Searcharxiv⌕ Search

SEARCH · Searcharxiv

Search Searcharxiv

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 145 records · Page 8Linked to original sources
arXiv2026

Honesty in Causal Forests: When It Helps and When It Hurts

Causal forests estimate how treatment effects vary across individuals, guiding personalized interventions in areas like marketing, operations, and public policy. A standard practice is honest estimation: dividing the data into two samples, one to define subgroups and another to estimate treatment effects within them. This is intended to reduce overfitting and is the default in many software packages. But is it the right choice? We show that honest estimation can reduce the accuracy of estimates of individual treatment effects, especially when effect heterogeneity is substantial and datasets are large enough to detect it. The reason is a bias-variance trade-off: honesty lowers the risk of overfitting but increases the risk of underfitting by limiting the data available to detect and model heterogeneity. Across more than 7,000 benchmark datasets, we find that the cost of using honesty by default can be as high as requiring 27% more data to match the performance of models trained without it. Honesty is best understood as a form of regularization. Whether to adopt it should depend on the goals of the application and its empirical performance, not on reflexive default use.

cs.LG↗
arXiv2026

Data-efficient Kernel Methods for Learning Hamiltonian Systems

Hamiltonian dynamics describe a wide range of physical systems. As such, data-driven simulations of Hamiltonian systems are important for many scientific and engineering problems. In this work, we propose kernel-based methods for identifying and forecasting Hamiltonian systems directly from trajectory data. We present two approaches: a 2-step method that reconstructs trajectories before learning the Hamiltonian, and a 1-step method that jointly infers both. Across several benchmark systems, including mass-spring dynamics, a nonlinear pendulum, and the Henon-Heiles system, we demonstrate that our framework achieves accurate, data-efficient predictions and outperforms 2-step kernel-based baselines, particularly in scarce-data regimes, while preserving the Hamiltonian structure. Moreover, we prove a priori error estimates, ensuring reliability of the learned models. We also provide a more general, problem-agnostic numerical framework that goes beyond Hamiltonian systems and can be used for data-driven learning of arbitrary dynamical systems.

math.NA↗
arXiv2026

Reliable Selection of Heterogeneous Treatment Effect Estimators

We study the problem of selecting the best heterogeneous treatment effect (HTE) estimator from a collection of candidates in settings where the treatment effect is fundamentally unobserved. We cast estimator selection as a multiple testing problem and introduce a ground-truth-free procedure based on a cross-fitted, exponentially weighted test statistic. A key component of our method is a two-way sample splitting scheme that decouples nuisance estimation from weight learning and ensures the stability required for valid inference. Leveraging a stability-based central limit theorem, we establish asymptotic familywise error rate control under mild regularity conditions. Empirically, our procedure provides reliable error control while substantially reducing false selections compared with commonly used methods across ACIC 2016, IHDP, and Twins benchmarks, demonstrating that our method is feasible and powerful even without ground-truth treatment effects.

stat.ML↗
arXiv2026

Active learning for data-driven reduced models of parametric differential systems with Bayesian operator inference

This work develops an active learning framework to intelligently enrich data-driven reduced-order models (ROMs) of parametric dynamical systems, which can serve as the foundation of virtual assets in a digital twin. Data-driven ROMs are explainable, computationally efficient scientific machine learning models that aim to preserve the underlying physics of complex dynamical simulations. Since the quality of data-driven ROMs is sensitive to the quality of the limited training data, we seek to identify training parameters for which using the associated training data results in the best possible parametric ROM. Our approach uses the operator inference methodology, a regression-based strategy which can be tailored to particular parametric structure for a large class of problems. We establish a probabilistic version of parametric operator inference, casting the learning problem as a Bayesian linear regression. Prediction uncertainties stemming from the resulting probabilistic ROM solutions are used to design a sequential adaptive sampling scheme to select new training parameter vectors that promote ROM stability and accuracy globally in the parameter domain. We conduct numerical experiments for several nonlinear parametric systems of partial differential equations and compare the results to ROMs trained on random parameter samples. The results demonstrate that the proposed adaptive sampling strategy consistently yields more stable and accurate ROMs than random sampling does under the same computational budget.

stat.ML↗
arXiv2026

Deep networks learn to parse uniform-depth context-free languages from local statistics

Understanding how the structure of language can be learned from sentences alone is a central question in both cognitive science and machine learning. Studies of the internal representations of Large Language Models (LLMs) support their ability to parse text when predicting the next word, while representing semantic notions independently of surface form. Yet, which data statistics make these feats possible, and how much data is required, remain largely unknown. Probabilistic context-free grammars (PCFGs) provide a tractable testbed for studying these questions. However, prior work has focused either on the post-hoc characterization of the parsing-like algorithms used by trained networks; or on the learnability of PCFGs with fixed syntax, where parsing is unnecessary. Here, we (i) introduce a tunable class of PCFGs in which both the degree of ambiguity and the correlation structure across scales can be controlled; (ii) provide a learning mechanism -- an inference algorithm inspired by the structure of deep convolutional networks -- that links learnability and sample complexity to specific language statistics; and (iii) validate our predictions empirically across deep convolutional and transformer-based architectures. Overall, we propose a unifying framework where correlations at different scales lift local ambiguities, enabling the emergence of hierarchical representations of the data.

stat.ML↗
arXiv2026

Entropy-Generated Attention Beyond Softmax and Entmax: Kaniadakis and Reciprocal-Symmetric Abe Operators

We derive two attention operators from generalized statistical entropies. Kaniadakis entropy yields an exact full-support normalization whose weights and low-score sensitivities decay algebraically, rather than exponentially as in Softmax or by exact truncation as in entmax. Classical Abe entropy yields an implicit reciprocal-symmetric operator. With $q=e^ε$, the involution $q\leftrightarrow q^{-1}$ removes every odd correction about Softmax; we obtain the normalized second- and fourth-order terms, including the deformation of the normalization multiplier. These stationary laws follow from a Fisher-metric Lagrangian on the probability simplex, whose Shannon sector recovers scaled dot-product Softmax. We also give a tangent-gradient test for deciding whether changing the entropy changes the attention profile or only its scale. Rényi and two-parameter Sharma--Mittal entropies retain the Tsallis--entmax inverse-gradient shape, but their global moments make the effective temperature input dependent when the external temperature is fixed. Distinguishing profile-shape equivalence from fixed-parameter operator equivalence separates new normalization shapes from adaptive rescalings and organizes the operators by support, tail behavior, and realization complexity.

cs.LG↗
arXiv2026

Efficient Clustering with Quality Guardrails for LLM-based Recommender Systems at Industry Scale

LLMs can be prohibitively expensive and slow to run at scale, especially for applications that invoke an LLM per sample over millions of inputs. A natural way to scale is to cluster the inputs, run the LLM only on cluster representatives, and propagate the outputs to other cluster members. However, the outputs a member receives are only as good as its match to the representative. Off-the-shelf clustering methods optimize an aggregate objective, targeting average-case quality without per-sample guardrails. As a result, members can be assigned to poorly-matched representatives, and the inherited outputs -- though appropriate for the representative -- may be irrelevant or even unsafe for the member. For example, a parent of a toddler grouped with parents of older children could receive age-inappropriate recommendations. Most clustering methods also scale poorly to millions of inputs in runtime and memory, limiting their use at industry scale. We propose a scalable two-stage clustering algorithm with provable per-sample guardrails: every sample is guaranteed to share a user-specified minimal embedding similarity and exact attribute match with its representative. The algorithm first generates initial clusters with Mini-batch K-Means, then greedily selects representatives within each to satisfy the guardrails. We provide theoretical guarantees, complexity analysis, and benchmarks against common methods on internal and public datasets. Our method delivers per-sample guardrails while running substantially faster and scaling to data sizes where most standard methods become intractable. We demonstrate its impact in a real-world deployment clustering 38 million customers, reducing downstream LLM cost and runtime by 50-fold while preserving personalization. This unblocked the launch of a persona-based recommender system that delivers significant gains in revenue and engagement in an A/B test.

cs.LG↗
arXiv2026

A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors

Pretrained diffusion models represent image distributions through a continuum of progressively smoothed distributions. This multiscale structure organizes generation from global structure to fine detail and supports high-quality, diverse samples. We exploit the same multiscale diffusion prior for linear imaging inverse problems. Rather than using the pretrained model only as a denoiser in an outer iteration, we define a surrogate likelihood whose center is aligned with the clean-image coordinate and whose covariance accounts for residual diffusion uncertainty. This construction defines an explicit surrogate posterior path, from which we derive continuous posterior dynamics. A tunable Langevin component supports target tracking and allows the amount of posterior exploration to be adapted to the application. We prove endpoint consistency and a finite-horizon tracking bound and, in the exact-score setting, first-order weak accuracy. For computation, we derive the Posterior-Dynamics Implicit--Explicit sampler (PD-IMEX), a stable method using one score evaluation per diffusion scale and an implicit data-consistency update. Experiments on deblurring, super-resolution, and inpainting show strong reconstruction quality at 100 score evaluations, coarse-grid stability, and controllable fidelity--diversity behavior.

stat.ML↗
arXiv2026

Activation-Keyed Momentum: An Anisotropic Momentum Update via the Delta Rule

Most modern optimizers form their momentum as an exponential moving average (EMA) of past gradients, forgetting every direction at one fixed rate. However, the inputs a deep network sees during training can be highly anisotropic, with a few directions queried frequently while most are seen rarely. Preconditioning methods address this anisotropy by wrapping extra processing around this buffer and leave the momentum update itself unchanged. We propose Activation-Keyed Momentum (AK-Momentum), which builds direction-awareness into the momentum update rule. The gradient of a linear layer splits into an input activation that acts as a key and an output-side error that acts as a value. Keying on that activation, AK-Momentum updates the momentum buffer by the canonical delta rule, so each direction is forgotten at a rate set by how often it appears. We prove that it is a valid momentum, that it applies the input-side curvature correction without matrix inversion, and that it clears stale directions faster than EMA under both a fixed and a drifting optimum. It is a drop-in replacement for the momentum buffer of any optimizer, its coefficient transfers across widths under $μ$P, and its extra compute stays between $22.2\%$ and $25.0\%$ of a gated-MLP block's linear cost with no persistent memory. In FineWeb-Edu pretraining, AdamW with AK-Momentum (AK-AdamW) reaches AdamW's validation loss in up to $46.39 \pm 4.32\%$ fewer steps at 67M and $22.12 \pm 0.80\%$ at 370M over three seeds, and the gain persists at 1B on a Chinchilla-optimal budget. A Muon baseline tuned under the same protocol sits above AK-AdamW at both language-model scales, and the gain holds for SGD, ResNet-18, and ViT-Tiny on CIFAR-10. Training-time diagnostics confirm the predicted mechanism, better gradient tracking and healthier input directions.

cs.LG↗
arXiv2026

Improved Gradient Descent Lower Bounds Beyond Nesterov

We study how far gradient descent (GD) can be accelerated by predetermined stepsizes in smooth convex optimization. Going beyond the classical $Ω(n^{-2})$ first-order oracle lower bound of Nemirovsky and Yudin (1983), we prove an $Ω(n^{-1.6342})$ non-anytime lower bound and an $Ω(n^{-1.2408})$ anytime lower bound. These improve the recent $Ω(n^{-1.932})$ non-anytime lower bound of Ma and Chen (2026) and the $Ω(n^{-4/3})$ anytime lower bound of Tsai et al. (2026), respectively. Both results continue to hold when the stepsizes may be negative. Our anytime lower bound also shows that the $O(n^{-\log_2(1+\sqrt{2})})$ rate of non-anytime silver schedules (Altschuler and Parrilo, 2025; Grimmer et al., 2025) is unattainable in the anytime setting. This establishes a strict separation between the two settings.

math.OC↗
arXiv2026

ALRA: Adaptive Local Relational Alignment for Logit-Based Pre-training Distillation of Autoregressive Language Models

Logit-based knowledge distillation for autoregressive language models usually aligns teacher and student next-token distributions over the entire vocabulary. However, this global objective overlooks relative preferences among likely token alternatives. Existing local approaches often select candidate tokens from either the teacher or the student alone. Teacher-only selection can miss tokens that the student considers likely, while student-only selection can rely on an inaccurate ranking early in training. We propose Adaptive Local Relational Alignment (ALRA), a position-specific framework combining student proposals with teacher guidance. At each valid prediction position, the student proposes likely tokens, while the teacher's most probable token is included as an anchor. ALRA adjusts the number of selected tokens according to how broadly the teacher distributes probability within this candidate set relative to the current batch. Adaptive Local Divergence retains the mass-matching term and separately matches the relative token distributions within the selected and remaining vocabulary regions. Unlike the exact full-vocabulary decomposition, it replaces the teacher-mass coefficients of the two conditional terms with unit coefficients, preventing either term from being downweighted solely because its region has low teacher probability. Student-Weighted Pairwise Relational Alignment emphasizes high-probability token pairs with small student probability gaps and gives less weight to unlikely or clearly separated pairs. Experiments on The Pile with randomly initialized 200M- and 500M-parameter students across nine zero-shot benchmarks yield average accuracies of 36.62% and 37.40%. ALRA exceeds the strongest competing distillation baseline by 0.94 and 0.83 percentage points and improves over pre-training without distillation by 2.31 and 2.91 points, respectively.

stat.ML↗
arXiv2026

Towards a Statistical Understanding of Mixture-of-Experts

Mixture-of-experts (MoE) architectures increase model capacity by combining a collection of expert predictors through input-dependent routing, while often activating only a small subset of experts for each input. Despite their growing importance in modern large-scale models, the statistical roles of their design choices, especially routing, sparse activation, and shared experts, remain only partially understood, as existing theory has largely focused on parametric or correctly specified MoE models. In this paper, we view MoE as a form of localized aggregation and show how this localization reshapes the approximation-estimation-computation tradeoff. We derive oracle risk bounds for learning dense and sparse routing with evolving experts, separating approximation, expert-learning, and router-estimation errors, and characterize how sparse Top-K routing can retain the benefits of localized aggregation while controlling per-input computation. We also interpret gating through the geometry of input space, relating routing performance to regions of local expert advantage, and show how shared experts, as adopted in architectures such as DeepSeekMoE, can extract common predictive structure so that routed experts focus on residual local variation. Together, these results provide a unified statistical framework for understanding MoE through input-dependent expert aggregation, in which expert specialization and computational tradeoffs are governed by local predictive structure.

stat.ML↗
arXiv2026

Correlated initialization of deep residual networks

We study the large-depth behavior of residual networks whose weights are correlated across layers at initialization. Our results confirm and extend a conjecture of Marion et al. [2025], according to which correlated initializations should interpolate continuously between the Brownian stochastic differential equation arising from independent initialization and the ordinary differential equation arising from perfectly correlated initialization. When the initialization is obtained from the application of a feature function to a stationary Gaussian sequence with regularly varying correlation, we prove that there exists a unique critical scaling such that the infinite-depth limit is the solution of a Young differential equation driven by a Hermite process. Hermite processes reduce to the fractional Brownian motion if the feature function generating the initialization has Hermite rank one, which is the case for the identity function, for example. We show that the critical scaling and asymptotic limit are uniquely determined by the decay of correlations together with the Hermite rank of the feature function. Consequently, the correlation structure and Hermite rank of the initialization represent meaningful hyperparameters in the asymptotic regime. By contrast, under finite-variance iid initialization, the asymptotic driver is universally Brownian up to normalization regardless of the choice of distribution. Our proofs rely on a collection of novel results establishing a robust stability theory for Young differential equations in Banach spaces.

math.PR↗
arXiv2026

High-Dimensional Learning Dynamics of Attention-Indexed Models

Attention mechanisms are central to modern foundation models, yet their training dynamics remain poorly understood, especially when the attention matrices have extensive rank. In this work, we study attention-indexed models, a broad framework that can represent multi-layer and multi-head attention architectures. First, we show that, in a suitable high-dimensional limit, the population-loss landscape is characterized by a finite set of trace order parameters. In contrast, online stochastic gradient descent (SGD) is governed by an infinite hierarchy of matrix moments, which we show can be exponentially well-approximated by a finite truncated system. Second, this framework reveals that attention parameterization itself can act as an architectural implicit bias. Direct optimization of an attention matrix $S\in\mathbb{R}^{d\times d}$ can remain trapped in an uninformative state. Tied attention ($S=WW^\top$) induces an automatic symmetry-breaking mechanism and yields weak recovery in $Θ(d^2\log d)$ samples. For untied attention, $S=UV^\top$, we uncover a fast-slow mechanism: the pre-activation mean first evolves on a fast timescale, while the overlaps evolve on a slower one. Weak recovery on the $Θ(d^2\log d)$ scale occurs when the state selected by the fast dynamics breaks the initial symmetry.

cs.LG↗
arXiv2026

Cooperative Multi-Task Semantic Communication for Joint Classification and Regression Tasks

Multi-Task semantic communication (SemCom) prioritizes simultaneous execution of multiple tasks over bit-accurate reconstruction in future intelligent networks. In our prior work [1], we introduced the cooperative multi-task SemCom (CMT-SemCom) framework, in which the semantic encoder is divided into a common unit (CU) and multiple specific units (SUs) to facilitate cooperative multi-task processing. However, CMT-SemCom has been evaluated on homogeneous classification tasks on simplistic datasets, limiting its applicability to real-world perception systems. In this paper, we extend our CMT-SemCom to jointly handle heterogeneous classification and regression tasks on the complex Cityscapes dataset. We adopt the information maximization (InfoMax) principle so that it accommodates mixed discrete and continuous semantic variables. In particular, we benchmark the proposed framework against independent single-task training, a conventional task-agnostic digital transmission, and single-encoder multi-decoder SemCom. Additionally, we investigate the impact of CU capacity on joint task performance, providing design insights. Extensive evaluations demonstrate that CMT-SemCom significantly outperforms the benchmarks.

eess.SP↗
arXiv2026

A Constraint-Aware Generative Framework for Synthetic Origin-Destination Demand in Logistics Networks

Large-scale logistics networks require synthetic data generation capabilities to support scenario-based planning under novel conditions-such as network reconfiguration and demand shocks. Existing approaches, which rely primarily on historical observations, lack the ability to generate demand patterns that adapt to changes in network topology while respecting operational constraints. We propose a constraint-aware conditional generative framework for synthetic origin-destination demand generation in hierarchical logistics networks. The framework models demand as a conditional distribution over destinations given each origin, enabling topology-aware synthesis that is both topologically realistic and operationally feasible. Operational guidance is incorporated directly into the generative objective via differentiable constraints, while a flexible conditioning mechanism supports various operational contexts and adaptation to evolving network configurations. We instantiate the proposed framework based on a conditional generative model. Experimental validation on industrial real fulfillment and transportation network demonstrates 16% improvement over graph neural network baselines, 87% operational compliance, and efficient cold-start adaptation, enabling applications in capacity planning, network design evaluation, and routing optimization.

eess.SY↗
arXiv2026

Rollcast: Proper-Score Gated Rolling Anchors for Adaptive Probabilistic Time-Series Forecasting

Rollcast is a probabilistic forecasting method for univariate time series that combines a compact set of rolling statistical anchors rather than relying on a single global model. Rolling means, medians, extrema, regression endpoints, and quantiles define candidate forecast locations and a representation of the current state. A state-dependent softmax gate learns anchor probabilities by minimizing negative log predictive density, while residual distributions retrieved from similar historical states provide local uncertainty. Recursive simulation propagates the resulting mixture over multiple forecast horizons. The method is evaluated in a Monte Carlo study covering eight data-generating processes, including autoregressive, random-walk, local-trend, threshold, regime-switching, stochastic-volatility, heavy-tailed, and variance-break dynamics. Across 2,000 independent fitted series, Rollcast is compared with the true conditional predictive distribution generated by an oracle simulator. Overall empirical coverage is 86.2% for nominal 90% intervals and 91.5% for nominal 95% intervals. Predictive intervals are on average 13.6% wider than the oracle at the 90% level, while CRPS is 14.4% higher than oracle CRPS. Performance is closest to the oracle under autoregressive, threshold, stochastic-volatility, heavy-tailed, and variance-break dynamics, while local trends and regime switching are more challenging. The results indicate that Rollcast can construct competitive probabilistic forecasts from simple, interpretable local summaries, while also identifying limitations in calibration and recursive uncertainty propagation.

stat.ML↗
arXiv2026

Spectral characteristics of autoencoder parameters as a vector representation of data

This paper examines the relationship between the parameters of autoencoder models and the statistical properties of the data on which they are trained. Autoencoders are defined as models with an encoder-decoder architecture, trained to reconstruct input data through a compressed latent representation. It is proposed that the model parameters can be viewed as a dense vector representation of the corresponding sample. To test this hypothesis, a theoretical and experimental study is conducted in which a vector representation is formed based on the spectral characteristics of the autoencoder parameter matrices. Theoretical analysis shows that the singular values of the model parameter matrices are related to the eigenvalues of the covariance matrix of the training data, ensuring the transfer of information between the data space and the parameter space. Experimental results on the CIFAR-10 and FashionMNIST datasets confirm that the resulting vector representations allow for a high degree of accuracy in distinguishing between models trained on different data subsets, without resorting to complex vector generation algorithms or using the original samples. These results suggest that the parameters of trained autoencoders can be viewed as sample representations.

cs.LG↗