Machine Learning · Cross-listed from cs.CL
Scalable Identification and Prioritization of Requisition-Specific Personal Competencies Using Large Language Models
Wanxin Li, Denver McNeney, Nivedita Prabhu et al. (+5 more)
AI-powered recruitment tools are increasingly adopted in personnel selection, yet they struggle to capture the requisition (req)-specific personal competencies (PCs) that distinguish successful candidates beyond job categories. We propose a large
language model (LLM)-based approach to identify and prioritize req-specific PCs from reqs. Our approach integrates dynamic few-shot prompting, reflection-based self-improvement, similarity-based filtering, and multi-stage validation. Applied to a
dataset of Program Manager reqs, our approach correctly identifies the highest-priority req-specific PCs with an average accuracy of 0.76, approaching human expert inter-rater reliability, and maintains a low out-of-scope rate of 0.07.
Read the full abstract ▾
All authors Wanxin Li, Denver McNeney, Nivedita Prabhu, Charlene Zhang, Renee Barr, Matthew Kitching, Khanh Dao Duc, Anthony S. Boyce
Machine Learning
Speculating Experts Accelerates Inference for Mixture-of-Experts
Vivan Madan, Prajwal Singhania, Abhinav Bhatele et al. (+2 more)
Mixture-of-Experts (MoE) models have gained popularity as a means of scaling the capacity of large
language models (LLMs) while maintaining sparse activations and reduced per-
token compute. However, in
memory-constrained inference settings, expert weights must be offloaded to CPU, creating a performance bottleneck from CPU-GPU transfers during decoding. We propose an expert prefetching scheme that leverages currently computed internal model representations to speculate future experts, enabling
memory transfers to overlap with computation. Across multiple MoE architectures, we demonstrate that future experts can be reliably predicted by these internal representations. We also demonstrate that executing speculated experts generally maintains downstream task accuracy, thus preserving more effective compute-
memory overlap by eliminating the need to re-fetch true router-selected experts. Integrated into an optimized inference engine, our approach achieves up to 14% reduction in time per output
token (TPOT) over on-demand loading of experts from CPU
memory. For MoEs where speculative execution alone yields suboptimal accuracy, we further examine lightweight
estimators that improve expert prediction hit rates, thereby reducing performance degradation. Our code is released in open-source at https://github.com/axonn-ai/yalis/tree/offload_prefetch.
Read the full abstract ▾
All authors Vivan Madan, Prajwal Singhania, Abhinav Bhatele, Tom Goldstein, Ashwinee Panda
Machine Learning · Cross-listed from q-fin.PM
Joint Return and Risk Modeling with Deep Neural Networks for Portfolio Construction
Keonvin Park
Portfolio construction traditionally relies on separately estimating expected returns and covariance
matrices using historical statistics, often leading to suboptimal allocation under time-varying
market conditions. This paper proposes a joint return and risk modeling framework based on deep neural networks that enables end-to-end learning of dynamic expected returns and risk structures from sequential financial data. Using daily data from ten large-cap US equities spanning 2010 to 2024, the proposed model is evaluated across return prediction, risk estimation, and portfolio-level performance. Out-of-sample results during 2020 to 2024 show that the deep
forecasting model achieves competitive predictive accuracy (RMSE = 0.0264) with economically meaningful directional accuracy (51.9%). More importantly, the learned representation effectively captures
volatility clustering and regime shifts. When integrated into portfolio optimization, the proposed Neural Portfolio strategy achieves an annual return of 36.4% and a Sharpe ratio of 0.91, outperforming equal weight and historical mean-variance
benchmarks in terms of risk-adjusted performance. These findings demonstrate that jointly modeling return and covariance dynamics can provide consistent improvements over traditional allocation approaches. The framework offers a scalable and practical alternative for data-driven portfolio construction under nonstationary
market conditions.
Read the full abstract ▾
Machine Learning
Towards Differentiating Between Failures and Domain Shifts in Industrial Data Streams
Natalia Wojak-Strzelecka, Szymon Bobek, Grzegorz J. Nalepa et al. (+1 more)
Anomaly and failure detection methods are crucial in identifying deviations from normal system operational conditions, which allows for actions to be taken in advance, usually preventing more serious damages. Long-lasting deviations indicate failures, while sudden, isolated changes in the data indicate anomalies. However, in many practical applications, changes in the data do not always represent abnormal system states. Such changes may be recognized incorrectly as failures, while being a normal
evolution of the system, e.g. referring to characteristics of starting the processing of a new product, i.e. realizing a domain shift. Therefore, distinguishing between failures and such ”healthy” changes in data distribution is critical to ensure the practical robustness of the system. In this paper, we propose a method that not only detects changes in the data distribution and anomalies but also allows us to distinguish between failures and normal domain shifts inherent to a given process. The proposed method consists of a modified Page-Hinkley changepoint detector for identification of the domain shift and possible failures and supervised domain-adaptation-based
algorithms for fast, online anomaly detection. These two are coupled with an explainable artificial intelligence (XAI) component that aims at helping the human operator to finally differentiate between domain shifts and failures. The method is illustrated by an experiment on a data stream from the steel factory.
Read the full abstract ▾
All authors Natalia Wojak-Strzelecka, Szymon Bobek, Grzegorz J. Nalepa, Jerzy Stefanowski
Machine Learning · Cross-listed from cs.AI
The ARC of Progress towards AGI: A Living Survey of Abstraction and Reasoning
Sahar Vahdati, Andrei Aioanei, Haridhra Suresh et al. (+1 more)
The Abstraction and
Reasoning Corpus (ARC-AGI) has become a key
benchmark for fluid intelligence in AI. This survey presents the first cross-generation analysis of 82 approaches across three
benchmark versions and the ARC Prize 2024-2025 competitions. Our central finding is that performance degradation across versions is consistent across all paradigms: program synthesis, neuro-symbolic, and neural approaches all exhibit 2-3x drops from ARC-AGI-1 to ARC-AGI-2, indicating fundamental limitations in compositional generalization. While systems now reach 93.0% on ARC-AGI-1 (Opus 4.6), performance falls to 68.8% on ARC-AGI-2 and 13% on ARC-AGI-3, as humans maintain near-perfect accuracy across all versions. Cost fell 390x in one year (o3's $4,500/task to GPT-5.2's $12/task), although this largely reflects reduced test-time parallelism. Trillion-scale models vary widely in score and cost, while Kaggle-constrained entries (660M-8B) achieve competitive results, aligning with Chollet's thesis that intelligence is skill-acquisition efficiency. Test-time adaptation and refinement loops emerge as critical success factors, while compositional
reasoning and interactive learning remain unsolved. ARC Prize 2025 winners needed hundreds of thousands of synthetic examples to reach 24% on ARC-AGI-2, confirming that
reasoning remains knowledge-bound. This first release of the ARC-AGI Living Survey captures the field as of February 2026, with updates at https://nimi-ai.com/arc-survey/
Read the full abstract ▾
All authors Sahar Vahdati, Andrei Aioanei, Haridhra Suresh, Jens Lehmann
Machine Learning · Cross-listed from cs.CV
GraphVLM: Benchmarking Vision Language Models for Multimodal Graph Learning
Jiajin Liu, Dongzhe Fan, Chuanhao Ji et al. (+2 more)
Vision-
Language Models (VLMs) have demonstrated remarkable capabilities in aligning and understanding
multimodal signals, yet their potential to reason over structured data, where
multimodal entities are connected through explicit relational graphs, remains largely underexplored. Unlocking this capability is crucial for real-world applications such as social networks, recommendation systems, and scientific discovery, where
multimodal information is inherently structured. To bridge this gap, we present GraphVLM, a systematic
benchmark designed to evaluate and harness the capabilities of VLMs for
multimodal graph learning (MMGL). GraphVLM investigates three complementary paradigms for integrating VLMs with graph
reasoning: (1) VLM-as-Encoder, which enriches graph neural networks through
multimodal feature fusion; (2) VLM-as-Aligner, which bridges modalities in latent or linguistic space to facilitate LLM-based structured
reasoning; and (3) VLM-as-Predictor, which directly employs VLMs as
multimodal backbones for graph learning tasks. Extensive experiments across six
datasets from diverse domains demonstrate that VLMs enhance
multimodal graph learning via all three roles. Among these paradigms, VLM-as-Predictor achieves the most substantial and consistent performance gains, revealing the untapped potential of
vision-
language models as a new foundation for
multimodal graph learning. The
benchmark code is publicly available at https://github.com/oamyjin/GraphVLM.
Read the full abstract ▾
All authors Jiajin Liu, Dongzhe Fan, Chuanhao Ji, Daochen Zha, Qiaoyu Tan
Machine Learning · Cross-listed from cs.CV
Multimodal Deep Learning for Dynamic and Static Neuroimaging: Integrating MRI and fMRI for Alzheimer Disease Analysis
Anima Kujur and Zahra Monfared
Magnetic Resonance Imaging (MRI) provides detailed structural information, while functional MRI (fMRI) captures temporal
brain activity. In this work, we present a
multimodal deep learning framework that integrates MRI and fMRI for multi-class classification of Alzheimer Disease (AD), Mild Cognitive Impairment, and Normal Cognitive State. Structural features are extracted from MRI using 3D convolutional neural networks, while temporal features are learned from fMRI sequences using recurrent architectures. These representations are fused to enable joint spatial-temporal learning. Experiments were conducted on a small paired MRI-fMRI
dataset (29 subjects), both with and without data augmentation. Results show that data augmentation substantially improves classification stability and generalization, particularly for the
multimodal 3DCNN-LSTM model. In contrast, augmentation was found to be ineffective for a large-scale single-modality MRI
dataset. These findings highlight the importance of
dataset size and modality when designing augmentation strategies for neuroimaging-based AD classification.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Graph2Video: Leveraging Video Models to Model Dynamic Graph Evolution
Hua Liu, Yanbin Wei, Fei Xing et al. (+3 more)
Dynamic graphs are common in real-world systems such as social media, recommender systems, and traffic networks. Existing dynamic graph models for link prediction often fall short in capturing the complexity of temporal
evolution. They tend to overlook fine-grained variations in temporal interaction order, struggle with dependencies that span long time horizons, and offer limited capability to model pair-specific relational dynamics. To address these challenges, we propose Graph2
Video, a
video-inspired framework that views the temporal neighborhood of a target link as a sequence of "graph frames". By stacking temporally ordered subgraph frames into a "graph
video", Graph2
Video leverages the inductive biases of
video foundation models to capture both fine-grained local variations and long-range temporal dynamics. It generates a link-level
embedding that serves as a lightweight and plug-and-play link-centric
memory unit. This
embedding integrates seamlessly into existing dynamic graph encoders, effectively addressing the limitations of prior approaches. Extensive experiments on
benchmark datasets show that Graph2
Video outperforms state-of-the-art baselines on the link prediction task in most cases. The results highlight the potential of borrowing spatio-temporal modeling techniques from computer
vision as a promising and effective approach for advancing dynamic graph learning.
Read the full abstract ▾
All authors Hua Liu, Yanbin Wei, Fei Xing, Tyler Derr, Haoyu Han, Yu Zhang
Machine Learning · Cross-listed from cs.CV
Bi-CamoDiffusion: A Boundary-informed Diffusion Approach for Camouflaged Object Detection
Patricia L. Suarez, Leo Thomas Ramos and Angel D. Sappa
Bi-CamoDiffusion is introduced, an
evolution of the CamoDiffusion framework for camouflaged object detection. It integrates edge priors into early-stage
embeddings via a parameter-free injection process, enhancing boundary sharpness and preventing structural ambiguity. An optimization objective that unifies spatial accuracy, structural constraints, and uncertainty supervision is also proposed, allowing the model to capture of both the object's global context and its intricate boundary transitions. Evaluations across the CAMO, COD10K, and NC4K
datasets show that Bi-CamoDiffusion surpasses the baseline, delivering sharper delineation of thin structures and protrusions while also minimizing false positives. The model consistently outperforms existing state-of-the-art methods across all evaluated metrics, including $S_m$, $F_{\beta}^{w}$, $E_m$, and $MAE$, demonstrating a more precise object-background separation and sharper boundary recovery. Code available at: https://github.com/plsuarez/Bi-CamoDiffusion
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
Learning When to Trust in Contextual Social Bandits
Majid Ghasemi and Mark Crowley
Robust reinforcement learning typically assumes that feedback sources are either globally trustworthy or corrupted within a fixed global budget. We identify a more subtle failure mode that escapes this dichotomy, which we call Contextual Sycophancy. In this failure, evaluators are truthful in benign contexts but systematically biased in critical ones, so that no single evaluator is reliable everywhere and the corrupt evaluators may form a majority in the contexts that matter. Our first result is an information-theoretic lower bound. We exhibit two problem instances that induce identical social-feedback distributions yet have disjoint optimal actions, proving that any
algorithm relying on social feedback alone (including any robust aggregator, regardless of breakdown point) incurs $\Omega(T)$ latent regret. This shows that breaking contextual sycophancy is impossible without having some information. We then show that a sparse stream of ground-truth audits, available with probability $p_{\mathrm{aud}}$, is sufficient. We propose \ESA, which learns a per-evaluator contextual trust boundary from audits and re-weights feedback accordingly, and we prove a high-probability latent-regret bound of $\tilde{\mathcal{O}}\!\big(\sqrt{T\,d_{VC}/p_{\mathrm{aud}}} + d\sqrt{T} + \epsilon_{\mathrm{tol}}T\big)$, where $d_{VC}$ is the complexity of the adversary's bias strategy. The audit-dependence $1/\sqrt{p_{\mathrm{aud}}}$ matches the information-theoretic necessity of audits. Empirically, \ESA\ recovers the ground truth when $80\%$ of the social layer is
adversarial, a regime in which median- and mean-based robust baselines fail.
Read the full abstract ▾
Machine Learning
Training Language Models via Neural Cellular Automata
Dan Lee, Seungwook Han, Akarsh Kumar et al. (+1 more)
Pre-training is crucial for large
language models (LLMs), as it is when most representations and capabilities are acquired. However, natural
language pre-training has problems: high-quality text is finite, contains human biases, and entangles knowledge with
reasoning. This raises a fundamental question: is natural
language the only path to intelligence? We propose using neural cellular automata (NCA) to generate synthetic, non-linguistic data for pre-pre-training LLMs–training on synthetic-then-natural
language. NCA data exhibits rich spatiotemporal structure and statistics resembling natural
language while being controllable and cheap to generate at scale. We find that pre-pre-training on only 164M NCA
tokens improves downstream
language modeling by up to 6% and accelerates convergence by up to 1.6x in 400M-3B models trained with Chinchilla optimal data budgets. Surprisingly, this even outperforms pre-pre-training on 1.6B
tokens of high-quality natural
language data with more compute. Investigating what drives transfer, we find that
attention layers are the most transferable, and that optimal NCA complexity varies by domain: code benefits from simpler dynamics, while math and web text favor more complex ones. These results enable systematic tuning of the synthetic distribution to target domains. More broadly, our work opens a path toward more efficient models with fully synthetic pre-training.
Read the full abstract ▾
All authors Dan Lee, Seungwook Han, Akarsh Kumar, Pulkit Agrawal
Machine Learning · Cross-listed from cs.IT
Quantization of Ricci Curvature in Information Geometry
Carlos C. Rodriguez
In 2004, while studying the information geometry of binary
Bayesian networks (bitnets), the author conjectured that the volume-averaged
Ricci scalar <R> computed with respect to the Fisher information metric is universally quantized to positive half-integers: <R> in (1/2)Z. This paper resolves the
conjecture after 20 years. We prove it for tree-structured and complete-graph bitnets via a universal Beta function cancellation mechanism, and disprove it in general by exhibiting explicit loop counterexamples. We extend the program to Gaussian DAG networks, where a sign dichotomy holds: discrete bitnets have positive
curvature, while Gaussian networks form solvable Lie groups with negative
curvature.
Read the full abstract ▾
Machine Learning
Cluster-Aware Attention-Based Deep Reinforcement Learning for Pickup and Delivery Problems
Wentao Wang, Lifeng Han and Guangyu Zou
The Pickup and Delivery Problem (PDP) is a fundamental and challenging variant of the Vehicle Routing Problem, characterized by tightly coupled pickup–delivery pairs, precedence constraints, and spatial layouts that often exhibit clustering. Existing deep reinforcement learning (DRL) approaches either model all nodes on a flat graph, relying on implicit learning to enforce constraints, or achieve strong performance through inference-time collaborative search at the cost of substantial latency. In this paper, we propose CAADRL (Cluster-Aware
Attention-based Deep Reinforcement Learning), a DRL framework that explicitly exploits the multi-scale structure of PDP instances via cluster-aware encoding and hierarchical decoding. The encoder builds on a
Transformer and combines global self-
attention with intra-cluster
attention over depot, pickup, and delivery nodes, producing
embeddings that are both globally informative and locally role-aware. Based on these
embeddings, we introduce a Dynamic Dual-Decoder with a learnable gate that balances intra-cluster routing and inter-cluster transitions at each step. The policy is trained end-to-end with a POMO-style policy gradient scheme using multiple symmetric rollouts per instance. Experiments on synthetic clustered and uniform PDP
benchmarks show that CAADRL matches or improves upon strong state-of-the-art baselines on clustered instances and remains highly competitive on uniform instances, particularly as problem size increases. Crucially, our method achieves these results with substantially lower inference time than neural collaborative-search baselines, suggesting that explicitly modeling cluster structure provides an effective and efficient inductive bias for neural PDP solvers.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.RO
OmniGuide: Universal Spatial Guidance Fields for Enhancing Generalist Robot Policies
Yunzhou Song, Long Le, Yong-Hyun Park et al. (+7 more)
Vision-
language-action (VLA) models have shown great promise as generalist policies for a large range of relatively simple tasks. However, they demonstrate limited performance on more complex tasks, such as those requiring complex spatial or semantic understanding, manipulation in clutter, or precise manipulation. We propose OmniGuide, a flexible framework that improves VLA performance on such tasks by leveraging arbitrary sources of guidance, such as 3D foundation models, semantic-
reasoning VLMs, and human pose models. We show how many kinds of guidance can be naturally expressed as differentiable energy functions with task-specific attractors and repellers located in 3D space, that influence the sampling of VLA actions. In this way, OmniGuide enables guidance sources with complementary task-relevant strengths to improve a VLA model's performance on challenging tasks. Extensive experiments in both simulation and real-world environments, across diverse sources of guidance, demonstrate that OmniGuide enhances the performance of state-of-the-art generalist policies (e.g., $\pi_{0.5}$, GR00T N1.6) significantly across success and safety rates. Critically, our unified framework matches or surpasses the performance of prior methods designed to incorporate specific sources of guidance into VLA policies. Project page: https://omniguide.github.io/
Read the full abstract ▾
All authors Yunzhou Song, Long Le, Yong-Hyun Park, Jie Wang, Junyao Shi, Lingjie Liu, Jiatao Gu, Eric Eaton, Dinesh Jayaraman, Kostas Daniilidis
Machine Learning · Cross-listed from cs.NI
Where Do Flow Semantics Reside? A Protocol-Native Tabular Pretraining Paradigm for Encrypted Traffic Classification
Sizhe Huang, Zitong Li and Shujie Yang
Self-supervised masked modeling shows promise for encrypted traffic classification by masking and reconstructing raw bytes. Yet recent work reveals these methods fail to reduce reliance on labeled data despite costly pretraining: under frozen encoder evaluation, accuracy drops from greater than 0.9 to less than 0.47. We argue the root cause is inductive bias mismatch: flattening traffic into byte sequences destroys protocol-defined semantics. We identify three specific issues: 1) field unpredictability, random fields like ip.id are unlearnable yet treated as reconstruction targets; 2)
embedding confusion, semantically distinct fields collapse into a unified
embedding space; 3) metadata loss, capture-time metadata essential for temporal analysis is discarded. To address this, we propose a protocol-native paradigm that treats protocol-defined field semantics as architectural priors, reformulating the task to align with the data's intrinsic tabular modality rather than incrementally adapting sequence-based architectures. Instantiating this paradigm, we introduce FlowSem-MAE, a tabular masked autoencoder built on Flow Semantic Units (FSUs). It features predictability-guided filtering that focuses on learnable FSUs, FSU-specific
embeddings to preserve field boundaries, and dual-axis
attention to capture intra-packet and temporal patterns. FlowSem-MAE significantly outperforms state-of-the-art across
datasets. With only half labeled data, it outperforms most existing methods trained on full data.
Read the full abstract ▾
Machine Learning
InFusionLayer: a CFA-based ensemble tool to generate new classifiers for learning and modeling
Eric Roginek, Jingyan Xu and D. Frank. Hsu
Ensemble learning is a well established body of methods for machine learning to enhance predictive performance by combining multiple
algorithms/models. Combinatorial Fusion Analysis (CFA) has provided method and practice for combining multiple scoring systems, using rank-score characteristic (RSC) function and cognitive diversity (CD), including ensemble method and model fusion. However, there is no general-purpose Python tool available that incorporate these techniques. In this paper we introduce InFusionLayer, a machine learning architecture inspired by CFA at the system fusion level that uses a moderate set of base models to optimize unsupervised and supervised learning multiclassification problems. We demonstrate InFusionLayer's ease of use for PyTorch, TensorFlow, and Scikit-learn workflows by validating its performance on various computer
vision datasets. Our results highlight the practical advantages of incorporating distinctive features of RSC function and CD, paving the way for more sophisticated ensemble learning applications in machine learning. We open-sourced our code to encourage continuing development and community accessibility to leverage CFA on github: https://github.com/ewroginek/Infusion
Read the full abstract ▾
Machine Learning
Revisiting Sharpness-Aware Minimization: A More Faithful and Effective Implementation
Jianlong Chen and Zhiming Zhou
Sharpness-Aware Minimization (SAM) enhances generalization by minimizing the maximum training loss within a predefined neighborhood around the parameters. However, its practical implementation approximates this as gradient ascent(s) followed by applying the gradient at the ascent point to update the current parameters. This practice can be justified as approximately optimizing the objective by neglecting the (full) derivative of the ascent point with respect to the current parameters. Nevertheless, a direct and intuitive understanding of why using the gradient at the ascent point to update the current parameters works superiorly is still lacking. Our work bridges this gap by proposing a novel and intuitive interpretation. We show that the gradient at the single-step ascent point, \uline{when applied to the current parameters}, provides a better approximation of the direction from the current parameters toward the maximum within the local neighborhood than the local gradient. This improved approximation thereby enables a more direct escape from the maximum within the local neighborhood. Nevertheless, our analysis further reveals two issues. First, the approximation by the gradient at the single-step ascent point is often inaccurate. Second, the approximation quality may degrade as the number of ascent steps increases. To address these limitations, we propose in this paper eXplicit Sharpness-Aware Minimization (XSAM). It tackles the first by explicitly estimating the direction of the maximum during training, while addressing the second by crafting a search space that effectively leverages the gradient information at the multi-step ascent point. XSAM features a unified formulation that applies to both single-step and multi-step settings and only incurs negligible computational overhead. Extensive experiments demonstrate the consistent superiority of XSAM against existing counterparts.
Read the full abstract ▾
Machine Learning
When to Retrain after Drift: A Data-Only Test of Post-Drift Data Size Sufficiency
Ren Fujiwara, Yasuko Matsubara and Yasushi Sakurai
Sudden concept drift makes previously trained predictors unreliable, yet deciding when to retrain and what post-drift data size is sufficient is rarely addressed. We propose CALIPER - a detector- and model-agnostic, data-only test that estimates the post-drift data size required for stable retraining. CALIPER exploits state dependence in streams generated by dynamical systems: we run a single-pass weighted local regression over the post-drift window and track a one-step proxy error as a function of a locality parameter $\theta$. When an effective sample size gate is satisfied, a monotonically non-increasing trend in this error with increasing a locality parameter indicates that the data size is sufficiently informative for retraining. We also provide a theoretical analysis of our method, and we show that the
algorithm has a low per-update time and
memory. Across
datasets from four heterogeneous domains, three learner families, and two detectors, CALIPER consistently matches or exceeds the best fixed data size for retraining while incurring negligible overhead and often outperforming incremental updates. CALIPER closes the gap between drift detection and data-sufficient adaptation in streaming learning.
Read the full abstract ▾
Machine Learning
An accurate flatness measure to estimate the generalization performance of CNN models
Rahman Taleghani, Maryam Mohammadi and Francesco Marchetti
Flatness measures based on the spectrum or the trace of the Hessian of the loss are widely used as proxies for the generalization ability of deep networks. However, most existing definitions are either tailored to fully connected architectures, relying on
stochastic estimators of the Hessian trace, or ignore the specific
geometric structure of modern Convolutional Neural Networks (CNNs). In this work, we develop a flatness measure that is both exact and architecturally faithful for a broad and practically relevant class of CNNs. We first derive a closed-form expression for the trace of the Hessian of the cross-
entropy loss with respect to convolutional kernels in networks that use global average pooling followed by a linear classifier. Building on this result, we then specialize the notion of relative flatness to convolutional layers and obtain a parameterization-aware flatness measure that properly accounts for the scaling
symmetries and filter interactions induced by convolution and pooling. Finally, we empirically investigate the proposed measure on families of CNNs trained on standard image-classification
benchmarks. The results obtained suggest that the proposed measure can serve as a robust tool to assess and compare the generalization performance of CNN models, and to guide the design of architecture and training choices in practice.
Read the full abstract ▾
Machine Learning
The Coupling Within: Flow Matching via Distilled Normalizing Flows
David Berthelot, Tianrong Chen, Jiatao Gu et al. (+6 more)
Flow models have rapidly become the go-to method for training and deploying large-scale generators, owing their success to inference-time flexibility via adjustable integration steps. A crucial ingredient in flow training is the choice of coupling measure for sampling noise/data pairs that define the flow matching (FM) regression loss. While FM training defaults usually to independent coupling, recent works show that adaptive couplings informed by noise/data distributions (e.g., via optimal transport, OT) improve both model training and inference. We radicalize this insight by shifting the paradigm: rather than computing adaptive couplings directly, we use distilled couplings from a different, pretrained model capable of placing noise and data spaces in bijection – a property intrinsic to normalizing flows (NF) through their maximum likelihood and invertibility requirements. Leveraging recent advances in NF image generation via auto-regressive (AR) blocks, we propose Normalized Flow Matching (NFM), a new method that distills the quasi-deterministic coupling of pretrained NF models to train student flow models. These students achieve the best of both worlds: significantly outperforming flow models trained with independent or even OT couplings, while also improving on the teacher AR-NF model.
Read the full abstract ▾
All authors David Berthelot, Tianrong Chen, Jiatao Gu, Marco Cuturi, Laurent Dinh, Bhavik Chandna, Michal Klein, Josh Susskind, Shuangfei Zhai
Machine Learning · Cross-listed from stat.ML
Statistical Inference via Generative Models: Flow Matching and Causal Inference
Shinto Eguchi
Generative AI has achieved remarkable empirical success, but from the perspective of statistics it often remains opaque: its predictions may be accurate, yet the underlying mechanism is difficult to interpret, analyze, and trust. This book reinterprets generative AI in the
language of statistics, using flow matching as a central example. The key idea is that generative models should be understood not merely as devices for producing plausible data, but as methods for the nonparametric learning of high-dimensional probability distributions. From this viewpoint, missing-data imputation becomes principled sampling from learned conditional distributions, counterfactual analysis becomes the estimation of intervention distributions, and distributional dynamics become statistically analyzable objects. Mathematically, flow matching represents distributional deformation through the continuity equation and a time-dependent velocity field, thereby extending score matching from the learning of static score fields to the learning of transport paths themselves. Building on this foundation, the book develops a statistical framework in which generative models are used to estimate nuisance components while inferential validity is maintained through orthogonalization and cross-fitting in the spirit of double/debiased machine learning. Applications to survival analysis, censoring, missingness, and causal inference show how generative models can be integrated into statistical inference for structured high-dimensional problems.
Read the full abstract ▾