Close Menu
techwavedispatch.com

    Subscribe to Updates

    Get the latest creative news from FooBar about art, design and business.

    What's Hot

    Why Apple Vision Pro Never Took Off Like Meta’s VR Headsets

    November 21, 2026

    towards scalable 2-parameter persistent homology

    November 21, 2026

    The UN fails to agree on rules regulating ‘killer robots’

    November 21, 2026
    Facebook X (Twitter) Instagram
    Trending
    • Why Apple Vision Pro Never Took Off Like Meta’s VR Headsets
    • towards scalable 2-parameter persistent homology
    • The UN fails to agree on rules regulating ‘killer robots’
    • How To Block A Device From Your Home Network
    • [2611.26095] Approximate Adjoint Models for Memory and Compute-Efficient Online Learning of Hybrid Models
    • Anthropic Employee Claims To Have Proven The Most Famous Math Problem Using Claude
    • [2609.39394] Can Computation from Earlier Problems Help LLMs Solve New Ones?
    • Signs It’s Time To Replace Your Phone’s Screen Protector
    Facebook X (Twitter) Instagram
    techwavedispatch.com
    Subscribe
    Saturday, November 21
    • Home
    • AI Tools & Software
    • Machine Learning
    • Generative AI
    • Robotics & Automation
    • Future Tech & Hardware
    • AI in Business
    • Ethics & Regulations
    • More
      • Gadgets & Smart Devices
      • Cybersecurity & AI
      • Tech Breakthroughs
    techwavedispatch.com
    Home»Machine Learning»[2611.26095] Approximate Adjoint Models for Memory and Compute-Efficient Online Learning of Hybrid Models
    Machine Learning

    [2611.26095] Approximate Adjoint Models for Memory and Compute-Efficient Online Learning of Hybrid Models

    adminBy adminNovember 21, 2026No Comments2 Mins Read
    Facebook Twitter Pinterest LinkedIn Tumblr Email
    [2611.26095] Approximate Adjoint Models for Memory and Compute-Efficient Online Learning of Hybrid Models
    Share
    Facebook Twitter LinkedIn Pinterest Email

    [Submitted on 19 Nov 2026]

    View a PDF of the paper titled Approximate Adjoint Models for Memory and Compute-Efficient Online Learning of Hybrid Models, by Emilio Gonz\’alez-Zamora and 3 other authors

    View PDF
    HTML (experimental)

    Abstract:Differentiable programming enables online calibration of numerical models by minimizing errors accumulated along simulated trajectories. This includes estimating physical parameters and training neural sub-models in hybrid configurations. Gradients are typically computed using adjoint methods, or backpropagation through time (BPTT), whose computational and memory costs grow with the length of the training window. This limits the duration and resolution of hybrid-model training, a major bottleneck for realistic geophysical applications. Approaches like truncated BPTT reduces memory use by discarding sensitivities across truncation boundaries, introducing gradient bias and neglecting long-range dependencies. We propose a class of gradient approximation methods that preserve the adjoint recurrence over the full trajectory while approximating only the pullback operators within it. Exact pullbacks are computed by automatic differentiation at sparse anchor states only. Between anchors, sensitivities propagate either through the identity (Zero-order) or through a reused, frozen pullback (Pullback Reuse). This approximation makes the parameter pullback constant within each chunk, allowing the gradient sum to factorize so that a single evaluation per chunk replaces one per time step. We evaluate both on three systems of increasing complexity, an incomplete Lorenz-63 model, a large-eddy closure for two-dimensional quasi-geostrophic turbulence, and bias correction in a multilayer quasi-geostrophic ocean model. Peak memory falls by up to an order of magnitude and runtime up to fourfold, with Pullback Reuse staying closest to the exact gradient direction. In all three cases, approximate gradients support hybrid-model training at comparable accuracy, showing that effective online learning does not require exact gradients.

    Submission history

    From: Emilio González-Zamora [view email]
    [v1]
    Thu, 19 Nov 2026 13:30:55 UTC (4,713 KB)

    Adjoint Approximate ComputeEfficient Hybrid learning Memory Models Online
    Share. Facebook Twitter Pinterest LinkedIn Tumblr Email
    admin
    • Website

    Related Posts

    towards scalable 2-parameter persistent homology

    November 21, 2026

    [2609.39394] Can Computation from Earlier Problems Help LLMs Solve New Ones?

    November 21, 2026

    [2611.26084] RL Can Only Reinforce What It Sees Succeed

    November 21, 2026
    Leave A Reply Cancel Reply

    Top Posts

    NVIDIA Is Investigating Reports That CEO Jensen Huang Was The Target Of Chinese Spy Efforts

    November 8, 202619 Views

    ADIndex: Layer-Adaptive Sparse Attention Indexing via Group-Level Distillation

    November 11, 20265 Views

    Anthropic releases new Mythos and Fable models amid RSI concerns

    November 9, 20265 Views

    Does a Trading Policy Need to Know What It Trades? Microstructure Invariance and Zero-Shot Transfer of Execution Policies

    November 9, 20265 Views
    Don't Miss
    Gadgets & Smart Devices

    Why Apple Vision Pro Never Took Off Like Meta’s VR Headsets

    By adminNovember 21, 20260

    Good hardware doesn’t necessarily make for a successful product. Devindra Hardawar…

    towards scalable 2-parameter persistent homology

    November 21, 2026

    The UN fails to agree on rules regulating ‘killer robots’

    November 21, 2026

    How To Block A Device From Your Home Network

    November 21, 2026
    About Us

    Welcome to TechWave Dispatch

    At TechWave Dispatch, we bring you the latest news, insights, and developments from the ever-evolving world of technology. Our mission is to keep readers informed about the innovations shaping our digital future.

    From artificial intelligence and machine learning to cybersecurity, robotics, smart devices, and groundbreaking technologies, we cover the topics that matter in today's fast-moving tech landscape.

    Our Picks

    Why Apple Vision Pro Never Took Off Like Meta’s VR Headsets

    November 21, 2026

    towards scalable 2-parameter persistent homology

    November 21, 2026

    The UN fails to agree on rules regulating ‘killer robots’

    November 21, 2026
    Most Popular

    After blocking Muse, Amazon now lets users text Alexa to help them shop

    November 6, 20260 Views

    A controlled world for robot learning and evaluation

    November 6, 20260 Views

    Egyptian and Nigerian English join the Open ASR Leaderboard

    November 6, 20260 Views
    Facebook X (Twitter) Instagram Pinterest
    • Terms and Conditions
    • Privacy Policy
    • Contact Us
    • About Us
    © 2026 TechWave Dispatch. All Rights Reserved.

    Type above and press Enter to search. Press Esc to cancel.