Uncertainty Estimation and Generalization Bounds for Modern Deep Learning

• URL: http://arxiv.org/abs/2606.13818v1
• Date: Thu, 11 Jun 2026 18:49:45 GMT
• Title: Uncertainty Estimation and Generalization Bounds for Modern Deep Learning
• Abstract summary: This thesis investigates how Bayesian principles can deepen our understanding of modern deep learning systems.<n>On the methodological side, the thesis introduces the Deep Variational Implicit Process (DVIP)<n>Two post-hoc methods are proposed to equip pretrained networks with uncertainty estimates.
• Score: 1.6582968942719265
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: This thesis investigates how Bayesian principles can deepen our understanding of modern deep learning systems. While neural networks achieve remarkable predictive performance, their ability to generalize and to quantify uncertainty remains only partly understood. This thesis approaches this challenge from both methodological and theoretical angles: unifying Bayesian inference, function-space modeling, and large-deviation theory under a common probabilistic perspective. On the methodological side, the thesis introduces the Deep Variational Implicit Process (DVIP), a scalable Bayesian framework that extends implicit processes to deep architectures. Complementing this, two post-hoc methods -- the Variational Linearized Laplace Approximation (VaLLA) and the Fixed-Mean Gaussian Process (FMGP) -- are proposed to equip pretrained deterministic networks with calibrated uncertainty estimates. The theoretical contributions focus on one of the central open questions in modern machine learning: why do large, over-parameterized neural networks generalize so well? To address this, the thesis develops a unified probabilistic framework that connects three key mechanisms -- diversity, smoothness, and stochasticity -- within the language of PAC-Bayesian and large-deviation theory.

Related papers

• Possibilistic Predictive Uncertainty for Deep Learning [75.00607359322863]
  We introduce Dirichlet-approximated possibilistic posterior predictions (DAPPr)<n>DAPPr is a principled framework leveraging possibility theory.<n>This projection-and-approximation strategy yields a simple training objective with closed-form solutions.
  arXiv  Detail & Related papers  (2026-05-01T12:14:01Z)
• Conjugate Learning Theory: Uncovering the Mechanisms of Trainability and Generalization in Deep Neural Networks [0.0]
  We develop a conjugate learning theoretical framework based on convex conjugate duality to characterize this learnability property.<n>We demonstrate that training deep neural networks (DNNs) with mini-batch descent (SGD) achieves global optima of empirical risk.<n>We derive deterministic and probabilistic bounds on generalization error based on conditional generalized entropy measures.
  arXiv  Detail & Related papers  (2026-02-18T04:26:55Z)
• On the Theoretical Foundation of Sparse Dictionary Learning in Mechanistic Interpretability [5.009082958329585]
  We develop the first unified theoretical framework considering sparse dictionary learning (SDL) as one unified optimization problem.<n>We provide the first theoretical explanations for some empirically observed phenomena, including feature absorption, dead neurons, and the neuron resampling technique.
  arXiv  Detail & Related papers  (2025-12-05T08:47:19Z)
• Bridging the Gap Between Bayesian Deep Learning and Ensemble Weather Forecasts [100.26854618129039]
  Weather forecasting is fundamentally challenged by the chaotic nature of the atmosphere.<n>Recent advances in Bayesian Deep Learning (BDL) offer a promising but often disconnected alternative.<n>We bridge these paradigms through a unified hybrid BDL framework for ensemble weather forecasting.
  arXiv  Detail & Related papers  (2025-11-18T07:49:52Z)
• A Review of Bayesian Uncertainty Quantification in Deep Probabilistic Image Segmentation [0.0]
  This review consolidates and contextualizes foundational concepts in uncertainty modeling.<n>We identify challenges, such as strong assumptions in spatial aggregation and lack of standardized benchmarks.<n>We propose directions for advancing uncertainty-aware segmentation in deep learning.
  arXiv  Detail & Related papers  (2024-11-25T13:26:09Z)
• A Rigorous Link between Deep Ensembles and (Variational) Bayesian Methods [14.845158804951552]
  We establish the first mathematically rigorous link between Bayesian, variational Bayesian, and ensemble methods. On a technical level, our contribution amounts to a generalised variational inference through the lense of Wasserstein flows.
  arXiv  Detail & Related papers  (2023-05-24T11:13:59Z)
• Variational Bayes Deep Operator Network: A data-driven Bayesian solver for parametric differential equations [0.0]
  We propose Variational Bayes DeepONet (VB-DeepONet) for operator learning. VB-DeepONet uses variational inference to take into account high dimensional posterior distributions.
  arXiv  Detail & Related papers  (2022-06-12T04:20:11Z)
• The Unreasonable Effectiveness of Deep Evidential Regression [72.30888739450343]
  A new approach with uncertainty-aware regression-based neural networks (NNs) shows promise over traditional deterministic methods and typical Bayesian NNs. We detail the theoretical shortcomings and analyze the performance on synthetic and real-world data sets, showing that Deep Evidential Regression is a quantification rather than an exact uncertainty.
  arXiv  Detail & Related papers  (2022-05-20T10:10:32Z)
• Unified Field Theory for Deep and Recurrent Neural Networks [56.735884560668985]
  We present a unified and systematic derivation of the mean-field theory for both recurrent and deep networks. We find that convergence towards the mean-field theory is typically slower for recurrent networks than for deep networks. Our method exposes that Gaussian processes are but the lowest order of a systematic expansion in $1/n$.
  arXiv  Detail & Related papers  (2021-12-10T15:06:11Z)
• Multivariate Deep Evidential Regression [77.34726150561087]
  A new approach with uncertainty-aware neural networks shows promise over traditional deterministic methods. We discuss three issues with a proposed solution to extract aleatoric and epistemic uncertainties from regression-based neural networks.
  arXiv  Detail & Related papers  (2021-04-13T12:20:18Z)
• Efficient Variational Inference for Sparse Deep Learning with Theoretical Guarantee [20.294908538266867]
  Sparse deep learning aims to address the challenge of huge storage consumption by deep neural networks. In this paper, we train sparse deep neural networks with a fully Bayesian treatment under spike-and-slab priors. We develop a set of computationally efficient variational inferences via continuous relaxation of Bernoulli distribution.
  arXiv  Detail & Related papers  (2020-11-15T03:27:54Z)
• A Chain Graph Interpretation of Real-World Neural Networks [58.78692706974121]
  We propose an alternative interpretation that identifies NNs as chain graphs (CGs) and feed-forward as an approximate inference procedure. The CG interpretation specifies the nature of each NN component within the rich theoretical framework of probabilistic graphical models. We demonstrate with concrete examples that the CG interpretation can provide novel theoretical support and insights for various NN techniques.
  arXiv  Detail & Related papers  (2020-06-30T14:46:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.