论文检索

Optimization · Discrete and Combinatorial Optimization

Morteza Monemizadeh, Kiarash Banihashem, Peyman Jabbarzade, MohammadTaghi Hajiaghayi, Samira Goudarzi

Non-monotone submodular maximization is a fundamental problem in machine learning and combinatorial optimization, with a range of applications including text and video summarization, recommendation systems, feature selection, Max Cut problems in graphs, and viral marketing strategies. In this work, we study non-monotone submodular maximization under a cardinality constraint $k$ in the fully dynamic setting, and obtain results that improve upon the previously established approximation guarantees of $(0.125 - \epsilon)$ using $\tilde{O}(\epsilon^{-1}k^2)$ oracle queries per update (NeurIPS'20) and $0.171$ using $\tilde{O}(\epsilon^{-3}k^4)$ oracle queries per update (NeurIPS'25). We present a dynamic algorithm that achieves a $0.262$-approximation with worst-case expected update time $O(\epsilon^{-3}\log(k)\log(\epsilon^{-1}k) + \epsilon^{-2}k^2\log(k))$, where $0 < \epsilon \leq 1$ is the error parameter. We also obtain another dynamic algorithm with update time bounded by $\text{poly}(\epsilon^{-1}, k)$ that achieves a $0.277$-approximation guarantee.

Optimization · Convex

Nicholas Di, Eric Chi, Samy Wu Fung

Operator splitting algorithms are a cornerstone of modern first-order optimization, decomposing complex problems into simpler subproblems solved via proximal operators. However, most functions lack closed-form proximal operators, which has long restricted these methods to a narrow set of problems. Hamilton-Jacobi-based proximal operator (HJ-Prox) is a recent derivative-free Monte Carlo technique based on Hamilton-Jacobi PDE theory, that approximates proximal operators numerically. In this work, we introduce a unified framework for operator splitting via HJ-Prox, which allows for deployment of operator splitting even when functions are not proximable. We prove that replacing exact proximal steps with HJ-Prox in algorithms such as proximal point, proximal gradient descent, Douglas–Rachford splitting, Davis–Yin splitting, and primal–dual hybrid gradient preserves convergence guarantees under mild assumptions. Numerical experiments demonstrate HJ-Prox is competitive and effective on a wide variety of statistical learning tasks.

General Machine Learning · Unsupervised and Semi-supervised Learning

Ran Eisenberg, Ofir Lindenbaum

Many learning problems require uncovering a hidden ordering that reveals structure in unordered data, such as monotonicity in sorting or spatial continuity in jigsaw reconstruction. In these settings, permutations can be learned as latent operators by optimizing objectives defined directly on the reordered output, often without access to ground-truth orderings. Differentiable relaxations such as Gumbel–Sinkhorn make this approach practical by approximating permutation matrices with doubly stochastic matrices. However, learning from structure without supervision induces a non-uniform uncertainty: some assignments become confident early, while others remain ambiguous. Existing methods control this process using a single global temperature, forcing all assignments to sharpen or diffuse simultaneously and leading to instability at scale. We introduce an entropy-adaptive formulation of Gumbel–Sinkhorn that locally modulates temperature based on assignment uncertainty. This allows confident assignments to discretize early while preserving exploration where uncertainty remains. Across sorting and jigsaw reconstruction tasks and in routing-style settings, adaptive entropy control improves training stability and final permutation quality relative to fixed-temperature baselines, particularly as problem size and assignment ambiguity increase.

Deep Learning · Foundation Models

David Schiff, Ofir Lindenbaum, Yonathan Efroni

Recent advancements in machine learning have largely been driven by foundation models (FMs) trained on large, diverse datasets, enabling them to generalize effectively to new, related tasks. However, extending this paradigm to reinforcement learning (RL), where an agent interacts with an environment to select actions, remains a significant challenge. Most existing approaches train FMs directly on sets of control tasks, but developing diverse RL environments and scaling training across them can be costly and complex. In this study, we explore a simpler alternative approach based on a classical reduction from RL to regression. We demonstrate that a foundation model pre-trained for regression tasks, when used as an in-context regression (ICR) model, can be directly applied to RL problems. Building on this insight, we introduce a gradient-free method, ICR-RL, that requires no additional training and leverages an ICR foundation model to tackle RL tasks. We evaluate our approach by applying the ICR model with the recently proposed TabPFN, which is trained on a wide range of regression tasks. Experiments conducted on the Gymnasium classic-control benchmark indicate that ICR-RL matches or outperforms state-of-the-art methods, including DQN and PPO. These results show that ICR foundation models can effectively solve RL tasks without fine-tuning, demonstrating their potential as a foundation for RL-oriented models

Social Aspects · Safety

Yingdan Shi, Sijia Liu, Kaize Ding, Ren Wang

Machine unlearning seeks to remove the influence of specified data from a trained model. While the unlearning accuracy provides a widely used metric for assessing unlearning performance, it falls short in assessing the reliability of forgetting. In this paper, we find that the forgetting data points misclassified by unlearning accuracy still have their ground truth labels included in the conformal prediction set from the uncertainty quantification perspective, leading to a phenomenon we term fake forgetting. To address this issue, we propose a novel metric CR, inspired by conformal prediction, that offers a more reliable assessment of forgetting quality. Building on these insights, we further propose an unlearning framework CPU that incorporates conformal prediction into the Carlini & Wagner adversarial attack loss, enabling the ground truth label to be effectively removed from the conformal prediction set. Through extensive experiments on image classification tasks, we demonstrate both the effectiveness of our proposed metric and the superior forgetting quality achieved by our framework. Code is available at https://anonymous.4open.science/r/MUCP-60E4.

General Machine Learning · Everything Else

Kejing Lu, Zhenpeng Pan, Jianbin Qin, Yoshiharu Ishikawa, Chuan Xiao

Approximate Nearest Neighbor Search (ANNS) is fundamental to modern AI applications. Most existing solutions optimize query efficiency but fail to align with the practical requirements of modern workloads. In this paper, we outline six critical demands of modern AI applications: high query efficiency, fast indexing, low memory footprint, scalability to high dimensionality, robustness across varying retrieval sizes, and support for online insertions. To satisfy all these demands, we introduce Projection-Augmented Graph (PAG), a new ANNS framework that integrates projection techniques into a graph index. PAG reduces unnecessary exact distance computations through asymmetric comparisons between exact and approximate distances guided by projection-based statistical tests. Three key components are designed and unified to the graph index to optimize indexing and searching. Experiments on six modern datasets demonstrate that PAG consistently achieves superior query per second (QPS)-recall performance---up to 5×faster than HNSW---while offering fast indexing speed and small memory footprint. PAG remains robust as dimensionality and retrieval size increase and naturally supports online insertions. Our source code is available at: https://anonymous.4open.science/r/PAG-A73D/ .

General Machine Learning · Everything Else

Hang Su, Yijun Mo, Zhiyu Zhang, Yankai Jiang, Bo Liu, Yichen Li, Imran Razzak

Federated Continual Learning (FCL) enables the continuous acquisition of knowledge from streaming tasks, but inherently struggles with the temporal dynamics of client data distributions. These dynamics naturally induce asynchronous concept drift, where distribution shifts occur independently across clients at unsynchronized times and with varying magnitudes. Such asynchrony generates conflicting updates that destabilize global convergence and exacerbate catastrophic forgetting. However, existing FCL research focuses on static or incremental settings, typically treating all incoming updates uniformly, which obscures concept drift under divergent distributions and fails to adapt to the evolution of learned concepts. To address these limitations, we propose RC-FCL, a retrospective calibration framework for FCL that can effectively distinguish asynchronous concept drift and adjust the learning strategy adaptively. Specifically, RC-FCL leverages a conditional generative model to synthesize class-conditional reference distributions of previously learned concepts for local drift detection. It calibrates local adaptation using a weighting mechanism driven by the local discriminator to prioritize informative samples, and executes a global aggregation strategy based on drift magnitude. Our experimental results demonstrate that RC-FCL achieves competitive performance against state-of-the-art methods.

General Machine Learning · Everything Else

Chunxu Zhang, Weipeng Zhang, Guodong Long, Zhiheng Xue, Bo Yang

Most federated recommender systems represent each user with a single embedding learned from local interaction data, implicitly assuming that user preferences are fixed and precisely identifiable. In federated settings, however, each client observes only a limited and fragmentary view of user behavior, rendering such point estimates inherently brittle. To address this mismatch, we model user preferences as distributions rather than points, allowing multiple compatible preference representations to coexist. Rather than collapsing evidence into a single embedding, our approach preserves uncertainty and diversity in user representations, providing a richer basis for preference modeling. We instantiate this idea with a diffusion-based generative framework that produces diverse user embeddings and derives recommendation scores by aggregating predictions across them. This distributional formulation yields more stable ranking behavior and improved robustness under ambiguous feedback. Extensive experiments on federated recommendation benchmark datasets demonstrate consistent and significant improvements over baselines. Our code is available.

General Machine Learning · Everything Else

Xiuying Wang, Yichen Li, Hang Su, Gaozhuo Liu, Shiwei Li, Chuang Zhao, Jiangming Shi, Imran Razzak

Federated Incremental Learning (FIL) aims to learn streaming tasks across distributed clients without catastrophic forgetting while preserving privacy. Most existing methods focus on sample-based replay techniques, which mitigate forgetting by replaying historical data samples. However, such methods often face challenges related to data privacy risks and significant resource overheads, making them impractical and difficult to deploy on edge devices with limited resources. To address this challenge, we propose a novel and \underline{Li}ghtweight \underline{F}ederated \underline{I}ncremental \underline{L}earning framework called \textbf{Li-FIL} that leverages dense features synthesized by a secure generator on the server to enable efficient feature-based replay on decoupled local models. More specifically, each client extracts high-confidence features from the new task, applies mixup to obtain a dense feature representation, and then privatizes these features before uploading them to the server, which reduces both storage and communication overhead. A generator is deployed on the server to learn the distributions of different clients and generate global features for replay. Moreover, to enable clients to better learn from these dense features, we decouple the local model into two components: a feature extractor and a classifier. This design allows feature replay and the alignment between new and previous features to be conducted separately and more effectively. Extensive experiments demonstrate that Li-FIL outperforms other state-of-the-art methods by up to 10.14 in terms of accuracy on both old and new tasks with superior resource efficiency.

General Machine Learning · Sequential, Network, and Time Series Modeling

Dong Huang, Chenyang Tian, Pengkun Yang

This paper studies the problem of recovering a hidden vertex correspondence between two correlated graphs when both edge weights and node features are observed. While most existing work on graph alignment relies primarily on edge information, many real-world applications provide informative node features in addition to graph topology. To capture this setting, we introduce the featured correlated Gaussian Wigner model, where two graphs are coupled through an unknown vertex permutation, and the node features are correlated under the same permutation. We characterize the optimal information-theoretic thresholds for exact recovery and partial recovery of the latent mapping. On the algorithmic side, we propose QPAlign, an efficient method based on a quadratic programming relaxation, and demonstrate its strong empirical performance on both synthetic and real datasets. Moreover, we also derive theoretical guarantees for the proposed procedure, supporting its reliability and providing convergence guarantees.

General Machine Learning · Transfer, Multitask and Meta-learning

Ziang Song, Zhou Zhidan, Zijun Zhang

Domain generalization aims to improve model performance on unseen, out-of-distribution (OOD) domains, yet existing methods often overlook the crucial aspect of uncertainty quantification in their predictions. While ensemble learning combined with knowledge distillation offers a promising avenue, naively combining these techniques is non-trivial and remains largely unexplored in the context of domain generalization. In this work, we systematically investigate different ensemble and distillation strategies for domain generalization tasks and design a tailored data allocation scheme. This approach trains teacher models on distinct subsets of domains and performs distillation on complementary (unseen) subsets, thereby fostering model diversity and training efficiency. Moreover, our theoretical analysis demonstrates that distilling from teachers on unseen domains effectively filters out domain-specific spurious correlations. To address the accuracy degradation often observed with standard uncertainty distillation, we further develop a novel technique that decouples uncertainty distillation from the standard distillation process, enabling accurate uncertainty estimation without compromising model accuracy. Our proposed method, *Domain-aware Ensemble Distillation* (DomED), is extensively evaluated against state-of-the-art domain generalization and ensemble distillation techniques across multiple benchmarks, achieving competitive accuracies and substantially improved uncertainty estimates.

General Machine Learning · Transfer, Multitask and Meta-learning

Hongyou Zhou, Zihan Ye, Ling Shao, Marc Toussaint

Despite strong zero-shot performance, SAM is unreliable under domain shift due to Mask-level Confidence Confusion (MCC), where a single IoU-based mask score fails to reflect pixel-wise reliability near boundaries. Motivated by the contrast between texture-biased shortcuts in neural networks and shape-centric processing in human vision, we model out-of-domain variation as appearance shifts and non-rigid deformations that jointly stress calibration. We propose Segment Anything with Robust Uncertainty-Accuracy Correlation (RUAC) for robust pixel-wise uncertainty estimation under appearance and deformation shifts. RUAC adds a lightweight uncertainty head, trains it with a collaborative style-deformation attack that jointly perturbs texture and geometry, and applies Uncertainty-Error Alignment to ensure uncertainty consistently highlights erroneous pixels even under adversarial perturbations. Across 23 zero-shot domains, RUAC improves segmentation quality and yields more faithful uncertainty with stronger uncertainty-accuracy correlation.

Applications · Chemistry, Physics, and Earth Sciences

Ziyang Yu, Yi He, Wenbing Huang, Wen Yan, Yang Liu

Estimating free energy differences quantifies thermodynamic preferences in molecular interactions, which is central to chemistry and drug discovery. Despite fruitful progress, existing methods still face key limitations: classical computational approaches remain prohibitively expensive due to their reliance on extensive molecular dynamics simulations, while deep learning-based methods are constrained by either less-expressive generative models or input dimensions tied to a specific system, resulting in negligible generalization. To address these challenges, we propose CARD, a generative framework that employs a novel radix-based decomposition to bijectively convert 3D coordinates into mixed discrete-continuous sequences, enabling coarse-to-fine autoregressive modeling with enhanced expressiveness. Notably, the model corresponds to a distribution with zero free energy, serving as a proposal for absolute free energy computation of arbitrary systems without relying on alchemical pathways. Experiments across diverse tasks demonstrate that CARD matches the accuracy of classical computational methods on unseen systems with diverse topologies, while achieving an approximately 40-fold speedup in inference.

General Machine Learning · Transfer, Multitask and Meta-learning

Md Abdullah Al Forhad, Yuansheng Zhu Zhu., Abhinab Acharya, Xumin Liu, Qi Yu, Weishi Shi

The Mixture of Experts (MoE) framework is widely used in continual learning to mitigate catastrophic forgetting. MoEs typically combine a small inter-task shared parameter space with largely independent expert parameters. However, as the number of tasks increases, the shared space becomes a bottleneck, reintroducing forgetting, while fully independent experts require explicit task ID predictors (e.g., routers), adding complexity. In this work, we eliminate the inter-task shared parameter space and the need for a task ID predictor by enabling expert communication and allowing knowledge to be shared dynamically, akin to human collaboration. We bridge the inter-expert knowledge sharing by leveraging the open-set learning capabilities of a multimodal foundation model (e.g., CLIP), thereby providing “expert priors” that bolster each expert’s task-specific representations. Guided by these priors, experts learn calibrated inter-task posteriors. Additionally, Multivariate Gaussians over the learned posteriors promote complementary specialization among experts. We propose new evaluation benchmarks that simulate realistic continual learning scenarios, and our prior-conditioned strategy consistently outperforms existing methods across diverse settings without relying on reference datasets or replay memory.

Applications · Neuroscience, Cognitive Science

Tianqiu Zhang, Muyang Lyu, Xiao Liu, Si Wu

Humans abstract experiences into structured representations to facilitate pattern inference and knowledge transfer. While the hippocampal-entorhinal (HPC-MEC) circuit is known to represent both spatial and conceptual spaces, the mechanisms for concurrently extracting abstract structures from continuous, high-dimensional dynamics remain poorly understood. We propose a brain-inspired hierarchical model that simultaneously infers latent transitions and constructs a predictive visual world model. Our architecture employs an inverse model for structural extraction alongside an HPC-MEC coupling model that dissociates relational structures (MEC) from integrated episodic scenes (HPC). Using rotation dynamics as a benchmark, we demonstrate the model's capacity for structural abstraction. By leveraging velocity-driven path integration, the framework enables robust prediction and structural reuse across diverse contexts, thereby achieving structural generalization. This work provides a novel computational framework for understanding how brain-inspired, self-supervised learning of world models facilitates the acquisition of reusable abstract knowledge.

Deep Learning · Robustness

Vishesh Kumar, Akshay Agarwal

Even after decades of advances in neural network training, the inherent robustness challenge remains open. While the sensitivity to adversarial perturbations is understandable given their intentional learning, the most surprising fact is the vulnerability to natural corruptions. Moreover, the reason for this inherent vulnerability remains unknown, and it is not limited to traditional CNNs but also applies to current models, including transformers and large foundation models. For the first time, through this work, we observe that natural corruptions often collapse the network's internal feature space into a high-entropy state, causing predictions to rely on a small subset of fragile features. Inspired by this, we propose a simple yet effective entropy-guided fine-tuning framework, Dem-HEC, that strengthens corruption robustness while maintaining clean accuracy. Our method generates high-entropy samples within a bounded perturbation region. It applies it to both clean and high-entropy samples, combined with knowledge distillation from a teacher snapshot, ensuring stable predictions. The proposed Dem-HEC is effective across datasets ranging from small to large-resolution, from pure CNNs to transformers, and to large foundation models, including DinoV3. The proposed approach outperforms the state-of-the-art (SOTA) models not only in improving robustness but also in retaining or boosting clean accuracy.

General Machine Learning · Transfer, Multitask and Meta-learning

Ali Vahedifar, Abhisek Ray, Qi Zhang

Continual learning enables neural networks to learn tasks sequentially without forgetting previously acquired knowledge. However, catastrophic forgetting, where performance on earlier tasks degrades sharply when learning new ones, remains a fundamental challenge. We address this problem with Shapley Neuron Valuation (SNV), a principled framework grounded in cooperative game theory that quantifies Neuron importance in continual learning. By selectively freezing important Neurons while keeping others plastic, SNV enables memory-free continual learning without architectural expansion. Extensive experiments show that SNV delivers substantial gains over memory-free baselines, achieving +19.50% accuracy on CIFAR-100 and +17.20% on TinyImageNet in the Class-IL setting. In Task-IL scenarios, SNV consistently surpasses existing memory-free approaches by large margins, reaching up to 9.08% higher accuracy on CIFAR-100 compared to the second-best memory-free method, while remaining competitive in comparison with memory-based methods.

General Machine Learning · Transfer, Multitask and Meta-learning

Zhiyuan Yu, Enneng Yang, Hao Jiang, Guojie Zhu, Feihong He, Peng Wang, Li Shen

Upcycling, a strategy that initializes Mixture-of-Experts (MoE) by replicating pre-trained feed-forward or MoE networks to expand model capacity, has become a popular method in continual learning due to its effectiveness in mitigating catastrophic forgetting. However, existing paradigms rely on indiscriminate expansion prioritize performance at the cost of extreme inefficiency, introducing parameter redundancy without exploiting the structural heterogeneity essential for counteracting forgetting with architectural economy. To address this, we investigate the determinants of forgetting in training dynamics using Centered Kernel Alignment (CKA) and loss landscape flatness to analyze the behavior of pre- and post-expansion MoE layers, uncovering instability in deep-layer representations and heterogeneous expert sensitivity to new tasks, thereby demonstrating the potential of selective upcycling to eliminate redundancy. Consequently, we propose a dynamic bilevel optimization framework to guide adaptive upcycling, featuring an outer loop employing a Gumbel-Softmax differentiable mask to perform Neural Architecture Search (NAS) for adaptive growth, while an inner loop optimizes weight updates via task objectives and CKA-regularized replay. Experiments on TRACE benchmark demonstrate that our proposed method achieves better average accuracy with 80\% forgetting reduction, while effectively eliminating 60\% of redundant parameter expansion that standard upcycling would introduce.

General Machine Learning · Transfer, Multitask and Meta-learning

Selim Furkan Tekin, Gaowen Liu, Ramana Kompella, Ling Liu

The advancement of LLMs and their accessibility have triggered renewed interest in multi-agent reinforcement learning as robust and adaptive frameworks for dynamically changing environments. This paper introduces RL-Focal, a two-stage RL agent framework that routes and ensembles LLMs. First, we develop the Decider RL-agent, which learns to dynamically select an ensemble of small size ($m_i$) among $N$ LLMs ($m_i \ll N$) for incoming queries from a user-defined downstream task $i$, by maximizing both error-diversity and reasoning-performance of the selected ensemble through iterative updates of task-adaptive rewards and policy. Second, to enable effective fusion of dynamically selected LLMs, we develop the stage-2 Fusion RL-agent, which learns to resolve reasoning conflicts from different LLMs and dynamically adapt to different ensemble teams composed by the Decider Agent for different downstream tasks. {\em Third}, we introduce the focal diversity metric to better model the error correlations among multiple LLMs further improving the generalization performance of the Decider Agent, which actively prunes the ensemble combinations. By focal diversity, we enhance performance across tasks by effectively promoting reward-aware and policy-adaptive ensemble selection and inference fusion. Extensive evaluations on five benchmarks show that RL-Focal achieves the performance improvement of 8.48\% with an ensemble of small size compared to the best individual LLM in a pool and offers stronger robustness. Code is available at \url{https://anonymous.4open.science/r/rl-focal-8DCF/}

Deep Learning · Other Representation Learning

Tianqiu Zhang, Muyang Lyu, Yufan Zhang, Fang Fang, Si Wu

Latent Action Models (LAMs) enable the learning of world models from unlabeled video by inferring abstract actions between consecutive frames. However, LAMs face a fundamental trade-off between action abstraction and generation fidelity. Existing methods typically circumvent this issue by using two-stage training with pre-trained world models or by limiting predictions to optical flow. In this paper, we introduce *DiLA*, a novel **Di**sentangled **L**atent **A**ction world model that aims to resolve this trade-off via content-structure disentanglement. Our key insight is that disentanglement and latent action learning are co-evolving: the predictive bottleneck inherent in latent action learning serves as a driving force for disentanglement, compelling the model to distill spatial layouts into the structure pathway while offloading visual details to a separate content pathway for generation. This synergy yields a continuous, semantically structured latent action space without compromising generative quality. *DiLA* achieves superior results in video generation quality, action transfer, visual planning, and manifold interpretability. These findings establish *DiLA* as a unified framework that simultaneously achieves high-level action abstraction and high-fidelity generation, advancing the frontier of self-supervised world model learning.