Synthetic Data Reveals Generalization Gaps in Correlated Multiple Instance Learning

Multiple instance learning (MIL) is often used in medical imaging to classify high-resolution 2D images by processing patches or classify 3D volumes by processing slices. However, conventional MIL approaches treat instances separately, ignoring contextual relationships such as the appearance of nearby patches or slices that can be essential in real applications. We design a synthetic classification task where accounting for adjacent instance features is crucial for accurate prediction. We demonstrate the limitations of off-the-shelf MIL approaches by quantifying their performance compared to the optimal Bayes estimator for this task, which is available in closed-form. We empirically show that newer correlated MIL methods still struggle to generalize as well as possible when trained from scratch on tens of thousands of instances.

Budgeted Multiple-Expert Deferral

Learning to defer uncertain predictions to costly experts offers a powerful strategy for improving the accuracy and efficiency of machine learning systems. However, standard training procedures for deferral algorithms typically require querying all experts for every training instance, an approach that becomes prohibitively expensive when expert queries incur significant computational or resource costs. This undermines the core goal of deferral: to limit unnecessary expert usage. To overcome this challenge, we introduce the budgeted deferral framework, which aims to train effective deferral algorithms while minimizing expert query costs during training. We propose new algorithms for both two-stage and single-stage multiple-expert deferral settings that selectively query only a subset of experts per training example. While inspired by active learning, our setting is fundamentally different: labels are already known, and the core challenge is to decide which experts to query in order to balance cost and predictive performance. We establish theoretical guarantees for both of our algorithms, including generalization bounds and label complexity analyses. Empirical results across several domains show that our algorithms substantially reduce training costs without sacrificing prediction accuracy, demonstrating the practical value of our budget-aware deferral algorithms.

Empirical Bayesian Multi-Bandit Learning

Multi-task learning in contextual bandits has attracted significant research interest due to its potential to enhance decision-making across multiple related tasks by leveraging shared structures and task-specific heterogeneity. In this article, we propose a novel hierarchical Bayesian framework for learning in various bandit instances. This framework captures both the heterogeneity and the correlations among different bandit instances through a hierarchical Bayesian model, enabling effective information sharing while accommodating instance-specific variations. Unlike previous methods that overlook the learning of the covariance structure across bandits, we introduce an empirical Bayesian approach to estimate the covariance matrix of the prior distribution.This enhances both the practicality and flexibility of learning across multi-bandits. Building on this approach, we develop two efficient algorithms: ebmTS (Empirical Bayesian Multi-Bandit Thompson Sampling) and ebmUCB (Empirical Bayesian Multi-Bandit Upper Confidence Bound), both of which incorporate the estimated prior into the decision-making process. We provide the frequentist regret upper bounds for the proposed algorithms, thereby filling a research gap in the field of multi-bandit problems. Extensive experiments on both synthetic and real-world datasets demonstrate the superior performance of our algorithms, particularly in complex environments. Our methods achieve lower cumulative regret compared to existing techniques, highlighting their effectiveness in balancing exploration and exploitation across multi-bandits.

Physics-Guided Conditional Diffusion Networks for Microwave Image Reconstruction

A conditional latent-diffusion based framework for solving the electromagnetic inverse scattering problem associated with microwave imaging is introduced. This generative machine-learning model explicitly mirrors the non-uniqueness of the ill-posed inverse problem. Unlike existing inverse solvers utilizing deterministic machine learning techniques that produce a single reconstruction, the proposed latent-diffusion model generates multiple plausible permittivity maps conditioned on measured scattered-field data, thereby generating several potential instances in the range-space of the non-unique inverse mapping. A forward electromagnetic solver is integrated into the reconstruction pipeline as a physics-based evaluation mechanism. The space of candidate reconstructions form a distribution of possibilities consistent with the conditioning data and the member of this space yielding the lowest scattered-field data discrepancy between the predicted and measured scattered fields is reported as the final solution. Synthetic and experimental labeled datasets are used for training and evaluation of the model. An innovative labeled synthetic dataset is created that exemplifies a varied set of scattering features. Training of the model using this new dataset produces high quality permittivity reconstructions achieving improved generalization with excellent fidelity to shape recognition. The results highlight the potential of hybrid generative physics frameworks as a promising direction for robust, data-driven microwave imaging.

MetaCaDI: A Meta-Learning Framework for Scalable Causal Discovery with Unknown Interventions

Uncovering the underlying causal mechanisms of complex real-world systems remains a significant challenge, as these systems often entail high data collection costs and involve unknown interventions. We introduce MetaCaDI, the first framework to cast the joint discovery of a causal graph and unknown interventions as a meta-learning problem. MetaCaDI is a Bayesian framework that learns a shared causal graph structure across multiple experiments and is optimized to rapidly adapt to new, few-shot intervention target prediction tasks. A key innovation is our model's analytical adaptation, which uses a closed-form solution to bypass expensive and potentially unstable gradient-based bilevel optimization. Extensive experiments on synthetic and complex gene expression data demonstrate that MetaCaDI significantly outperforms state-of-the-art methods. It excels at both causal graph recovery and identifying intervention targets from as few as 10 data instances, proving its robustness in data-scarce scenarios.

Beyond Augmentation: Leveraging Inter-Instance Relation in Self-Supervised Representation Learning

This paper introduces a novel approach that integrates graph theory into self-supervised representation learning. Traditional methods focus on intra-instance variations generated by applying augmentations. However, they often overlook important inter-instance relationships. While our method retains the intra-instance property, it further captures inter-instance relationships by constructing k-nearest neighbor (KNN) graphs for both teacher and student streams during pretraining. In these graphs, nodes represent samples along with their latent representations. Edges encode the similarity between instances. Following pretraining, a representation refinement phase is performed. In this phase, Graph Neural Networks (GNNs) propagate messages not only among immediate neighbors but also across multiple hops, thereby enabling broader contextual integration. Experimental results on CIFAR-10, ImageNet-100, and ImageNet-1K demonstrate accuracy improvements of 7.3%, 3.2%, and 1.0%, respectively, over state-of-the-art methods. These results highlight the effectiveness of the proposed graph based mechanism. The code is publicly available at https://github.com/alijavidani/SSL-GraphNNCLR.

Cross-Paradigm Graph Backdoor Attacks with Promptable Subgraph Triggers

Graph Neural Networks(GNNs) are vulnerable to backdoor attacks, where adversaries implant malicious triggers to manipulate model predictions. Existing trigger generators are often simplistic in structure and overly reliant on specific features, confining them to a single graph learning paradigm, such as graph supervised learning, graph contrastive learning, or graph prompt learning. This specialized design, which aligns the trigger with one learning objective, results in poor transferability when applied to other learning paradigms. For instance, triggers generated for the graph supervised learning paradigm perform poorly when tested within graph contrastive learning or graph prompt learning environments. Furthermore, these simple generators often fail to utilize complex structural information or node diversity within the graph data. These constraints limit the attack success rates of such methods in general testing scenarios. Therefore, to address these limitations, we propose Cross-Paradigm Graph Backdoor Attacks with Promptable Subgraph Triggers(CP-GBA), a new transferable graph backdoor attack that employs graph prompt learning(GPL) to train a set of universal subgraph triggers. First, we distill a compact yet expressive trigger set from target graphs, which is structured as a queryable repository, by jointly enforcing class-awareness, feature richness, and structural fidelity. Second, we conduct the first exploration of the theoretical transferability of GPL to train these triggers under prompt-based objectives, enabling effective generalization to diverse and unseen test-time paradigms. Extensive experiments across multiple real-world datasets and defense scenarios show that CP-GBA achieves state-of-the-art attack success rates.

Generalizable Reasoning through Compositional Energy Minimization

Generalization is a key challenge in machine learning, specifically in reasoning tasks, where models are expected to solve problems more complex than those encountered during training. Existing approaches typically train reasoning models in an end-to-end fashion, directly mapping input instances to solutions. While this allows models to learn useful heuristics from data, it often results in limited generalization beyond the training distribution. In this work, we propose a novel approach to reasoning generalization by learning energy landscapes over the solution spaces of smaller, more tractable subproblems. At test time, we construct a global energy landscape for a given problem by combining the energy functions of multiple subproblems. This compositional approach enables the incorporation of additional constraints during inference, allowing the construction of energy landscapes for problems of increasing difficulty. To improve the sample quality from this newly constructed energy landscape, we introduce Parallel Energy Minimization (PEM). We evaluate our approach on a wide set of reasoning problems. Our method outperforms existing state-of-the-art methods, demonstrating its ability to generalize to larger and more complex problems. Project website can be found at: https://alexoarga.github.io/compositional_reasoning/

Unified Reinforcement and Imitation Learning for Vision-Language Models

Vision-Language Models (VLMs) have achieved remarkable progress, yet their large scale often renders them impractical for resource-constrained environments. This paper introduces Unified Reinforcement and Imitation Learning (RIL), a novel and efficient training algorithm designed to create powerful, lightweight VLMs. RIL distinctively combines the strengths of reinforcement learning with adversarial imitation learning. This enables smaller student VLMs not only to mimic the sophisticated text generation of large teacher models but also to systematically improve their generative capabilities through reinforcement signals. Key to our imitation framework is an LLM-based discriminator that adeptly distinguishes between student and teacher outputs, complemented by guidance from multiple large teacher VLMs to ensure diverse learning. This unified learning strategy, leveraging both reinforcement and imitation, empowers student models to achieve significant performance gains, making them competitive with leading closed-source VLMs. Extensive experiments on diverse vision-language benchmarks demonstrate that RIL significantly narrows the performance gap with state-of-the-art open- and closed-source VLMs and, in several instances, surpasses them.

RLBoost: Harvesting Preemptible Resources for Cost-Efficient Reinforcement Learning on LLMs

Reinforcement learning (RL) has become essential for unlocking advanced reasoning capabilities in large language models (LLMs). RL workflows involve interleaving rollout and training stages with fundamentally different resource requirements. Rollout typically dominates overall execution time, yet scales efficiently through multiple independent instances. In contrast, training requires tightly-coupled GPUs with full-mesh communication. Existing RL frameworks fall into two categories: co-located and disaggregated architectures. Co-located ones fail to address this resource tension by forcing both stages to share the same GPUs. Disaggregated architectures, without modifications of well-established RL algorithms, suffer from resource under-utilization. Meanwhile, preemptible GPU resources, i.e., spot instances on public clouds and spare capacity in production clusters, present significant cost-saving opportunities for accelerating RL workflows, if efficiently harvested for rollout. In this paper, we present RLBoost, a systematic solution for cost-efficient RL training that harvests preemptible GPU resources. Our key insight is that rollout's stateless and embarrassingly parallel nature aligns perfectly with preemptible and often fragmented resources. To efficiently utilize these resources despite frequent and unpredictable availability changes, RLBoost adopts a hybrid architecture with three key techniques: (1) adaptive rollout offload to dynamically adjust workloads on the reserved (on-demand) cluster, (2) pull-based weight transfer that quickly provisions newly available instances, and (3) token-level response collection and migration for efficient preemption handling and continuous load balancing. Extensive experiments show RLBoost increases training throughput by 1.51x-1.97x while improving cost efficiency by 28%-49% compared to using only on-demand GPU resources.