Variational Sparse Paired Autoencoders (vsPAIR) for Inverse Problems and Uncertainty Quantification

• URL: http://arxiv.org/abs/2602.02948v2
• Date: Tue, 10 Feb 2026 18:33:37 GMT
• Title: Variational Sparse Paired Autoencoders (vsPAIR) for Inverse Problems and Uncertainty Quantification
• Authors: Jack Michael Solomon, Rishi Leburu, Matthias Chung,
• Abstract summary: Inverse problems arise when one seeks to reconstruct hidden, underlying quantities from noisy measurements.<n>We propose the Variational Sparse Paired Autoencoder (vsPAIR) to provide fast inference alongside uncertainty estimates.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Inverse problems are fundamental to many scientific and engineering disciplines; they arise when one seeks to reconstruct hidden, underlying quantities from noisy measurements. Many applications demand not just point estimates but interpretable uncertainty. Providing fast inference alongside uncertainty estimates remains challenging yet desirable in numerous applications. We propose the Variational Sparse Paired Autoencoder (vsPAIR) to address this challenge. The architecture pairs a standard VAE encoding observations with a sparse VAE encoding quantities of interest, connected through a learned latent mapping. The variational structure enables uncertainty estimation, the paired architecture encourages interpretability by anchoring QoI representations to clean data, and sparse encodings provide structure by concentrating information into identifiable factors rather than diffusing across all dimensions. To validate the effectiveness of our proposed architecture, we conduct experiments on blind inpainting and computed tomography, demonstrating that vsPAIR is a capable inverse problem solver that can provide interpretable and structured uncertainty estimates.

Related papers

• Task-Awareness Improves LLM Generations and Uncertainty [48.857040212979484]
  Bayes-optimal responses consistently outperform standard decoding methods like beam search.<n>Our decision-theoretic framework is applicable to any problem that admits a latent response structure.
  arXiv  Detail & Related papers  (2026-01-29T10:16:23Z)
• Overcoming Joint Intractability with Lossless Hierarchical Speculative Decoding [58.92526489742584]
  We propose provably lossless.<n> verification method that significantly boosts the expected number of accepted tokens.<n>We show that HSD yields consistent improvements in acceptance rates across diverse model families and benchmarks.
  arXiv  Detail & Related papers  (2026-01-09T11:10:29Z)
• Accelerate Speculative Decoding with Sparse Computation in Verification [49.74839681322316]
  Speculative decoding accelerates autoregressive language model inference by verifying multiple draft tokens in parallel.<n>Existing sparsification methods are designed primarily for standard token-by-token autoregressive decoding.<n>We propose a sparse verification framework that jointly sparsifies attention, FFN, and MoE components during the verification stage to reduce the dominant computation cost.
  arXiv  Detail & Related papers  (2025-12-26T07:53:41Z)
• Multi-Fidelity Delayed Acceptance: hierarchical MCMC sampling for Bayesian inverse problems combining multiple solvers through deep neural networks [0.3499870393443268]
  Inverse uncertainty quantification (UQ) tasks are computationally demanding when dealing with physics-based models.<n>Data-driven surrogate models may help reduce evaluation costs, but their utility is often limited by the expense of generating high-fidelity data.<n>We propose a Multi-Fidelity Delayed Acceptance scheme for Bayesian inverse problems.
  arXiv  Detail & Related papers  (2025-12-18T11:32:16Z)
• Adaptive Evidential Learning for Temporal-Semantic Robustness in Moment Retrieval [39.603000380180774]
  Debiased Evidential Learning for Moment Retrieval (DEMR) is a novel framework that incorporates a Reflective Flipped Fusion (RFF) block for cross-modal alignment.<n>We introduce a Geom-regularizer to refine uncertainty predictions, enabling adaptive alignment with difficult moments and improving retrieval accuracy.
  arXiv  Detail & Related papers  (2025-11-30T16:13:20Z)
• GRADE: Generating multi-hop QA and fine-gRAined Difficulty matrix for RAG Evaluation [5.002953635224383]
  Retrieval-Augmented Generation (RAG) systems are widely adopted in knowledge-intensive NLP tasks.<n>Current evaluations often overlook the structural complexity and multi-step reasoning required in real-world scenarios.<n>We propose textscGRADE, a novel evaluation framework that models task difficulty along two dimensions.
  arXiv  Detail & Related papers  (2025-08-23T11:26:41Z)
• Practical classical error correction for parity-encoded spin systems [0.0]
  A parity-encoding (PE) architecture consists of an expanded spin system with only local connectivity among them.<n>This paper proposes a practical decoding method tailored to correlated spin-flip errors in spin readout of PE architecture.
  arXiv  Detail & Related papers  (2025-02-11T01:31:24Z)
• Alpha-VI DeepONet: A prior-robust variational Bayesian approach for enhancing DeepONets with uncertainty quantification [0.0]
  We introduce a novel deep operator network (DeepONet) framework that incorporates generalised variational inference (GVI) By incorporating Bayesian neural networks as the building blocks for the branch and trunk networks, our framework endows DeepONet with uncertainty quantification. We demonstrate that modifying the variational objective function yields superior results in terms of minimising the mean squared error.
  arXiv  Detail & Related papers  (2024-08-01T16:22:03Z)
• Certainly Uncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness [106.52630978891054]
  We present a taxonomy of uncertainty specific to vision-language AI systems. We also introduce a new metric confidence-weighted accuracy, that is well correlated with both accuracy and calibration error.
  arXiv  Detail & Related papers  (2024-07-02T04:23:54Z)
• QGait: Toward Accurate Quantization for Gait Recognition with Binarized Input [17.017127559393398]
  We propose a differentiable soft quantizer, which better simulates the gradient of the round function during backpropagation. This enables the network to learn from subtle input perturbations. We further refine the training strategy to ensure convergence while simulating quantization errors.
  arXiv  Detail & Related papers  (2024-05-22T17:34:18Z)
• Uncertainty in latent representations of variational autoencoders optimized for visual tasks [3.9504737666460037]
  We investigate the properties of inference in Variational Autoencoders (VAEs)<n>We draw inspiration from classical computer vision to introduce an inductive bias into the VAE.<n>We find that restored inference capabilities are delivered by developing a motif in the inference network.
  arXiv  Detail & Related papers  (2024-04-23T16:26:29Z)
• Goal-oriented Uncertainty Quantification for Inverse Problems via Variational Encoder-Decoder Networks [0.0]
  We describe a new approach that uses variational encoder-decoder (VED) networks for efficient goal-oriented uncertainty quantification for inverse problems. We harness recent advances in machine learning, i.e., VED networks, to describe a data-driven approach to large-scale inverse problems.
  arXiv  Detail & Related papers  (2023-04-17T14:44:59Z)
• Uncertainty Quantification in Medical Image Segmentation with Multi-decoder U-Net [3.961279440272763]
  We exploit the medical image segmentation uncertainty by measuring segmentation performance with multiple annotations in a supervised learning manner. We propose a U-Net based architecture with multiple decoders, where the image representation is encoded with the same encoder, and segmentation referring to each annotation is estimated with multiple decoders. The proposed architecture is trained in an end-to-end manner and able to improve predictive uncertainty estimates.
  arXiv  Detail & Related papers  (2021-09-15T01:46:29Z)
• Hierarchical Variational Autoencoder for Visual Counterfactuals [79.86967775454316]
  Conditional Variational Autos (VAE) are gathering significant attention as an Explainable Artificial Intelligence (XAI) tool. In this paper we show how relaxing the effect of the posterior leads to successful counterfactuals. We introduce VAEX an Hierarchical VAE designed for this approach that can visually audit a classifier in applications.
  arXiv  Detail & Related papers  (2021-02-01T14:07:11Z)
• Towards a Theoretical Understanding of the Robustness of Variational Autoencoders [82.68133908421792]
  We make inroads into understanding the robustness of Variational Autoencoders (VAEs) to adversarial attacks and other input perturbations. We develop a novel criterion for robustness in probabilistic models: $r$-robustness. We show that VAEs trained using disentangling methods score well under our robustness metrics.
  arXiv  Detail & Related papers  (2020-07-14T21:22:29Z)
• NADS: Neural Architecture Distribution Search for Uncertainty Awareness [79.18710225716791]
  Machine learning (ML) systems often encounter Out-of-Distribution (OoD) errors when dealing with testing data coming from a distribution different from training data. Existing OoD detection approaches are prone to errors and even sometimes assign higher likelihoods to OoD samples. We propose Neural Architecture Distribution Search (NADS) to identify common building blocks among all uncertainty-aware architectures.
  arXiv  Detail & Related papers  (2020-06-11T17:39:07Z)

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.