Navigating the Noise: Bringing Clarity to ML Parameterization Design with O(100) Ensembles

• URL: http://arxiv.org/abs/2309.16177v3
• Date: Wed, 18 Dec 2024 00:27:15 GMT
• Title: Navigating the Noise: Bringing Clarity to ML Parameterization Design with O(100) Ensembles
• Abstract summary: Machine-learning (ML) parameterizations of subgrid processes may one day replace conventional parameterizations.<n>Uncertainty about the relationship between offline and online performance hinders their development.<n>We show how systematic reductions in offline error manifest in changes to online error and online stability.
• Score: 1.9199275795132604
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine-learning (ML) parameterizations of subgrid processes (here of turbulence, convection, and radiation) may one day replace conventional parameterizations by emulating high-resolution physics without the cost of explicit simulation. However, uncertainty about the relationship between offline and online performance (i.e., when integrated with a large-scale general circulation model (GCM)) hinders their development. Much of this uncertainty stems from limited sampling of the noisy, emergent effects of upstream ML design decisions on downstream online hybrid simulation. Our work rectifies the sampling issue via the construction of a semi-automated, end-to-end pipeline for $\mathcal{O}(100)$ size ensembles of hybrid simulations, revealing important nuances in how systematic reductions in offline error manifest in changes to online error and online stability. For example, removing dropout and switching from a Mean Squared Error (MSE) to a Mean Absolute Error (MAE) loss both reduce offline error, but they have opposite effects on online error and online stability. Other design decisions, like incorporating memory, converting moisture input from specific humidity to relative humidity, using batch normalization, and training on multiple climates do not come with any such compromises. Finally, we show that ensemble sizes of $\mathcal{O}(100)$ may be necessary to reliably detect causally relevant differences online. By enabling rapid online experimentation at scale, we can empirically settle debates regarding subgrid ML parameterization design that would have otherwise remained unresolved in the noise.

Related papers

• Sparse MLLM Anchors, Dense Adaptation: Breaking the Self-Referential Loop in Wild Test-Time Adaptation [17.055807559866093]
  We introduce MASA (Multimodal-LLM-Anchored Semantic Adaptation), which complements model-internal evidence with structured semantic descriptions from a frozen large language model (MLLM)<n> MASA encodes descriptions, propagates them to neighboring test samples, and stores the resulting visual-semantic information in an online prototype memory.<n>We evaluate MASA on the WTTA ImageNet-C benchmark under limited-batch, mixed-domain, and imbalanced-label-shift settings with ResNet and ViT backbones.
  arXiv  Detail & Related papers  (2026-09-15T11:48:30Z)
• Closed-Form Spectral Regularization for Multi-Task Model Merging [96.82449201305234]
  Model merging combines several independently fine-tuned experts into a single multi-task model without any training data.<n>State-of-the-art merging methods formulate merging as a layer-wise interference problem.<n>We propose SWUDI, a closed-form method that combines a soft exponential filter, which matches the gradient-flow trajectory of iterative descent.
  arXiv  Detail & Related papers  (2026-06-05T14:00:47Z)
• When Model Merging Breaks Routing: Training-Free Calibration for MoE [67.27839627141972]
  Hessian-Aware Router (HARC) is a training-free framework that leverages second-order curvature information to realign the merged router.<n> Experiments on mathematical reasoning and code generation tasks show that HARC effectively mitigates routing breakdown across diverse MoE merging baselines.
  arXiv  Detail & Related papers  (2026-06-02T09:33:33Z)
• Self-Calibrating LLM-Based Analog Circuit Sizing with Interpretable Design Equations [0.0]
  We present a self-calibrating framework for analog circuit sizing.<n>A large language model (LLM) derives topology-specific analytical design equations directly from a raw circuit netlist.<n>A deterministic calibration loop extracts process-dependent parameters from a single transistor-level simulation.
  arXiv  Detail & Related papers  (2026-04-08T04:35:25Z)
• AE-ViT: Stable Long-Horizon Parametric Partial Differential Equations Modeling [0.0]
  We propose a joint model consisting of a convolutional encoder, a transformer operating on latent representations, and a decoder for reconstruction.<n>Our approach combines the efficiency of latent evolution with the fidelity of full-field models, outperforming DL-ROMs, latent transformers, and plain ViTs in multi-field prediction.
  arXiv  Detail & Related papers  (2026-04-07T21:19:45Z)
• LLM-Generated Fault Scenarios for Evaluating Perception-Driven Lane Following in Autonomous Edge Systems [0.5046831208137847]
  We introduce a decoupled offline-online fault injection framework for autonomous vision systems on edge devices.<n>This architecture separates the validation process into two distinct phases: a computationally intensive Offline Phase and a lightweight Online Phase.<n>We extensively validated this framework on a ResNet18 lane-following model across 460 fault scenarios.
  arXiv  Detail & Related papers  (2026-04-01T09:27:46Z)
• Sample Margin-Aware Recalibration of Temperature Scaling [20.87493013833571]
  Recent advances in deep learning have significantly improved predictive accuracy.<n>Modern neural networks remain systematically overconfident, posing risks for deployment in safety-critical scenarios.<n>We propose a lightweight, data-efficient recalibration method that precisely scales logits based on the margin between the top two logits.
  arXiv  Detail & Related papers  (2025-06-30T03:35:05Z)
• Decentralized Nonconvex Composite Federated Learning with Gradient Tracking and Momentum [78.27945336558987]
  Decentralized server (DFL) eliminates reliance on client-client architecture. Non-smooth regularization is often incorporated into machine learning tasks. We propose a novel novel DNCFL algorithm to solve these problems.
  arXiv  Detail & Related papers  (2025-04-17T08:32:25Z)
• A Two-step Linear Mixing Model for Unmixing under Hyperspectral Variability [1.6061490167492505]
  Spectral unmixing is an important task in the research field of hyperspectral image processing. The Linear Mixing Model has received an attention due to its simplicity and ease of use. We show that the model is competitive and in some cases superior to existing well-established unmixing methods.
  arXiv  Detail & Related papers  (2025-02-24T14:44:40Z)
• SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models [85.67096251281191]
  We present an innovative approach to model fusion called zero-shot Sparse MIxture of Low-rank Experts (SMILE) construction. SMILE allows for the upscaling of source models into an MoE model without extra data or further training. We conduct extensive experiments across diverse scenarios, such as image classification and text generation tasks, using full fine-tuning and LoRA fine-tuning.
  arXiv  Detail & Related papers  (2024-08-19T17:32:15Z)
• Beyond Closure Models: Learning Chaotic-Systems via Physics-Informed Neural Operators [78.64101336150419]
  Predicting the long-term behavior of chaotic systems is crucial for various applications such as climate modeling. An alternative approach to such a full-resolved simulation is using a coarse grid and then correcting its errors through a temporalittext model. We propose an alternative end-to-end learning approach using a physics-informed neural operator (PINO) that overcomes this limitation.
  arXiv  Detail & Related papers  (2024-08-09T17:05:45Z)
• Towards Physically Consistent Deep Learning For Climate Model Parameterizations [46.07009109585047]
  parameterizations are a major source of systematic errors and large uncertainties in climate projections. Deep learning (DL)-based parameterizations, trained on data from computationally expensive short, high-resolution simulations, have shown great promise for improving climate models. We propose an efficient supervised learning framework for DL-based parameterizations that leads to physically consistent models.
  arXiv  Detail & Related papers  (2024-06-06T10:02:49Z)
• Dynamic Deep Learning Based Super-Resolution For The Shallow Water Equations [0.4188114563181614]
  We demonstrate that a simulation with a 20km resolution that is frequently corrected by a U-net-type neural network can achieve discretization errors of a simulation with 10km resolution. The network, originally developed for image-based super-resolution in post-processing, is trained to compute the difference between solutions on both meshes.
  arXiv  Detail & Related papers  (2024-04-09T15:46:00Z)
• Joint Parameter and Parameterization Inference with Uncertainty Quantification through Differentiable Programming [0.20530463088872453]
  We introduce a novel framework for the joint estimation of physical parameters and machine learning parameterizations with uncertainty quantification. Our framework incorporates online training and efficient Bayesian inference within a high-dimensional parameter space, facilitated by differentiable programming.
  arXiv  Detail & Related papers  (2024-03-04T17:02:23Z)
• Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation [56.79064699832383]
  We establish a Cloud-Edge Elastic Model Adaptation (CEMA) paradigm in which the edge models only need to perform forward propagation. In our CEMA, to reduce the communication burden, we devise two criteria to exclude unnecessary samples from uploading to the cloud.
  arXiv  Detail & Related papers  (2024-02-27T08:47:19Z)
• ClimSim-Online: A Large Multi-scale Dataset and Framework for Hybrid ML-physics Climate Emulation [45.201929285600606]
  We present ClimSim-Online, which includes an end-to-end workflow for developing hybrid ML-physics simulators. The dataset is global and spans ten years at a high sampling frequency. We provide a cross-platform, containerized pipeline to integrate ML models into operational climate simulators.
  arXiv  Detail & Related papers  (2023-06-14T21:26:31Z)
• Environment Transformer and Policy Optimization for Model-Based Offline Reinforcement Learning [25.684201757101267]
  We propose an uncertainty-aware sequence modeling architecture called Environment Transformer. Benefiting from the accurate modeling of the transition dynamics and reward function, Environment Transformer can be combined with arbitrary planning, dynamics programming, or policy optimization algorithms for offline RL.
  arXiv  Detail & Related papers  (2023-03-07T11:26:09Z)
• Online Probabilistic Model Identification using Adaptive Recursive MCMC [8.465242072268019]
  We suggest the Adaptive Recursive Markov Chain Monte Carlo (ARMCMC) method. It eliminates the shortcomings of conventional online techniques while computing the entire probability density function of model parameters. We demonstrate our approach using parameter estimation in a soft bending actuator and the Hunt-Crossley dynamic model.
  arXiv  Detail & Related papers  (2022-10-23T02:06:48Z)
• Fast and Accurate Error Simulation for CNNs against Soft Errors [64.54260986994163]
  We present a framework for the reliability analysis of Conal Neural Networks (CNNs) via an error simulation engine. These error models are defined based on the corruption patterns of the output of the CNN operators induced by faults. We show that our methodology achieves about 99% accuracy of the fault effects w.r.t. SASSIFI, and a speedup ranging from 44x up to 63x w.r.t.FI, that only implements a limited set of error models.
  arXiv  Detail & Related papers  (2022-06-04T19:45:02Z)
• Hierarchical model reduction driven by machine learning for parametric advection-diffusion-reaction problems in the presence of noisy data [0.0]
  We propose a new approach to generate a reliable reduced model for a parametric elliptic problem in the presence of noisy data. We show that directional HiPOD looses in terms of accuracy when problem data are affected by noise. We replace with Machine Learning fitting models which better discriminate relevant physical features in the data from irrelevant noise.
  arXiv  Detail & Related papers  (2022-04-01T16:02:05Z)
• Real-time simulation of parameter-dependent fluid flows through deep learning-based reduced order models [0.2538209532048866]
  Reduced order models (ROMs) provide reliable approximations to parameter-dependent fluid dynamics problems in rapid times. Deep learning (DL)-based ROMs overcome all these limitations by learning in a non-intrusive way both the nonlinear trial manifold and the reduced dynamics. The resulting POD-DL-ROMs are shown to provide accurate results in almost real-time for the flow around a cylinder benchmark, the fluid-structure interaction between an elastic beam attached to a fixed, rigid block and a laminar incompressible flow, and the blood flow in a cerebral aneurysm.
  arXiv  Detail & Related papers  (2021-06-10T13:07:33Z)
• Bridging the Gap Between Clean Data Training and Real-World Inference for Spoken Language Understanding [76.89426311082927]
  Existing models are trained on clean data, which causes a textitgap between clean data training and real-world inference. We propose a method from the perspective of domain adaptation, by which both high- and low-quality samples are embedding into similar vector space. Experiments on the widely-used dataset, Snips, and large scale in-house dataset (10 million training examples) demonstrate that this method not only outperforms the baseline models on real-world (noisy) corpus but also enhances the robustness, that is, it produces high-quality results under a noisy environment.
  arXiv  Detail & Related papers  (2021-04-13T17:54:33Z)
• Edge Federated Learning Via Unit-Modulus Over-The-Air Computation (Extended Version) [64.76619508293966]
  This paper proposes a unit-modulus over-the-air computation (UM-AirComp) framework to facilitate efficient edge federated learning. It uploads simultaneously local model parameters and updates global model parameters via analog beamforming. We demonstrate the implementation of UM-AirComp in a vehicle-to-everything autonomous driving simulation platform.
  arXiv  Detail & Related papers  (2021-01-28T15:10:22Z)
• Identification of Probability weighted ARX models with arbitrary domains [75.91002178647165]
  PieceWise Affine models guarantees universal approximation, local linearity and equivalence to other classes of hybrid system. In this work, we focus on the identification of PieceWise Auto Regressive with eXogenous input models with arbitrary regions (NPWARX) The architecture is conceived following the Mixture of Expert concept, developed within the machine learning field.
  arXiv  Detail & Related papers  (2020-09-29T12:50:33Z)
• Optimization-driven Machine Learning for Intelligent Reflecting Surfaces Assisted Wireless Networks [82.33619654835348]
  Intelligent surface (IRS) has been employed to reshape the wireless channels by controlling individual scattering elements' phase shifts. Due to the large size of scattering elements, the passive beamforming is typically challenged by the high computational complexity. In this article, we focus on machine learning (ML) approaches for performance in IRS-assisted wireless networks.
  arXiv  Detail & Related papers  (2020-08-29T08:39:43Z)

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.