Close Menu
techwavedispatch.com

    Subscribe to Updates

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

    What's Hot

    Total Wireless Promo Codes & Deals: 50% Off Select Plans

    November 21, 2026

    [2505.14240] Learning with Local Search MCMC Layers

    November 21, 2026

    Therabody Promo Codes: 15% Off November 2026

    November 21, 2026
    Facebook X (Twitter) Instagram
    Trending
    • Total Wireless Promo Codes & Deals: 50% Off Select Plans
    • [2505.14240] Learning with Local Search MCMC Layers
    • Therabody Promo Codes: 15% Off November 2026
    • Deviations from the NTK Regime in CNNs under Joint Depth-Width Scaling
    • Mountain Hardwear Coupon Code 15% Off November
    • [2212.06123] Security of Deep Reinforcement Learning for Autonomous Driving: A Survey
    • 20% Off Brooks Promo Code | November 2026
    • A PDE-structured transport operator with shared implicit updates for multiscale CDR systems
    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»[2505.14240] Learning with Local Search MCMC Layers
    Machine Learning

    [2505.14240] Learning with Local Search MCMC Layers

    adminBy adminNovember 21, 2026No Comments2 Mins Read
    Facebook Twitter Pinterest LinkedIn Tumblr Email
    [2505.14240] Learning with Local Search MCMC Layers
    Share
    Facebook Twitter LinkedIn Pinterest Email

    [Submitted on 20 May 2025 (v1), last revised 19 Nov 2026 (this version, v4)]

    View a PDF of the paper titled Learning with Local Search MCMC Layers, by Germain Vivier-Ardisson and 2 other authors

    View PDF
    HTML (experimental)

    Abstract:Integrating combinatorial optimization layers into neural networks has recently attracted significant research interest. However, many existing approaches lack theoretical guarantees or fail to perform adequately when relying on inexact solvers. This is a critical limitation, as many operations research problems are NP-hard, often necessitating the use of neighborhood-based local search heuristics. In this paper, we introduce a principled approach for learning with such inexact solvers. Inspired by the connection between simulated annealing and Metropolis-Hastings, we transform the problem specific neighborhood systems used in local search heuristics into proposal distributions, implementing MCMC on the set of feasible solutions. This allows us to construct differentiable, stochastic combinatorial layers and associated loss functions. Replacing an exact solver with a local search strongly reduces the computational burden of learning on many applications. We demonstrate our approach on a dynamic vehicle routing problem with time windows, binary vector and k-subset prediction tasks, as well as a multi-dimensional knapsack decision-focused learning problem.

    Submission history

    From: Germain Vivier-Ardisson [view email]
    [v1]
    Tue, 20 May 2025 11:47:42 UTC (7,309 KB)
    [v2]
    Mon, 29 Sep 2025 09:05:00 UTC (7,349 KB)
    [v3]
    Mon, 24 Aug 2026 13:16:28 UTC (7,413 KB)
    [v4]
    Thu, 19 Nov 2026 14:10:01 UTC (7,419 KB)

    layers learning Local MCMC search
    Share. Facebook Twitter Pinterest LinkedIn Tumblr Email
    admin
    • Website

    Related Posts

    Deviations from the NTK Regime in CNNs under Joint Depth-Width Scaling

    November 21, 2026

    [2212.06123] Security of Deep Reinforcement Learning for Autonomous Driving: A Survey

    November 21, 2026

    A PDE-structured transport operator with shared implicit updates for multiscale CDR systems

    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

    If AGI is so close, why is everyone leaving? The neolabs and their bets

    November 6, 20265 Views
    Don't Miss
    Gadgets & Smart Devices

    Total Wireless Promo Codes & Deals: 50% Off Select Plans

    By adminNovember 21, 20260

    Total Wireless, formerly known as Total by Verizon, is a prepaid, no-contract wireless provider with…

    [2505.14240] Learning with Local Search MCMC Layers

    November 21, 2026

    Therabody Promo Codes: 15% Off November 2026

    November 21, 2026

    Deviations from the NTK Regime in CNNs under Joint Depth-Width Scaling

    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

    Total Wireless Promo Codes & Deals: 50% Off Select Plans

    November 21, 2026

    [2505.14240] Learning with Local Search MCMC Layers

    November 21, 2026

    Therabody Promo Codes: 15% Off November 2026

    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.