $\widetilde{\mathcal{O}}(T^{-1/4})$. Our framework also extends to certain infinite families of groups (e.g., all linear functions on the context space) by exploiting a $1$-Lipschitz property of the $\ell_1$-multicalibration error with respect to $\mathcal{H}$.

Online multiple hypothesis testing has attracted a lot of attention in many applications, e.g., anomaly status detection and stock market price monitoring. The state-of-the-art generalized $\alpha$-investing (GAI) algorithms can control online false discovery rate (FDR) on p-values only under specific dependence structures, a situation that rarely occurs in practice. The e-LOND algorithm (Xu & Ramdas, 2024) utilizes e-values to achieve online FDR control under arbitrary dependence but suffers from a significant loss in power as testing levels are derived from pre-specified descent sequences. To address these limitations, we propose a novel framework on valid e-values named e-GAI. The proposed e-GAI can ensure provable online FDR control under more general dependency conditions while improving the power by dynamically allocating the testing levels. These testing levels are updated not only by relying on both the number of previous rejections and the prior costs, but also, differing from the GAI framework, by assigning less $\alpha$-wealth for each rejection from a risk aversion perspective. Within the e-GAI framework, we introduce two new online FDR procedures, e-LORD and e-SAFFRON, and provide strategies for the long-term performance to address the issue of $\alpha$-death, a common phenomenon within the GAI framework. Furthermore, we demonstrate that e-GAI can be generalized to conditionally super-uniform p-values. Both simulated and real data experiments demonstrate the advantages of both e-LORD and e-SAFFRON in FDR control and power.

Most learning algorithms with formal regret guarantees assume that all mistakes are recoverable and essentially rely on trying all possible behaviors. This approach is problematic when some mistakes are *catastrophic*, i.e., irreparable. We propose an online learning problem where the goal is to minimize the chance of catastrophe. Specifically, we assume that the payoff in each round represents the chance of avoiding catastrophe in that round and try to maximize the product of payoffs (the overall chance of avoiding catastrophe) while allowing a limited number of queries to a mentor. We also assume that the agent can transfer knowledge between similar inputs. We first show that in general, any algorithm either queries the mentor at a linear rate or is nearly guaranteed to cause catastrophe. However, in settings where the mentor policy class is learnable in the standard online model, we provide an algorithm whose regret and rate of querying the mentor both approach 0 as the time horizon grows. Although our focus is the product of payoffs, we provide matching bounds for the typical additive regret. Conceptually, if a policy class is learnable in the absence of catastrophic risk, it is learnable in the presence of catastrophic risk if the agent can ask for help.

Strategic classification addresses a learning problem where a decision-maker implements a classifier over agents who may manipulate their features in order to receive favorable predictions. In the standard model of online strategic classification, in each round, the decision-maker implements and publicly reveals a classifier, after which agents perfectly best respond based on this knowledge. However, in practice, whether to disclose the classifier is often debated---some decision-makers believe that hiding the classifier can prevent misclassification errors caused by manipulation. In this paper, we formally examine how limiting the agents' access to the current classifier affects the decision-maker's performance. Specifically, we consider an extended online strategic classification setting where agents lack direct knowledge about the current classifier and instead manipulate based on a weighted average of historically implemented classifiers. Our main result shows that in this setting, the decision-maker incurs $(1-\gamma)^{-1}$ or $k_{\text{in}}$ times more mistakes compared to the full-knowledge setting, where $k_{\text{in}}$ is the maximum in-degree of the manipulation graph (representing how many distinct feature vectors can be manipulated to appear as a single one), and $\gamma$ is the discount factor indicating agents' memory of past classifiers. Our results demonstrate how withholding access to the classifier can backfire and degrade the decision-maker's performance in online strategic classification.

Existing algorithms for online conformal prediction---guaranteeing marginal coverage in adversarial settings---are variants of online gradient descent (OGD), but their analyses of worst-case coverage do not follow from the regret guarantee of OGD. What is the relationship between no-regret learning and online conformal prediction? We observe that although standard regret guarantees imply marginal coverage in i.i.d. settings, this connection fails as soon as we either move to adversarial environments or ask for group conditional coverage. On the other hand, we show a tight connection between *threshold calibrated* coverage and swap-regret in adversarial settings, which extends to group-conditional (multi-valid) coverage. We also show that algorithms in the *follow the regularized leader* family of no regret learning algorithms (which includes online gradient descent) can be used to give group-conditional coverage guarantees in adversarial settings for arbitrary grouping functions. Via this connection we analyze and conduct experiments using a multi-group generalization of the ACI algorithm of Gibbs & Candes (2021).

Conformal prediction has emerged as an effective strategy for uncertainty quantification by modifying a model to output sets of labels instead of a single label. These prediction sets come with the guarantee that they contain the true label with high probability. However, conformal prediction typically requires a large calibration dataset of i.i.d. examples. We consider the online learning setting, where examples arrive over time, and the goal is to construct prediction sets dynamically. Departing from existing work, we assume semi-bandit feedback, where we *only observe the true label if it is contained in the prediction set*. For instance, consider calibrating a document retrieval model to a new domain; in this setting, a user would only be able to provide the true label if the target document is in the prediction set of retrieved documents. We propose a novel conformal prediction algorithm targeted at this setting, and prove that it obtains sublinear regret compared to the optimal conformal predictor. We evaluate our algorithm on a retrieval task, an image classification task, and an auction price-setting task, and demonstrate that it empirically achieves good performance compared to several baselines.

In this paper, we propose an improved online confidence bound for multinomial logistic (MNL) models and apply this result to MNL bandits, achieving variance-dependent optimal regret. Recently, Lee & Oh (2024) established an online confidence bound for MNL models and achieved nearly minimax-optimal regret in MNL bandits. However, their results still depend on the norm-boundedness of the unknown parameter $B$ and the maximum size of possible outcomes $K$. To address this, we first derive an online confidence bound of $\mathcal{O} (\sqrt{d \log t} + B )$, which is a significant improvement over the previous bound of $\mathcal{O} (B \sqrt{d} \log t \log K )$ (Lee & Oh, 2024). This is mainly achieved by establishing tighter self-concordant properties of the MNL loss and introducing a novel intermediary term to bound the estimation error. Using this new online confidence bound, we propose a constant-time algorithm, **OFU-MNL++**, which achieves a variance-dependent regret bound of $\mathcal{O} \Big( d \log T \sqrt{ \sum_{t=1}^T \sigma_t^2 } \Big) $ for sufficiently large $T$, where $\sigma_t^2$ denotes the variance of the rewards at round $t$, $d$ is the dimension of the contexts, and $T$ is the total number of rounds. Furthermore, we introduce an Maximum Likelihood Estimation (MLE)-based algorithm that achieves an anytime, **OFU-M$^2$NL**, $\operatorname{poly}(B)$-free regret of $\mathcal{O} \Big( d \log (BT) \sqrt{ \sum_{t=1}^T \sigma_t^2 } \Big) $.

The contextual multi-armed bandit (MAB) is a widely used framework for problems requiring sequential decision-making under uncertainty, such as recommendation systems. In applications involving a large number of users, the performance of contextual MAB can be significantly improved by facilitating collaboration among multiple users. This has been achieved by the clustering of bandits (CB) methods, which adaptively group the users into different clusters and achieve collaboration by allowing the users in the same cluster to share data. However, classical CB algorithms typically rely on numerical reward feedback, which may not be practical in certain real-world applications. For instance, in recommendation systems, it is more realistic and reliable to solicit preference feedback between pairs of recommended items rather than absolute rewards. To address this limitation, we introduce the first "clustering of dueling bandit algorithms" to enable collaborative decision-making based on preference feedback. We propose two novel algorithms: (1) Clustering of Linear Dueling Bandits (COLDB) which models the user reward functions as linear functions of the context vectors, and (2) Clustering of Neural Dueling Bandits (CONDB) which uses a neural network to model complex, non-linear user reward functions. Both algorithms are supported by rigorous theoretical analyses, demonstrating that user collaboration leads to improved regret bounds. Extensive empirical evaluations on synthetic and real-world datasets further validate the effectiveness of our methods, establishing their potential in real-world applications involving multiple users with preference-based feedback.

Out-of-distribution (OOD) detection task is significant in reliable and safety-critical applications. Existing approaches primarily focus on developing the powerful score function, but overlook the design of decision-making rules based on these score function. In contrast to prior studies, we rethink the OOD detection task from an perspective of online multiple hypothesis testing. We then propose a novel generalized LOND (g-LOND) algorithm to solve the above problem. Theoretically, the g-LOND algorithm controls false discovery rate (FDR) at pre-specified level without the consideration for the dependence between the p-values. Furthermore, we prove that the false positive rate (FPR) of the g-LOND algorithm converges to zero in probability based on the generalized Gaussian-like distribution family. Finally, the extensive experimental results verify the effectiveness of g-LOND algorithm for OOD detection.

Online linear programming (OLP) has found broad applications in revenue management and resource allocation. State-of-the-art OLP algorithms achieve low regret by repeatedly solving linear programming (LP) subproblems that incorporate updated resource information. However, LP-based methods are computationally expensive and often inefficient for large-scale applications. By contrast, recent first-order OLP algorithms are more computationally efficient but typically suffer from weaker regret guarantees. To address these shortcomings, we propose a new algorithm that combines the strengths of LP-based and first-order OLP algorithms. Our algorithm re-solves the LP subproblems periodically at a predefined frequency $f$ and uses the latest dual prices to guide online decision-making. In parallel, a first-order method runs during each interval between LP re-solves and smooths resource consumption. Our algorithm achieves $\mathcal{O}(\log (T/f) + \sqrt{f})$ regret and delivers a "wait-less" online decision-making process that balances computational efficiency and regret guarantees. Extensive experiments demonstrate at least $10$-fold improvements in regret over first-order methods and $100$-fold improvements in runtime over LP-based methods.

Multi-Label Online Continual Learning (MOCL) requires models to learn continuously from endless multi-label data streams, facing complex challenges including persistent catastrophic forgetting, potential missing labels, and uncontrollable imbalanced class distributions. While existing MOCL methods attempt to address these challenges through various techniques, \textit{they all overlook label-specific region identifying and feature learning} - a fundamental solution rooted in multi-label learning but challenging to achieve in the online setting with incremental and partial supervision. To this end, we first leverage the inherent structural information of input data to evaluate and verify the innate localization capability of different pre-trained models. Then, we propose CUTER (CUT-out-and-Experience-Replay), a simple yet versatile strategy that provides fine-grained supervision signals by further identifying, strengthening and cutting out label-specific regions for efficient experience replay. It not only enables models to simultaneously address catastrophic forgetting, missing labels, and class imbalance challenges, but also serves as an orthogonal solution that seamlessly integrates with existing approaches. Extensive experiments on multiple multi-label image benchmarks demonstrate the superiority of our proposed method. The code is available at \href{https://github.com/wxr99/Cut-Replay}{https://github.com/wxr99/Cut-Replay}

We consider a setting in which the agent aims to maximize the expected cumulative reward, subject to a constraint that the entropic risk of the total utility exceeds a given threshold. Unlike the risk-neutral case, standard primal-dual approaches fail to directly yield regret and violation bounds, as value iteration with respect to a combined state-action value function is not applicable in the risk-sensitive setting. To address this, we adopt the Optimized Certainty Equivalent (OCE) representation of the entropic risk measure and reformulate the problem by augmenting the state space with a continuous budget variable. We then propose a primal-dual algorithm tailored to this augmented formulation. In contrast to the standard approach for risk-neutral CMDPs, our method incorporates a truncated dual update to account for the possible absence of strong duality. We show that the proposed algorithm achieves regret of $\tilde{\mathcal{O}}\big(V_{g,\max}K^{3/4} + \sqrt{H^4 S^2 A \log(1/\delta)}K^{3/4}\big)$ and constraint violation of $\tilde{\mathcal{O}}\big(V_{g,\max} \sqrt{ {H^3 S^2 A \log(1/\delta)}}K^{3/4} \big)$ with probability at least $1-\delta$, where $S$ and $A$ denote the cardinalities of the state and action spaces, respectively, $H$ is the episode length, $K$ is the number of episodes, $\alpha < 0$ is the risk-aversion parameter, and $V_{g,\max} = \frac{1}{|\alpha|}(\exp(|\alpha|H) - 1)$. *To the best of our knowledge, this is the first result establishing sublinear regret and violation bounds for the risk-sensitive CMDP problem.*

Offline-to-online reinforcement learning (RL) aims to integrate the complementary strengths of offline and online RL by pre-training an agent offline and subsequently fine-tuning it through online interactions. However, recent studies reveal that offline pre-trained agents often underperform during online fine-tuning due to inaccurate value estimation caused by distribution shift, with random initialization proving more effective in certain cases. In this work, we propose a novel method, Online Pre-Training for Offline-to-Online RL (OPT), explicitly designed to address the issue of inaccurate value estimation in offline pre-trained agents. OPT introduces a new learning phase, Online Pre-Training, which allows the training of a new value function tailored specifically for effective online fine-tuning. Implementation of OPT on TD3 and SPOT demonstrates an average 30\% improvement in performance across a wide range of D4RL environments, including MuJoCo, Antmaze, and Adroit.

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.

Although the differential privacy (DP) of decentralized online learning has garnered considerable attention recently, existing algorithms are unsatisfactory due to their inability to achieve $(\epsilon, 0)$-DP over all $T$ rounds, recover the optimal regret in the non-private case, and maintain the lightweight computation under complex constraints. To address these issues, we first propose a new decentralized online learning algorithm satisfying $(\epsilon, 0)$-DP over $T$ rounds, and show that it can achieve $\widetilde{O}(n(\rho^{-1/4}+\epsilon^{-1}\rho^{1/4})\sqrt{T})$ and $\widetilde{O}(n (\rho^{-1/2}+\epsilon^{-1}))$ regret bounds for convex and strongly convex functions respectively, where $n$ is the number of local learners and $\rho$ is the spectral gap of the communication matrix. As long as $\epsilon=\Omega(\sqrt{\rho})$, these bounds nearly match existing lower bounds in the non-private case, which implies that $(\epsilon, 0)$-DP of decentralized online learning may be ensured nearly for free. Our key idea is to design a block-decoupled accelerated gossip strategy that can be incorporated with the classical tree-based private aggregation, and also enjoys a faster average consensus among local learners. Furthermore, we develop a projection-free variant of our algorithm to keep the efficiency under complex constraints. As a trade-off, the above regret bounds degrade to $\widetilde{O}(n(T^{3/4}+\epsilon^{-1}T^{1/4}))$ and $\widetilde{O}(n(T^{2/3}+\epsilon^{-1}))$ respectively, which however are even better than the existing private centralized projection-free online algorithm.