General ML · generalization

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.

It is increasingly common in machine learning to use learned models to label data and then employ such data to train more capable models. The phenomenon of weak-to-strong generalization exemplifies the advantage of this two-stage procedure: a strong student is trained on imperfect labels obtained from a weak teacher, and yet the strong student outperforms the weak teacher. In this paper, we show that the potential improvement is substantial, in the sense that it affects the scaling law followed by the test error. Specifically, we consider students and teachers trained via random features ridge regression (RFRR). Our main technical contribution is to derive a deterministic equivalent for the excess test error of the student trained on labels obtained via the teacher. Via this deterministic equivalent, we then identify regimes in which the scaling law of the student improves upon that of the teacher, unveiling that the improvement can be achieved both in bias-dominated and variance-dominated settings. Strikingly, the student may attain the minimax optimal rate regardless of the scaling law of the teacher---in fact, when the test error of the teacher does not even decay with the sample size.

Multi-task neural routing solvers have emerged as a promising paradigm for their ability to solve multiple vehicle routing problems (VRPs) using a single model. However, existing neural solvers typically rely on predefined problem constraints or require per-problem fine-tuning, which substantially limits their zero-shot generalization ability to unseen VRP variants. To address this critical bottleneck, we propose URS, a unified neural routing solver that achieves zero-shot generalization across a wide range of unseen VRPs with a single model. We propose a unified data representation (UDR) that replaces problem enumeration with data unification, thereby broadening the problem coverage and reducing reliance on domain expertise. In addition, we introduce a mixed bias module (MBM) during encoding to improve node embeddings, which efficiently captures multiple priors inherent to various problems. On top of the UDR, we develop a problem-conditioned parameter generator to further improve zero-shot generalization. Extensive experiments show that URS consistently produces high-quality solutions for 110 VRP variants (including 99 unseen variants) while demonstrating impressive scalability to large-scale instances with up to 7000 nodes. To the best of our knowledge, URS is the first neural solver to handle over 100 VRP variants with a single model. Our code is available at https://github.com/CIAM-Group/URS.

Positive-Unlabeled (PU) learning is a weakly-supervised paradigm that trains a binary classifier from labeled positive and unlabeled instances. In PU risk estimation, the empirical risk consists of an unlabeled term and a positive term. In this paper, we observe that when labeled positives are scarce, the risk deviation is dominated by the generalization bound of the positive term, which is composed of a complexity term governed by Rademacher complexity and a concentration term governed by the uniform range bound, leading to estimator instability. Based on this observation, we theoretically derive the sufficient sample threshold, defined as the smallest number of labeled positives required to achieve a target excess risk with high probability, and reveal its explicit dependence on both components. Inspired by this insight, we propose ScalePU, which incorporates variance regularization to induce a restricted sub-hypothesis space with reduced Rademacher complexity, and geometric regularization to encourage compact clustering of positive samples with a tighter effective range. Theoretical analysis demonstrates that both mechanisms effectively lower the threshold through improvements to different components of the bound. Experiments on eight benchmark datasets validate the effectiveness of ScalePU, with significant improvements under extreme label scarcity.

Weak-to-strong generalization (W2SG) is the phenomenon in which a powerful student model, trained on labels produced by a weaker teacher, ultimately outperforms the teacher on the target task. In this work, we theoretically investigate how W2SG can arise via a generalized bias–variance decomposition under Bregman divergence. We show that the expected population risk gap between the student and the teacher is characterized by the expected misfit between the two models. Unlike earlier misfit-based analyses, our theory removes several restrictive assumptions, e.g., it does not require the student hypothesis class to be convex. Our results indicate that W2SG is more likely when the student effectively approximates the teacher's posterior mean. Specializing to squared loss, we provide a sufficient condition (illustrated through a concrete example) under which the student converges to its posterior mean teacher; in particular, increasing the student model size can ensure this convergence. For cross-entropy loss, our analysis further suggests that lowering the entropy of the student's predictive distribution can promote W2SG. We also find that the reverse cross-entropy, unlike the standard forward cross-entropy, is less sensitive to the teacher's predictive uncertainty. Finally, we verify these theoretical insights empirically and demonstrate that incorporating reverse cross-entropy consistently improves student performance.

Programmatic policies are often reported to generalize better than neural policies in reinforcement learning (RL) benchmarks. We revisit some of these claims and show that much of the observed gap arises from uncontrolled experimental factors rather than intrinsic representational reasons. Re-evaluating three core benchmarks used in influential papers---TORCS, Karel, and Parking---we find that neural policies, when trained with a few modifications, such as sparse observations and cautious intrinsic reward functions, can match or exceed the out-of-distribution (OOD) generalization of programmatic policies. We argue that a representation enables OOD generalization if (i) the policy space it induces includes a generalizing policy and (ii) the search algorithm can find it. The neural and programmatic policies in prior work are comparable in OOD generalization because the domain-specific languages used induce policy spaces similar to those of neural networks, and our modifications help the gradient search find generalizing solutions. By disentangling representational factors from experimental confounds, we advance our understanding of what makes a representation succeed or fail at OOD generalization.

Weak-to-strong generalization provides a promising paradigm for scaling large language models (LLMs) by training stronger models on samples from aligned weaker ones, without requiring human feedback or explicit reward modeling. However, its robustness and generalization are hindered by the noise and biases in weak-model outputs, which limit its applicability in practice. To address this challenge, we leverage implicit rewards, which approximate explicit rewards through log-likelihood ratios, and reveal their structural equivalence with Contrastive Decoding (CD), a decoding strategy shown to reduce noise in LLM generation. Building on this connection, we propose \textbf{Contrastive Weak-to-Strong Generalization (ConG)}, a framework that employs contrastive decoding between pre- and post-alignment weak models to generate higher-quality samples. This approach enables more reliable capability transfer, denoising, and improved robustness, substantially mitigating the limitations of traditional weak-to-strong methods. Empirical results across different model families confirm consistent improvements, demonstrating the generality and effectiveness of ConG. Taken together, our findings highlight the potential of ConG to advance weak-to-strong generalization and provide a promising pathway toward AGI. Our code is available at: \url{https://github.com/jianghoucheng/ConG}

Robust distributed learning algorithms aim to maintain reliable performance despite the presence of misbehaving workers. Such misbehaviors are commonly modeled as *Byzantine failures*, allowing arbitrarily corrupted communication, or as *data poisoning*, a weaker form of corruption restricted to local training data. While prior work shows similar optimization guarantees for both models, an important question remains: *How do these threat models impact generalization?* We show, for the first time, a fundamental gap in generalization guarantees between the two threat models: Byzantine failures yield strictly worse rates than those achievable under data poisoning. Our findings leverage a tight algorithmic stability analysis of robust distributed learning. Specifically, we prove that: *(i)* under data poisoning, the uniform algorithmic stability of an algorithm with optimal optimization guarantees degrades by an additive factor of $\Theta ( \frac{f}{n-f} )$, with $f$ out of $n$ workers misbehaving; whereas *(ii)* under Byzantine failures, the degradation is in $\Omega \big( \sqrt{ \frac{f}{n-2f}} \big)$.

Humans easily determine which color belongs to which shape in multi-object scenes, an ability known as concept binding. Vision–language embedding models such as CLIP struggle with binding: they recognize individual concepts but fail to represent which concepts form which objects. Although CLIP behaves like a bag-of-concepts model in cross-modal retrieval, object information is recoverable from its image and text embeddings separately. We study this tension through the binding function, which maps concepts to scene embeddings. We find that scene embeddings decompose additively into object representations, explaining why uni-modal probes can recover object information. However, CLIP’s binding function is high-complexity, which likely prevents the image and text encoders from learning a shared binding mechanism that generalizes to unseen concept combinations. We then ask whether this limitation is fundamental. We show that it is not. In controlled transformer models trained from scratch, binding generalization emerges with sufficient data coverage. These models learn low-complexity binding functions characterized by multiplicative interactions between concepts, enabling systematic generalization.

Estimating the generalization gap and developing optimization methods that improve generalization are crucial for deep learning models, for both theoretical understanding and practical applications. Leveraging unlabeled data for these purposes offers significant advantages in real-world scenarios. This paper introduces a novel generalization measure, $\textit{local inconsistency}$, derived from an information-geometric perspective on the parameter space of neural networks. A key feature of local inconsistency is that it can be computed without explicit labels. We establish theoretical underpinnings by connecting local inconsistency to the Fisher information matrix and the loss Hessian. Empirically, we demonstrate that local inconsistency correlates with the generalization gap. Based on these findings, we propose Inconsistency-Aware Minimization (IAM), which incorporates local inconsistency into the training objective. We demonstrate that in standard supervised learning settings, IAM enhances generalization, achieving performance comparable to that of existing methods such as Sharpness-Aware Minimization. Furthermore, IAM exhibits efficacy in semi- and self-supervised learning scenarios, where the local inconsistency is computed from unlabeled data.

Scaling factors in residual branches have emerged as a prevalent method for boosting neural network performance, especially in normalization-free architectures. While prior work has primarily examined scaling effects from an optimization perspective, this paper investigates their role in residual architectures through the lens of generalization theory. Specifically, we establish that wide residual networks (ResNets) with constant scaling factors become asymptotically unlearnable as depth increases. In contrast, when the scaling factor exhibits rapid depth-wise decay combined with early stopping, over-parameterized ResNets achieve minimax-optimal generalization rates. To establish this, we demonstrate that the generalization capability of wide ResNets can be approximated by the kernel regression associated with a specific kernel. Our theoretical findings are validated through experiments on synthetic data and real-world classification tasks, including MNIST and CIFAR-100.

We prove the first margin-based generalization bound for voting classifiers, that is asymptotically tight in the tradeoff between the size of the hypothesis set, the margin, the fraction of training points with the given margin, the number of training samples and the failure probability.

In many modern machine learning pipelines, abundant pretrained representations serve as noisy proxy covariates, while task-specific labels remain scarce. We study semi-supervised regression in this setting, and propose a simple two stage estimator that learns kernel eigenfeatures from all proxy covariates and fits a ridge predictor on labeled data. We derive finite sample bounds showing that fast labeled sample rates are recovered when proxy perturbation is controlled and unlabeled proxy covariates are sufficiently abundant. We also show that distribution regression is a direct special case, with analogous guarantees when the finite bag size is large enough. Experiments show consistent gains over supervised and semi-supervised baselines, especially in low label regimes.

Tabular Language Models (TLMs) have been claimed to achieve strong generalization for tabular prediction. We conduct a systematic re-evaluation of Tabula-8B as a representative TLM, utilizing 165 datasets from the UniPredict benchmark. Our investigation reveals three findings. First, binary and categorical classification achieve near-zero median lift over majority-class baselines and strong aggregate performance is driven entirely by quartile classification tasks. Second, top-performing datasets exhibit pervasive contamination, including complete train-test overlap and task-level leakage that evades standard deduplication. Third, instruction-tuning without tabular exposure recovers 92.2% of standard classification performance and on quartile classification, format familiarity closes 71.3% of the gap with the residual attributable to contaminated datasets. These findings suggest claimed generalization likely reflects evaluation artifacts rather than learned tabular reasoning. We conclude with recommendations for strengthening TLM evaluation.

Compositional generalization, the ability to reason about novel combinations of familiar concepts, is fundamental to human cognition and a critical challenge for machine learning. Object-centric (OC) representations, which encode a scene as a set of objects, are often argued to support such generalization, but systematic evidence in visually rich settings is limited. We introduce a Visual Question Answering benchmark across three controlled visual worlds (CLEVRTex, Super-CLEVR, and MOVi-C) to measure how well vision encoders, with and without object-centric biases, generalize to unseen combinations of object properties. To ensure a fair and comprehensive comparison, we carefully account for training data diversity, sample size, representation size, downstream model capacity, and compute. We use DINOv2 and SigLIP2, two widely used vision encoders, as the foundation models and their OC counterparts. Our key findings reveal that (1) OC approaches are superior in harder compositional generalization settings; (2) original dense representations surpass OC only on easier settings and typically require substantially more downstream compute; and (3) OC models are more sample efficient, achieving stronger generalization with fewer images, whereas dense encoders catch up or surpass them only with sufficient data and diversity. Overall, object-centric representations offer stronger compositional generalization when any one of dataset size, training data diversity, or downstream compute is constrained.

Graph neural networks (GNNs) excel in graph analyzing tasks but often suffer from poor generalization under Out-of-Distribution (OOD) scenarios. Although this problem has attracted increasing attention, most solutions primarily rely on empirical designs, lacking effective mechanisms to characterize and quantify invariance for graph representation learning. To address these limitations, we propose DIGL, a novel graph learning method that improves the OOD generalization of GNNs. Our work makes an initial attempt to geometrize invariance for graphs by introducing computational optimal transport (OT) theory to characterize invariance principle. Specifically, we formulate the underlying invariant prototype shared by graphs across different environments as a distribution barycenter, and consider graph representations in each specific environment as distortions of the prototype. Building on this idea, we establish an invariant learning framework to promote the model to learn purely invariant graph representations for downstream tasks. Moreover, we derive a unified optimization objective for model implementation and provide theoretical analysis to justify our method. Extensive experiments on a broad range of benchmark datasets demonstrate the superior generalization ability of our method compared with baseline methods under various OOD settings.

Generalized Category Discovery (GCD) assigns unlabeled instances, mixed with labeled data, to known or novel categories, requiring human-like compositional reasoning: reusing primitives learned from known classes and deciding when new combinations imply new categories. Existing GCD methods operate on unstructured token features and struggle to extrapolate to novel compositions. We propose CoGe-GCD, which rethinks GCD through compositional generalization with two coupled stages. (i) Compositional Perception structures patch tokens by mapping them to a small vocabulary of primitives and refining token embeddings via competitive token-primitive assignment and information passing, yielding coherent groups for discovery. (ii) Generalizing Induction exploits the induced geometric structure and applies a structure-preserving calibration over spatial relations, maintaining probabilistic semantics while improving extrapolation to unseen primitive combinations. CoGe-GCD is implemented as an inductive-bias module between backbone and projection head, without modifying heads or losses, and can be plugged into diverse GCD frameworks. On standard benchmarks, it consistently improves all-class accuracy, unknown-class number estimation, and geometric quality, with marginal computational overhead.

Mainstream strategies for finetuning pretrained multimodal models often degrade out-of-distribution (OOD) robustness, a phenomenon known as catastrophic forgetting. In this paper, we develop a theoretical framework for multimodal contrastive finetuning, yielding closed-form solutions and a geometric decomposition for these strategies. This framework shows that self-distillation is more effective than other regularization approaches to retain the knowledge of the pretrained model. Our analysis reveals a largely overlooked limitation: standard Exponential Moving Average (EMA) teachers, widely used in robust finetuning, suffer from collapse. To solve this, we prove that a Weighted Moving Average (WMA) teacher maintains a persistent regularizing force over finite horizons and yields bias-free convergence in the task subspace while preserving orthogonal knowledge. These insights motivate **TRACER** (**T**rajectory-**R**obust **A**nchoring for **C**ontrastive **E**ncoder **R**egularization), which combines contrastive learning with WMA-guided multi-perspective distillation. Extensive experiments on CLIP finetuning demonstrate consistent OOD accuracy and calibration gains across three backbone architectures, and comprehensive ablations confirm that TRACER is both principled and robust to hyperparameter choices. Code is available at [https://github.com/HesamAsad/TRACER](https://github.com/HesamAsad/TRACER).

Length generalization is a key property of a learning algorithm that enables it to make correct predictions on inputs of any length, given finite training data. To provide such a guarantee, one needs to be able to compute a length generalization bound, beyond which the model is guaranteed to generalize. This paper concerns the open problem of the computability of such generalization bounds for $\mathsf{C}$-$\mathsf{RASP}$, a class of languages which is closely linked to transformers. A positive partial result was recently shown by Chen et al. for $\mathsf{C}$-$\mathsf{RASP}$ with only one layer and, under some restrictions, also with two layers. We provide complete answers to the above open problem. Our main result is the non-existence of computable length generalization bounds for $\mathsf{C}$-$\mathsf{RASP}$ (already with two layers) and hence for transformers. To complement this, we provide a computable bound for the positive fragment of $\mathsf{C}$-$\mathsf{RASP}$, which we show equivalent to fixed-precision transformers. For both positive $\mathsf{C}$-$\mathsf{RASP}$ and fixed-precision transformers, we show that the length complexity is exponential, and prove optimality of the bounds.

An artificial intelligence must have a model of its environment that is *causal*, supporting reasoning about interventions and counterfactuals, and also *combinatorial*, supporting generalization to unseen combinations of objects. In this work, we formally study when and how such a model can be learned. We develop *relational structural causal models*, extending structural causal models (Pearl 2009) to settings where objects and their relations vary. First, we show how answers to not only causal but also observational queries about unseen combinations of objects can not be identified without further assumptions. To enable such identification---including in the presence of unobserved confounding---we define *relational causal graphs* and derive symbolic identification criteria. Finally, we propose *relational neural causal models*, a provably correct approach that outperforms non-relational baselines on simulated traffic scenes with varying cars, signals, and pedestrians.