Stabilization

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 25

All topics

Predictive Dual Smoothing for Column Generation
Sep 28, 2026Senne Berden, Noah Schutte, Andrea Lodi +1Linear Programming Smoothing
KU Leuven · TU Delft · Cornell Tech
Diffusion-Based Rollouts as a Stabilization Mechanism for Long-Horizon Environmental Forecasting
Sep 27, 2026Marina Vicens-Miquel, Amy McGovern, Aaron J. Hill +2Long-Horizon Forecasting Stabilization
University of Oklahoma, School of Meteorology, Norman, Oklahoma · University of Oklahoma, School of Computer Science, Norman, Oklahoma · NSF AI Institute for Research on Trustworthy AI in Weather, Climate, and Coastal Oceanography, Norman, Oklahoma +2
GazeFS: Target-Centered Gaze-Trajectory Forecasting and Stabilization from Gaze-Head History
Sep 3, 2026Yaozheng Xia, Zaiping Zhu, Bo Pang +4Gaze Target Estimation Stabilization
School of Information Science and Technology, School of Artificial Intelligence, Beijing Forestry University · School of Digital Art, Nanjing University of the Arts · School of Computer Science, Peking University +1
Stabilizing Camera-Controlled Novel View Synthesis at Inference Time
Sep 3, 2026Prajwal Singh, Arjun Badola, Seema Kumari +2Video Diffusion Models Camera Control
CVIG Lab and ISLab, D3 Center · Osaka University
Robustness Emerges Early in Training Dynamics, but Is Not Preserved
Aug 5, 2026Jiangang Yang, Wenhui Shi, Lu Hu +2Stabilization Prior Knowledge Integration
Institute of Microelectronics, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China
EvoHIL: Self-Evolving Reward and Flow-Matched Policy Optimization for Robust Human-in-the-Loop Reinforcement Learning
Aug 4, 2026Shuoqin Zhang, Tongtong Cheng, Xiru Gao +7Human-In-The-Loop Reinforcement Learning From Human Feedback
WASABI: Whole-graph Assignment-based Stabilizer for lAne topology By Inter-frame tracking
Jul 22, 2026Tetsuhiro Uchida, Myu Sasaki, Kensho Nakajima +2Autonomous Driving Perception Autonomous Driving
Sony Honda Mobility Inc.
A Memory Efficient Unified Algorithm for Online Learning of Linear Dynamical Systems
Jul 2, 2026Yuval Ran-Milo, Angelos Assos, Elad HazanNonlinear Dynamics Dynamical Systems
Tel Aviv University · Princeton University
Stabilizing Extrapolation in Looped Transformers via Learned Stochastic Stopping
Jun 29, 2026Hsun-Yu Kuo, El Mahdi Chayti, Patrik Reizinger +2Stochastic Multi-Stage Training
EPFL, Lausanne, Switzerland · Max Planck Institute for Intelligent Systems & ELLIS Institute, Tübingen, Germany
Reachability Guarantees for Cart-Pole Swing-Up and Stabilization
Jun 26, 2026Mohamed Khalid M JaffarLyapunov Function Linear Quadratic Regulator
Department of Aerospace Engineering University of Maryland, College Park, USA
Zero-shot Transfer of Reinforcement Learning Control Policies for the Swing-Up and Stabilization of a Cart-Pole System
Jun 20, 2026Nikki Xu, Hien TranReinforcement Learning Control Generative Control Policies
Department of Mathematics, Box 8205, NC State University, Raleigh, NC 27695
When Does Streaming Tool Use Help? Characterizing Tool-Intent Stabilization in Streaming Retrieval-Augmented Generation
Jun 18, 2026Elroy GalbraithStreaming Stabilization
SMG Labs
Mitigating the Contractivity Trap in Diffusion ODEs via Stein Stabilization
Jun 5, 2026Shigui Li, Delu ZengDiffusion Models Wasserstein Gradient Flows
School of Mathematics, South China University of Technology, Guangzhou, China · School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China
Flatland: The Adventures of Gradient Descent with Large Step Sizes
Jun 4, 2026Leonardo Galli, Curtis Fox, Wiebke Bartolomaeus +2Gradient Descent Step Accuracy
LMU Munich · Munich Center for Machine Learning · University of British Columbia +1
CamFlow+: Hybrid Motion Bases for 2D Camera Motion Estimation with Stabilization Applications
Jun 4, 2026Haipeng Li, Zhen Liu, Zhanglei Yang +6Optical Flow Homography
School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China · School of Aeronautics and Astronautics, Sichuan University, Chengdu, Sichuan, China · YingCai Honors College, University of Electronic Science and Technology of China, Chengdu, Sichuan, China +2
$\boldsymbol{f}$ -OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control
May 18, 2026Xianwei Chen, Shimin Zhang, Jibin WuRp-Opsd Gradient Staleness
The Hong Kong Polytechnic University
Stabilizing, Scaling & Enhancing MeanFlow for Large-scale Diffusion Distillation
May 18, 2026Xiao He, Yang Li, Peizhen Zhang +3Meanflow Diffusion Models
1State Key Laboratory of Integrated Services Networks, Xidian University · 2Tencent Hunyuan
Wind-Aware Optimal Trajectory Planning for Efficient Gliding of Fixed-Wing Aerial Systems
May 15, 2026Luca Morando, Nishanth Bobbili, Giuseppe LoiannoUnmanned Aerial Vehicle Trajectories Aerial Navigation
New York University, NY 10012, USA · University of California Berkeley, Department of Electrical Engineering and Computer Sciences, Berkeley, CA 94720, USA
Augmented Lagrangian Multiplier Network for State-wise Safety in Reinforcement Learning
May 1, 2026Jiaming Zhang, Yujie Yang, Yao Lyu +2Lagrangian Methods Stabilization
GIFT: Global stabilisation via Intrinsic Fine Tuning
Apr 25, 2026Rory Young, Nicolas PugeaultStabilization Continual Fine-Tuning
School of Computing Science University of Glasgow
Passive Variable Impedance For Shared Control
Apr 22, 2026Maximilian Mühlbauer, Nepomuk Werner, Ribin Balachandran +4Impedance Control Robotic Manipulator
School of Computation, Information and Technology, Sensor Based Robotic Systems and Intelligent Assistance Systems, Technical University Munich, Friedrich-Ludwig-Bauer-Str. 3, Garching, Germany. · German Aerospace Center (DLR), Robotics and Mechatronics Center (RMC), Münchener Str. 20, 82234 Weßling, Germany.
Pairing Regularization for Mitigating Many-to-One Collapse in GANs
Apr 22, 2026Kuan-Yu Lin, Yu-Chih Huang, Tie LiuGenerative Adversarial Network Regularization
Institute of Communications Engineering, National Yang Ming Chiao Tung University · Department of Electrical & Computer Engineering, Texas A&M University
Curvature-Aligned Probing for Local Loss-Landscape Stabilization
Apr 16, 2026Nikita Kiselev, Andrey GrabovoyAnisotropic Loss Landscapes Curvature-Aware Spectral Framework
Department of Intelligent Systems Moscow Institute of Physics and Technology
Model-Free Output Feedback Stabilization via Policy Gradient Methods
Jan 27, 2026Ankang Zhang, Ming Chi, Xiaoling Wang +1Robust Control Stabilization
School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China · College of Automation, Nanjing University of Posts and Telecommunications, Nanjing 210023, China
Recursive Learning Without Collapse: A Weighting-Based Stabilization Framework
Feb 25, 2025Hengzhi He, Shirong Xu, Guang ChengSynthetic Data Generative Models
Department of Statistics and Data Science, University of California, Los Angeles · Wang Yanan Institute for Studies in Economics, Xiamen University

Sep 28, 2026, cs.LGJ/K move · Enter open · S save

Predictive Dual Smoothing for Column Generation

Senne Berden, Noah Schutte, Andrea Lodi, Tias Guns

KU Leuven · TU Delft · Cornell Tech

Linear Programming Smoothing Stabilization Student-Generated Trajectories Data Generation

Open paper AskPDF arXiv

Solving large-scale linear programs efficiently is an important challenge in many optimization settings. A key technique is column generation, which alternates between solving the master problem over a restricted subset of the variables, and using a pricing subproblem to identify new variables to add. The pricing subproblem is guided by the dual solution of the current restricted master problem, but oscillations in these dual solutions can substantially slow convergence. Dual stabilization methods address this issue. Dual smoothing is a common stabilization method, which guides the pricing subproblem using a combination of the current dual solution and duals from previous iterations. However, while past dual solutions can stabilize the dual trajectory, they do not necessarily guide pricing towards useful new variables. We therefore introduce predictive dual smoothing, which instead combines the current dual solution with a learned prediction of future duals to steer pricing towards variables that are more useful in subsequent iterations. The predictor is trained offline using supervision extracted from standard column generation trajectories and is used only to modify the pricing subproblem's objective function, while exact reduced-cost checks and fallback pricing with the unsmoothed duals preserve correctness. Experiments on cutting stock and generalized assignment problems show that predictive dual smoothing substantially reduces generated columns and wall-clock time relative to standard column generation and existing classical and learned stabilization methods. These gains extend to out-of-distribution instance sizes, and predictive smoothing provides further improvements when combined with strong classical stabilization.

Momentum

Related topics

Latest papers 25