Neural Network Stability

Follow this topic Ask about this topic

Latest papers

37 papers9 papers in the last four weeks, against 1 the four weeks before. 0.1% of all new papers.

Length-Independent Stability and $L_2$ -Gain Certificates for Chains of Delayed Neural Modules
Oct 18, 2026Ömer Faruk İşcanlıNeural Network Stability Modular Neural Networks
Department of Computer Engineering, Istanbul University-Cerrahpaşa, Istanbul, Türkiye
ControlJEPA: Principled Trajectory Regularization via Lyapunov Tube Loss
Oct 18, 2026Thai-Khanh Nguyen, Nhi Y. Pham, Uyen N. B. Vo +3Latent-Space Regularization Neural Network Stability
Faculty of Information Technology 1, Posts & Telecommunications Institute of Technology · Center for AI Research, VinUniversity · Faculty of Artificial Intelligence, Posts & Telecommunications Institute of Technology +2
Global Convergence in Deep Networks via the Second Law of Thermodynamics
Oct 17, 2026Matan Tsipory, Ofir Gaash, Itamar Harel +2Neural Network Training Dynamics Stochastic Optimization Convergence
Technion - Israel Institute of Technology, The Andrew and Erna Viterbi Faculty of Electrical & Computer Engineering, Technion City, Haifa 3200003, Israel. · Technion - Israel Institute of Technology, Faculty of Data and Decision Sciences, Technion City, Haifa 3200003, Israel. · Toyota Technological Institute at Chicago, Chicago, IL, USA.
Muon Operates Beyond the Edge of Stability
Oct 16, 2026Niko Covic, Baraq Lipshitz, Alexander Padula +1Muon Optimizer Edge of Stability
Department of Informatics, ETH Zurich, Switzerland.
Distributed Performance Boosting through Neural Control for Plug-and-Play Networks
Oct 16, 2026Danilo Saccani, Leonardo Massai, Giancarlo Ferrari-TrecateDistributed Control Neural Network Stability
Ecole polytechnique federale de Lausanne (EPFL), CH-1015 Lausanne, Switzerland.
Understanding Stability of Outer Nesterov Momentum on Stochastic Pseudo-Gradients
Oct 15, 2026Nishant Sharma, Laura Gomezjurado Gonzalez, Ganesh Talluri +2Neural Network Stability Neural Network Training Dynamics
Chandar Research Lab · Mila – Quebec AI Institute · Université de Montréal +4
Lipschitz Thinking: Ten Years of Certifiable-by-Design Robust Neural Networks
Oct 5, 2026Fabio Brau, Giorgio Piras, Maura Pintor +1Neural Network Robustness Certified Robustness
Department of Electrical and Electronic Engineering, University of Cagliari, Cagliari, Italy
Learning Provable Neural Network Observer for Uncertain Dynamical Systems
Sep 25, 2026Zhangyi Wang, Jiaxu Liu, Song Chen +2Neural Network Stability Lyapunov Stability
College of Control Science and Engineering, Zhejiang University, China · School of Science, Huzhou Normal University, China · Department of Mathematics, National University of Singapore, Singapore
Stable initialization without the CLT
Sep 24, 2026Simon Kuang, Kyle Chickering, Xinfan LinNeural Network Initialization Neural Network Stability
Department of Mechanical and Aerospace Engineering University of California, Davis
When Does Scale-Invariant Optimization Become Unstable? An Exact Schedule Law with Weight Decay
Sep 8, 2026Hasan Amin, Wei-Kai Chang, Rajiv KhannaLearning Rate Scheduling Weight Decay
Purdue University
Eigenanalysis framework for autoregressive neural emulators of multi-scale chaotic dynamics
Aug 17, 2026Conrad Ainslie, Pedram Hassanzadeh, Michael W. Mahoney +1Neural Network Stability Neural Surrogate Modeling
Department of Applied Mathematics, University of California, Santa Cruz, Santa Cruz, 95064, CA · Department of Geophysical Sciences, University of Chicago, Chicago, IL 60637 · Committee on Computational and Applied Mathematics, University of Chicago, Chicago, IL 60637 +3
Local Stability and Gaussian Smoothing of Quantized Neural Networks
Jul 22, 2026Sergey Salishev, Anton Makarov, Oleg GranichinNeural Network Stability Neural Network Activation Functions
St. Petersburg State University, 199034, Saint Petersburg, Russia
Phasor Attention: Mean Root Square Normalization for Phase Manifold Preservation
Jul 20, 2026Sungwoo Goo, Hwi-yeol Yun, Sangkeun JungNeural Network Stability Gradient Clipping
College of Pharmacy, Chungnam National University, Daejeon, Republic of Korea · Department of Computer Science & Engineering, Chungnam National University, Daejeon, Republic of Korea
Backward Coherence and Hidden-State Stability in Recurrent Neural Networks: A Quasi-Reverse-Martingale Theory
Jun 8, 2026Yuan-chin Ivan ChangRecurrent Neural Networks Neural Network Stability
Institute of Statistical Science, Academia Sinica · Academia Road, Section 2, Nankang, Taipei 115, Taiwan
Between Amnesia and Chaos: A Memory Stability Expressivity Trilemma for Trainable Dissipative Oscillator Networks
Jun 7, 2026Caleb MunigetyDynamical Systems Lyapunov Stability
Independent Researcher
Flatland: The Adventures of Gradient Descent with Large Step Sizes
Jun 4, 2026Leonardo Galli, Curtis Fox, Wiebke Bartolomaeus +2Edge of Stability Gradient Descent
LMU Munich · Munich Center for Machine Learning · University of British Columbia +1
Mean--Fluctuation Dynamics at the Edge of Stability
Jun 3, 2026Antonin Chodron de CourcelEdge of Stability Gradient Descent Dynamics
Ecole Normale Sup´erieure, CNRS, 45 rue d’Ulm, 75005 Paris, France
Deep-layer limit and stability analysis of the basic forward-backward-splitting induced network (II): learning problems
May 26, 2026Xuan Lin, Chunlin WuNeural Network Stability Optimization Convergence Analysis
China Academy of Aerospace System and Innovation, 100088, Beijing, China · School of Mathematical Sciences, Nankai University, 94 Weijin Road, 300071, Tianjin, China
Non-normal spectral signatures of instability in neural network training dynamics
May 22, 2026Souvik GhoshDynamical Systems Neural Network Optimization
Department of Physics, National Sun Yat-sen University, Kaohsiung 80424, Taiwan
TIDE: Asymmetric Neural Circuits for Stabilized Temporal Inhibitory-Excitatory Dynamics
May 19, 2026Alexander Kyuroson, Denis Kleyko, Marcus LiwickiNeural Network Stability Dynamic Neural Networks
Luleå University of Technology, Luleå, Sweden · Örebro University & RISE Research Institutes of Sweden
Layer-wise Derivative Controlled Networks
May 14, 2026Rowan Martnishn, Sean AndersonNeural Network Stability
1Sentivity AI · 2Virginia Tech
AdamO: A Collapse-Suppressed Optimizer for Offline RL
May 3, 2026Nan Qiao, Sheng Yue, Shuning Wang +1Reinforcement Learning Orthogonal Optimization
1Tsinghua University, China · 2Central South University, China · 3Sun Yat-sen University, China
A Hybridizable Neural Time Integrator for Stable Autoregressive Forecasting
Apr 22, 2026Brooks Kinch, Xiaozhe Hu, Yilong Huang +6Neural Surrogate Modeling Time Series Transformers
Mechanical Engineering and Applied Mechanics, University of Pennsylvania, Philadelphia, PA, USA · Department of Mathematics, Tufts University, Medford, MA, USA · Department of Mathematics and Cybernetics, SINTEF Digital, Oslo, Norway +3
The Origin of Edge of Stability
Apr 22, 2026Elon LitmanEdge of Stability Gradient Descent
Stanford University
Generalization at the Edge of Stability
Apr 21, 2026Mario Tuci, Caner Korkmaz, Umut Şimşekli +1Intrinsic Dimensionality Neural Network Generalization
INRIA, CNRS, Département d’Informatique de l’Ecole Normale Supérieure / PSL, France · Department of Computing, Imperial College London, United Kingdom
ZC-Swish: Stabilizing Deep BN-Free Networks for Edge and Micro-Batch Applications
Apr 21, 2026Suvinava BasakNeural Network Stability Neural Network Activation Functions
TU Braunschweig, Universitätspl. 2, 38106 Braunschweig, Germany
Stability and Generalization in Looped Transformers
Apr 16, 2026Asher LabovichNeural Network Generalization Dynamical Systems
A Nonlinear Separation Principle via Contraction Theory: Applications to Neural Networks, Control, and Learning
Apr 16, 2026Anand Gokhale, Anton V. Proskurnikov, Yu Kawano +1Dynamical Systems Contraction Theory
Center for Control, Dynamical Systems, and Computation, UC Santa Barbara, Santa Barbara, CA 93106 USA · Department of Electronics and Telecommunications, Politecnico di Torino, Italy, 10129 · Graduate School of Advanced Science and Engineering, Hiroshima University, Higashi-Hiroshima 739-8527, Japan
Zeroth-Order Optimization at the Edge of Stability
Apr 16, 2026Minhak Song, Liang Zhang, Bingcong Li +3Edge of Stability Zeroth-Order Optimization
KAIST · KRAFTON · ETH Zurich +2
Conservation Law Breaking at the Edge of Stability: A Spectral Theory of Non-Convex Neural Network Optimization
Apr 8, 2026Daniel Nobrega MedeirosNeural Network Optimization Gradient Descent Dynamics
University of Colorado Boulder

Oct 18, 2026J/K move · Enter open · S save

Length-Independent Stability and $L_2$ -Gain Certificates for Chains of Delayed Neural Modules

Ömer Faruk İşcanlı

Department of Computer Engineering, Istanbul University-Cerrahpaşa, Istanbul, Türkiye

Neural Network Stability Modular Neural Networks Lyapunov Stability

Open paper AskPDF arXiv

Networks of repeated neural modules with delayed neighbour coupling need stability guarantees for every number of modules, but delay-dependent criteria certify one network at a time and grow with its size. This paper derives stability and

L_2

-gain certificates of length-independent size for open chains and rings of modules of two alternating types with slope-restricted activations. A local and a transmission delay act independently and are only bounded and continuous. A Lyapunov-Krasovskii functional with fixed integration limits and module-local variables that repeat with the module type reduces the certificate of every chain to one cell of two modules. Local conditions and a single linear matrix inequality of order 96 on this cell, or 104 for the gain, certify global asymptotic stability and a common

L_2

-gain bound for all open chains and all rings with an even number of at least four modules. Up to a margin, the stability inequality is also necessary for the repeated variables to certify every length. All uniform certificates, including certified coupling regions, are verified in exact rational arithmetic. In the numerical study, the certified coupling reaches 92% of an outer bound given by unstable members of the model class for short delays and 79% at the nominal delay bounds. For 16 modules at unit coupling strength, certificates of the same functional computed for that length alone raise the certified delay scale by 2% to 7% in four cases. A single stability problem with 1298 scalar variables thus replaces per-length certification of long chains at little cost.