Diffusion models are increasingly used as powerful conditional generators, yet real deployments often involve multiple target distributions arising from different tasks, e.g., diverse prompt domains in text-to-image generation, or multiple environments in robotics with diffusion policies. This naturally leads to a multi-objective learning (MOL) problem. A key challenge is that achieving good Pareto trade-offs can require a generalist model class with substantially larger capacity than what suffices for solving any individual task, thereby increasing statistical cost since sample complexity typically scales with the model complexity. To reconcile this, we develop a principled MOL framework for diffusion models with limited data: a semi-supervised regime where paired (labeled) samples are scarce, but (unlabeled) condition data are abundant. We propose a two-stage training procedure that first fits lightweight specialist models from limited paired data, and then distills them into a generalist model by generating pseudo-samples. We establish generalization bounds showing that the required number of paired samples only depends on the complexity of the specialist model classes. We further extend the theory to diffusion policies for sequential decision making to account for distribution shift in on-policy rollouts. Extensive experiments on robotic control and image restoration tasks are conducted to verify our theoretical results.

We provide a unifying framework for the design and analysis of multi-calibrated predictors. By placing the multi-calibration problem in the general setting of multi-objective learning---where learning guarantees must hold simultaneously over a set of distributions and loss functions---we exploit connections to game dynamics to achieve state-of-the-art guarantees for a diverse set of multi-calibration learning problems. In addition to shedding light on existing multi-calibration guarantees and greatly simplifying their analysis, our approach also yields improved guarantees, such as error tolerances that scale with the square-root of group size versus the constant tolerances guaranteed by prior works, and improving the complexity of $k$-class multi-calibration by an exponential factor of $k$ versus Gopalan et al.. Beyond multi-calibration, we use these game dynamics to address emerging considerations in the study of group fairness and multi-distribution learning.

Multi-objective learning (MOL) often arises in emerging machine learning problems when multiple learning criteria or tasks need to be addressed. Recent works have developed various _dynamic weighting_ algorithms for MOL, including MGDA and its variants, whose central idea is to find an update direction that _avoids conflicts_ among objectives. Albeit its appealing intuition, empirical studies show that dynamic weighting methods may not always outperform static alternatives. To bridge this gap between theory and practice, we focus on a new variant of stochastic MGDA - the Multi-objective gradient with Double sampling (MoDo) algorithm and study its generalization performance and the interplay with optimization through the lens of algorithm stability. We find that the rationale behind MGDA -- updating along conflict-avoidant direction - may \emph{impede} dynamic weighting algorithms from achieving the optimal ${\cal O}(1/\sqrt{n})$ population risk, where $n$ is the number of training samples. We further highlight the variability of dynamic weights and their impact on the three-way trade-off among optimization, generalization, and conflict avoidance that is unique in MOL.

Many machine learning tasks aim to find models that work well not for a single, but for a group of criteria, often opposing ones. One such example is imbalanced data classification, where, on the one hand, we want to achieve the best possible classification quality for data from the minority class without degrading the classification quality of the majority class. One solution is to propose an aggregate learning criterion and reduce the multi-objective learning task to a single-criteria optimization problem. Unfortunately, such an approach is characterized by ambiguity of interpretation since the value of the aggregated criterion does not indicate the value of the component criteria. Hence, there are more and more proposals for algorithms based on multi-objective optimization (MOO), which can simultaneously optimize multiple criteria. However, such an approach results in a set of multiple non-dominated solutions (Pareto front). The selection of a single solution from the Pareto front is a challenge itself, and much attention is paid to the issue of how to select it considering user preferences, as well as how to compare solutions returned by different MOO algorithms among themselves. Thus, a significant gap has been identified in the classifier evaluation methodology, i.e., how to reliably compare methods returning single solutions with algorithms returning solutions in the form of Pareto fronts. To fill the aforementioned gap, this article proposes a new, reliable way of evaluating algorithms based on multi-objective algorithms with methods that return single solutions while pointing out solutions from a Pareto front tailored to the user's preferences. This work focuses only on algorithm comparison, not their learning. The algorithms selected for this study are illustrative to help understand the proposed approach.

Department of Applied Mathematics Harbin Institute of T echnology, W eihai Weihai, China gaoxiang.zhao@stu.hit.edu.cn Abstract--Real-Time Auction (RT A) Interception aims to filter out invalid or irrelevant traffic to enhance the integrity and reliability of downstream data. However, two key challenges remain: (i) the need for accurate estimation of traffic quality together with sufficiently high confidence in the model's predictions--typically addressed through uncertainty modeling--and (ii) the efficiency bottlenecks that such uncertainty modeling introduces in real-time applications due to repeated inference. T o address these challenges, we propose DAUM, a joint modeling framework that integrates multi-objective learning with uncertainty modeling, yielding both traffic quality predictions and reliable confidence estimates. Building on DAUM, we further apply knowledge distillation to reduce the computational overhead of uncertainty modeling, while largely preserving predictive accuracy and retaining the benefits of uncertainty estimation. Experiments on the JD advertisement dataset demonstrate that DAUM consistently improves predictive performance, with the distilled model delivering a tenfold increase in inference speed. In online advertising, RT A mechanisms play a central role in determining which traffic are exposed to downstream systems. Since not all incoming traffic contributes equally to campaign performance, an effective interception process is needed to filter out unproductive requests while preserving those that align with predefined objectives. Achieving this goal is particularly challenging because it requires not only the accurate prediction of multiple user-behavior metrics but also dependable estimates of prediction confidence under highly dynamic conditions. A natural way to address these requirements is to combine multi-objective optimization with uncertainty modeling.

In multi-objective learning (MOL), several possibly competing prediction tasks must be solved jointly by a single model. Achieving good trade-offs may require a model class $\mathcal{G}$ with larger capacity than what is necessary for solving the individual tasks. This, in turn, increases the statistical cost, as reflected in known MOL bounds that depend on the complexity of $\mathcal{G}$. We show that this cost is unavoidable for some losses, even in an idealized semi-supervised setting, where the learner has access to the Bayes-optimal solutions for the individual tasks as well as the marginal distributions over the covariates. On the other hand, for objectives defined with Bregman losses, we prove that the complexity of $\mathcal{G}$ may come into play only in terms of unlabeled data. Concretely, we establish sample complexity upper bounds, showing precisely when and how unlabeled data can significantly alleviate the need for labeled data. These rates are achieved by a simple, semi-supervised algorithm via pseudo-labeling.

This paper presents our approach to the SemEval-2025 Task~6 (PromiseEval), which focuses on verifying promises in corporate ESG (Environmental, Social, and Governance) reports. We explore three model architectures to address the four subtasks of promise identification, supporting evidence assessment, clarity evaluation, and verification timing. Our first model utilizes ESG-BERT with task-specific classifier heads, while our second model enhances this architecture with linguistic features tailored for each subtask. Our third approach implements a combined subtask model with attention-based sequence pooling, transformer representations augmented with document metadata, and multi-objective learning. Experiments on the English portion of the ML-Promise dataset demonstrate progressive improvement across our models, with our combined subtask approach achieving a leaderboard score of 0.5268, outperforming the provided baseline of 0.5227. Our work highlights the effectiveness of linguistic feature extraction, attention pooling, and multi-objective learning in promise verification tasks, despite challenges posed by class imbalance and limited training data.

We provide a unifying framework for the design and analysis of multi-calibrated predictors. By placing the multi-calibration problem in the general setting of multi-objective learning---where learning guarantees must hold simultaneously over a set of distributions and loss functions---we exploit connections to game dynamics to achieve state-of-the-art guarantees for a diverse set of multi-calibration learning problems. In addition to shedding light on existing multi-calibration guarantees and greatly simplifying their analysis, our approach also yields improved guarantees, such as error tolerances that scale with the square-root of group size versus the constant tolerances guaranteed by prior works, and improving the complexity of k -class multi-calibration by an exponential factor of k versus Gopalan et al.. Beyond multi-calibration, we use these game dynamics to address emerging considerations in the study of group fairness and multi-distribution learning.

We provide a unifying framework for the design and analysis of multi-calibrated predictors. By placing the multi-calibration problem in the general setting of multi-objective learning---where learning guarantees must hold simultaneously over a set of distributions and loss functions---we exploit connections to game dynamics to achieve state-of-the-art guarantees for a diverse set of multi-calibration learning problems. In addition to shedding light on existing multi-calibration guarantees and greatly simplifying their analysis, our approach also yields improved guarantees, such as error tolerances that scale with the square-root of group size versus the constant tolerances guaranteed by prior works, and improving the complexity of k -class multi-calibration by an exponential factor of k versus Gopalan et al.. Beyond multi-calibration, we use these game dynamics to address emerging considerations in the study of group fairness and multi-distribution learning.

Multi-objective learning (MOL) often arises in emerging machine learning problems when multiple learning criteria or tasks need to be addressed. Recent works have developed various _dynamic weighting_ algorithms for MOL, including MGDA and its variants, whose central idea is to find an update direction that _avoids conflicts_ among objectives. Albeit its appealing intuition, empirical studies show that dynamic weighting methods may not always outperform static alternatives. To bridge this gap between theory and practice, we focus on a new variant of stochastic MGDA - the Multi-objective gradient with Double sampling (MoDo) algorithm and study its generalization performance and the interplay with optimization through the lens of algorithm stability. We find that the rationale behind MGDA -- updating along conflict-avoidant direction - may \emph{impede} dynamic weighting algorithms from achieving the optimal {\cal O}(1/\sqrt{n}) population risk, where n is the number of training samples.