arXiv subjects

Marius Kloft

Publications and source records attributed to Marius Kloft.

At least 19 recordsLinked to original sources

arXiv2026

Minimax-Optimal Generalization Bounds for Smooth Deep Neural Networks Trained by (Stochastic) Gradient Descent

Characterizing the optimization dynamics and statistical performance of over-parameterized deep neural networks (DNNs) remains a central challenge in understanding the remarkable success of deep learning. We establish quantitative bounds showing that kernel gradient descent in the reproducing kernel Hilbert space induced by the deterministic infinite-width neural tangent kernel approximates finite-width deep regression with smooth activations under gradient descent (GD) and stochastic gradient descent (SGD) training. The approximation gap is governed by the network width and training horizon, with an additional stochastic gradient error in the SGD case. This connection provides a general mechanism for transferring learning-theoretic guarantees from kernel methods to deep regression. As an application, under general source and effective dimension conditions, we show that both GD- and SGD-trained DNNs attain the minimax-optimal excess population risk rate, up to logarithmic factors, provided that the network width grows polynomially in the sample size. To the best of our knowledge, these are the first such guarantees for standard fully connected deep neural networks with smooth activations trained by GD and SGD.

stat.ML↗

arXiv2026

Population Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise

We establish the first population risk bounds for Kolmogorov-Arnold Networks (KANs) trained by mini-batch SGD with gradient clipping, covering non-private SGD as well as differentially private SGD (DP-SGD) with Gaussian perturbations that interpolate between independent and temporally correlated noise. This setting is substantially closer to practice than prior KAN theory along two axes: training is by mini-batch SGD, the standard recipe for modern networks, rather than full-batch gradient descent (GD); and correlated-noise mechanisms have empirically shown a more favorable privacy-utility tradeoff than independent-noise mechanisms. Our results cover the corresponding full-batch GD and independent-noise DP-GD results for KANs by Wang et al. (2026), while yielding sharper fixed-second-layer specializations. The technical core is a new analysis route for correlated-noise DP training in the non-convex regime. Temporal dependence breaks the conditional-centering structure underlying standard one-step SGD arguments, and the projection step obstructs the exact cancellation structure of correlated perturbations. We address these difficulties through an auxiliary unprojected dynamics, a shifted iterate that absorbs the current noise perturbation, and a high-probability bootstrap certifying projection inactivity. Combining this optimization analysis with a stability-based generalization argument yields the stated population risk bounds. To the best of our knowledge, this is the first optimization and population risk analysis of a correlated-noise mechanism for DP training beyond convex learning, in particular for neural networks.

cs.LG↗

arXiv2026

Skipping the Zeros in Diffusion Models for Sparse Data Generation

Diffusion models (DMs) excel on dense continuous data, but are not designed for sparse continuous data. They do not model exact zeros that represent the deliberate absence of a signal. As a result, they erase sparsity patterns and perform unnecessary computation on mostly zero entries. With Sparsity-Exploiting Diffusion (SED), we model only non-zero values, preserving sparsity. SED delivers computational savings while maintaining or improving generation quality by skipping zeros during training and inference. Across physics and biology benchmarks, SED matches or surpasses conventional DMs and domain-specific baselines, while vision experiments provide intuitive insights into the limitations of dense DMs and the benefits of SED.

cs.LG↗

arXiv2026

Structurally Separated Uncertainty in Supervised Latent Variable Models

Predictive uncertainty is commonly decomposed into epistemic and aleatoric components, but standard decompositions often produce strongly correlated estimates because both quantities are derived from the same predictive distribution. We study an alternative design principle, \emph{structural separation}, which assigns epistemic and aleatoric uncertainty to disjoint parameter paths trained with distinct supervision targets: reducible prediction error for epistemic uncertainty and persistent label ambiguity for aleatoric uncertainty. We instantiate this principle in two supervised latent-variable models, a Credal Concept Bottleneck Model and a credal Self-Explaining Neural Network, and prove a gradient-isolation result showing that the two uncertainty heads are not coupled through shared training gradients under the proposed parameterization. Across five ambiguity-aware benchmarks, structural separation substantially reduces epistemic-aleatoric correlation while preserving predictive performance. Further analyses show that aleatoric estimates track annotator- or corpus-derived ambiguity, while epistemic estimates are more sensitive to prediction error and data availability. These results suggest that supervised latent-variable architectures provide a practical route toward uncertainty estimates that are not merely decorrelated, but operationally distinguishable.

cs.LG↗

arXiv2026

Optimization, Generalization and Differential Privacy Bounds for Gradient Descent on Kolmogorov-Arnold Networks

Kolmogorov--Arnold Networks (KANs) have recently emerged as a structured alternative to standard MLPs, yet a principled theory for their training dynamics, generalization, and privacy properties remains limited. In this paper, we analyze gradient descent (GD) for training two-layer KANs and derive general bounds that characterize their training dynamics, generalization, and utility under differential privacy (DP). As a concrete instantiation, we specialize our analysis to logistic loss under an NTK-separable assumption, where we show that polylogarithmic network width suffices for GD to achieve an optimization rate of order $1/T$ and a generalization rate of order $1/n$, with $T$ denoting the number of GD iterations and $n$ the sample size. In the private setting, we characterize the noise required for $(\epsilon,\delta)$-DP and obtain a utility bound of order $\sqrt{d}/(n\epsilon)$ (with $d$ the input dimension), matching the classical lower bound for general convex Lipschitz problems. Our results imply that polylogarithmic width is not only sufficient but also necessary under differential privacy, revealing a qualitative gap between non-private (sufficiency only) and private (necessity also emerges) training regimes. Experiments further illustrate how these theoretical insights can guide practical choices, including network width selection and early stopping.

cs.LG↗

arXiv2025

Formally Exploring Time-Series Anomaly Detection Evaluation Metrics

Undetected anomalies in time series can trigger catastrophic failures in safety-critical systems, such as chemical plant explosions or power grid outages. Although many detection methods have been proposed, their performance remains unclear because current metrics capture only narrow aspects of the task and often yield misleading results. We address this issue by introducing verifiable properties that formalize essential requirements for evaluating time-series anomaly detection. These properties enable a theoretical framework that supports principled evaluations and reliable comparisons. Analyzing 37 widely used metrics, we show that most satisfy only a few properties, and none satisfy all, explaining persistent inconsistencies in prior results. To close this gap, we propose LARM, a flexible metric that provably satisfies all properties, and extend it to ALARM, an advanced variant meeting stricter requirements.

cs.LG↗

arXiv2025

DiffStyleTS: Diffusion Model for Style Transfer in Time Series

Style transfer combines the content of one signal with the style of another. It supports applications such as data augmentation and scenario simulation, helping machine learning models generalize in data-scarce domains. While well developed in vision and language, style transfer methods for time series data remain limited. We introduce DiffTSST, a diffusion-based framework that disentangles a time series into content and style representations via convolutional encoders and recombines them through a self-supervised attention-based diffusion process. At inference, encoders extract content and style from two distinct series, enabling conditional generation of novel samples to achieve style transfer. We demonstrate both qualitatively and quantitatively that DiffTSST achieves effective style transfer. We further validate its real-world utility by showing that data augmentation with DiffTSST improves anomaly detection in data-scarce regimes.

cs.LG↗

arXiv2025

PIANO: Physics Informed Autoregressive Network

Solving time-dependent partial differential equations (PDEs) is fundamental to modeling critical phenomena across science and engineering. Physics-Informed Neural Networks (PINNs) solve PDEs using deep learning. However, PINNs perform pointwise predictions that neglect the autoregressive property of dynamical systems, leading to instabilities and inaccurate predictions. We introduce Physics-Informed Autoregressive Networks (PIANO) -- a framework that redesigns PINNs to model dynamical systems. PIANO operates autoregressively, explicitly conditioning future predictions on the past. It is trained through a self-supervised rollout mechanism while enforcing physical constraints. We present a rigorous theoretical analysis demonstrating that PINNs suffer from temporal instability, while PIANO achieves stability through autoregressive modeling. Extensive experiments on challenging time-dependent PDEs demonstrate that PIANO achieves state-of-the-art performance, significantly improving accuracy and stability over existing methods. We further show that PIANO outperforms existing methods in weather forecasting.

cs.LG↗

arXiv2025

Continual Neural Topic Model

In continual learning, our aim is to learn a new task without forgetting what was learned previously. In topic models, this translates to learning new topic models without forgetting previously learned topics. Previous work either considered Dynamic Topic Models (DTMs), which learn the evolution of topics based on the entire training corpus at once, or Online Topic Models, which are updated continuously based on new data but do not have long-term memory. To fill this gap, we propose the Continual Neural Topic Model (CoNTM), which continuously learns topic models at subsequent time steps without forgetting what was previously learned. This is achieved using a global prior distribution that is continuously updated. In our experiments, CoNTM consistently outperformed the dynamic topic model in terms of topic quality and predictive perplexity while being able to capture topic changes online. The analysis reveals that CoNTM can learn more diverse topics and better capture temporal changes than existing methods.

cs.LG↗

arXiv2025

Multi-level Supervised Contrastive Learning

Contrastive learning is a well-established paradigm in representation learning. The standard framework of contrastive learning minimizes the distance between "similar" instances and maximizes the distance between dissimilar ones in the projection space, disregarding the various aspects of similarity that can exist between two samples. Current methods rely on a single projection head, which fails to capture the full complexity of different aspects of a sample, leading to suboptimal performance, especially in scenarios with limited training data. In this paper, we present a novel supervised contrastive learning method in a unified framework called multilevel contrastive learning (MLCL), that can be applied to both multi-label and hierarchical classification tasks. The key strength of the proposed method is the ability to capture similarities between samples across different labels and/or hierarchies using multiple projection heads. Extensive experiments on text and image datasets demonstrate that the proposed approach outperforms state-of-the-art contrastive learning methods

cs.LG↗

arXiv2025

Sparse Data Diffusion for Scientific Simulations in Biology and Physics

Sparse data is fundamental to scientific simulations in biology and physics, from single-cell gene expression to particle calorimetry, where exact zeros encode physical absence rather than weak signal. However, existing diffusion models lack the physical rigor to faithfully represent this sparsity. This work introduces Sparse Data Diffusion (SDD), a generative method that explicitly models exact zeros via Sparsity Bits, unifying efficient ML generation with physically grounded sparsity handling. Empirical validation in particle physics and single-cell biology demonstrates that SDD achieves higher fidelity than baseline methods in capturing sparse patterns critical for scientific analysis, advancing scalable and physically faithful simulation.

cs.LG↗

arXiv2025

Challenging Assumptions in Learning Generic Text Style Embeddings

Recent advancements in language representation learning primarily emphasize language modeling for deriving meaningful representations, often neglecting style-specific considerations. This study addresses this gap by creating generic, sentence-level style embeddings crucial for style-centric tasks. Our approach is grounded on the premise that low-level text style changes can compose any high-level style. We hypothesize that applying this concept to representation learning enables the development of versatile text style embeddings. By fine-tuning a general-purpose text encoder using contrastive learning and standard cross-entropy loss, we aim to capture these low-level style shifts, anticipating that they offer insights applicable to high-level text styles. The outcomes prompt us to reconsider the underlying assumptions as the results do not always show that the learned style representations capture high-level text styles.

cs.LG↗

arXiv2024

Towards Graph Foundation Models: A Study on the Generalization of Positional and Structural Encodings

Recent advances in integrating positional and structural encodings (PSEs) into graph neural networks (GNNs) have significantly enhanced their performance across various graph learning tasks. However, the general applicability of these encodings and their potential to serve as foundational representations for graphs remain uncertain. This paper investigates the fine-tuning efficiency, scalability with sample size, and generalization capability of learnable PSEs across diverse graph datasets. Specifically, we evaluate their potential as universal pre-trained models that can be easily adapted to new tasks with minimal fine-tuning and limited data. Furthermore, we assess the expressivity of the learned representations, particularly, when used to augment downstream GNNs. We demonstrate through extensive benchmarking and empirical analysis that PSEs generally enhance downstream models. However, some datasets may require specific PSE-augmentations to achieve optimal performance. Nevertheless, our findings highlight their significant potential to become integral components of future graph foundation models. We provide new insights into the strengths and limitations of PSEs, contributing to the broader discourse on foundation models in graph learning.

cs.LG↗

arXiv2024

SetPINNs: Set-based Physics-informed Neural Networks

Physics-Informed Neural Networks (PINNs) solve partial differential equations using deep learning. However, conventional PINNs perform pointwise predictions that neglect dependencies within a domain, which may result in suboptimal solutions. We introduce SetPINNs, a framework that effectively captures local dependencies. With a finite element-inspired sampling scheme, we partition the domain into sets to model local dependencies while simultaneously enforcing physical laws. We provide a rigorous theoretical analysis showing that SetPINNs yield unbiased, lower-variance estimates of residual energy and its gradients, ensuring improved domain coverage and reduced residual error. Extensive experiments on synthetic and real-world tasks show improved accuracy, efficiency, and robustness.

cs.LG↗

arXiv2024

Comgra: A Tool for Analyzing and Debugging Neural Networks

Neural Networks are notoriously difficult to inspect. We introduce comgra, an open source python library for use with PyTorch. Comgra extracts data about the internal activations of a model and organizes it in a GUI (graphical user interface). It can show both summary statistics and individual data points, compare early and late stages of training, focus on individual samples of interest, and visualize the flow of the gradient through the network. This makes it possible to inspect the model's behavior from many different angles and save time by rapidly testing different hypotheses without having to rerun it. Comgra has applications for debugging, neural architecture design, and mechanistic interpretability. We publish our library through Python Package Index (PyPI) and provide code, documentation, and tutorials at https://github.com/FlorianDietz/comgra.

cs.LG↗

arXiv2024

Anomaly Detection of Tabular Data Using LLMs

Large language models (LLMs) have shown their potential in long-context understanding and mathematical reasoning. In this paper, we study the problem of using LLMs to detect tabular anomalies and show that pre-trained LLMs are zero-shot batch-level anomaly detectors. That is, without extra distribution-specific model fitting, they can discover hidden outliers in a batch of data, demonstrating their ability to identify low-density data regions. For LLMs that are not well aligned with anomaly detection and frequently output factual errors, we apply simple yet effective data-generating processes to simulate synthetic batch-level anomaly detection datasets and propose an end-to-end fine-tuning strategy to bring out the potential of LLMs in detecting real anomalies. Experiments on a large anomaly detection benchmark (ODDS) showcase i) GPT-4 has on-par performance with the state-of-the-art transductive learning-based anomaly detection methods and ii) the efficacy of our synthetic dataset and fine-tuning strategy in aligning LLMs to this task.

cs.LG↗

arXiv2024

AI-based Anomaly Detection for Clinical-Grade Histopathological Diagnostics

While previous studies have demonstrated the potential of AI to diagnose diseases in imaging data, clinical implementation is still lagging behind. This is partly because AI models require training with large numbers of examples only available for common diseases. In clinical reality, however, only few diseases are common, whereas the majority of diseases are less frequent (long-tail distribution). Current AI models overlook or misclassify these diseases. We propose a deep anomaly detection approach that only requires training data from common diseases to detect also all less frequent diseases. We collected two large real-world datasets of gastrointestinal biopsies, which are prototypical of the problem. Herein, the ten most common findings account for approximately 90% of cases, whereas the remaining 10% contained 56 disease entities, including many cancers. 17 million histological images from 5,423 cases were used for training and evaluation. Without any specific training for the diseases, our best-performing model reliably detected a broad spectrum of infrequent ("anomalous") pathologies with 95.0% (stomach) and 91.0% (colon) AUROC and generalized across scanners and hospitals. By design, the proposed anomaly detection can be expected to detect any pathological alteration in the diagnostic tail of gastrointestinal biopsies, including rare primary or metastatic cancers. This study establishes the first effective clinical application of AI-based anomaly detection in histopathology that can flag anomalous cases, facilitate case prioritization, reduce missed diagnoses and enhance the general safety of AI models, thereby driving AI adoption and automation in routine diagnostics and beyond.

cs.AI↗

arXiv2024

Interpretable Tensor Fusion

Conventional machine learning methods are predominantly designed to predict outcomes based on a single data type. However, practical applications may encompass data of diverse types, such as text, images, and audio. We introduce interpretable tensor fusion (InTense), a multimodal learning method for training neural networks to simultaneously learn multimodal data representations and their interpretable fusion. InTense can separately capture both linear combinations and multiplicative interactions of diverse data types, thereby disentangling higher-order interactions from the individual effects of each modality. InTense provides interpretability out of the box by assigning relevance scores to modalities and their associations. The approach is theoretically grounded and yields meaningful relevance scores on multiple synthetic and real-world datasets. Experiments on six real-world datasets show that InTense outperforms existing state-of-the-art multimodal interpretable approaches in terms of accuracy and interpretability.

cs.LG↗