Modern Deep Networks

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 31

All topics

Verifying Neural Networks with Reinforcement Learning
Sep 28, 2026Hai Duong, Thanh Le, ThanhVu NguyenNeural Network Verification Reinforcement Learning With Verifiable Reward
Department of Computer Science George Mason University Fairfax, VA, USA · Unaffiliated Yokosuka, Japan
Neural Approximation by Function Composition: Rigidity and Doubly Exponential Convergence
Sep 22, 2026Wentao Huang, Haizhang ZhangNeural Approximations Approximation
Department of Mathematics, The University of Hong Kong, Hong Kong, P.R. China. · School of Mathematics, Sun Yat-sen University, Guangzhou, P.R. China.
FairLint-DL: An IDE-Native Tool for Fairness Debugging of Deep Learning Software
Sep 14, 2026Archit Rathod, Saeid Tizpaz-NiariAlgorithmic Fairness Large Language Model Bias
University of Illinois at Chicago Chicago, USA
Convergent Evolution in Neural Representation Space: Emergent Order in Deep Belief Networks
Aug 6, 2026Patrick Krauss, Achim Schilling, Andreas Maier +2Modern Deep Networks Neural Network Training
Cognitive Computational Neuroscience Group, Pattern Recognition Lab, Friedrich-Alexander-University Erlangen-Nürnberg (FAU), Germany · Neuromodulation and Neuroprosthetics, University Hospital Mannheim, University Heidelberg, Germany · Neuroscience Lab, University Hospital Erlangen, Germany +1
Binding Biometrics with AI Agent Identifiers for Delegation of Authority
Aug 4, 2026Joseph Geo Benjamin, Anil K Jain, Karthik NandakumarBiometrics Delegation
Michigan State University, MI, USA
Understanding Fault Tolerance of Adversarially Robust Pruned Models
Aug 4, 2026Manali Dangarikar, Cory MerkelModern Deep Networks Structured Pruning
Brain Lab Rochester Institute of Technology Rochester, NY, USA
Exploration of the generative capabilities of Boltzmann machines applied to social systems under the majority rule
Jul 25, 2026Mauricio A. Valle, Gonzalo A. RuzBoltzmann Distributions Modern Deep Networks
Faculty of Engineering and Sciences Universidad Adolfo Ibáñez Millennium Nucleus for Social Data Science (SODAS) Santiago, Chile · Faculty of Engineering and Sciences Universidad Adolfo Ibáñez Millennium Nucleus for Social Data Science (SODAS) Millennium Nucleus in Data Science for Plant Resilience (PhytoLearning) Santiago, Chile
Hilbert Operator for Progressive Encoding (HOPE): A Mathematical Framework for Deconstructing Learned Representations in Deep Networks
Jul 23, 2026Hossein Mobahi, Peter L. BartlettModern Deep Networks Deep Network
Google DeepMind · University of California, Berkeley
MIS-HCC: Hierarchical Channel Clustering for Efficient Medical Image Segmentation
Jul 19, 2026Bo Zhao, Haoran Yu, Lifei Liu +5Semi-Supervised Medical Image Segmentation Modern Deep Networks
Yale University · University of Florida · Wichita State University +5
Weight Feedback Computes the Jacobian Transpose Locally in Modern Deep Networks
Jul 15, 2026Junlong Shen, Xingyu LiBackpropagation Predictive Coding
Department of Electrical and Computer Engineering, University of Alberta, Edmonton, Canada · Alberta Machine Intelligence Institute (Amii), Edmonton, Canada
Reassessing Muon for Matrix Factorization
Jul 14, 2026Ali Parviz, Gal Mishne, Alex CloningerMuon Adam
†. Halicioğlu Data Science Institute, UC San Diego. · ∗. Department of Mathematics, UC San Diego.
A Trainable-by-Parts Operator Learning Framework: Bridging DeepONet and Karhunen-Loeve Expansions for Large-Scale Applications
Jun 26, 2026Christian Munoz, Alexandre TartakovskyProbabilistic Operator Learning Modern Deep Networks
Civil Engineering Department University of Illinois Urbana-Champaign Urbana, IL 61801 · Pacific Northwest National Laboratory,Jun Richland, WA 99352
Fast and Slow Variational Continual Learning
Jun 22, 2026Subarnaduti Paul, Yohan Jung, Mohammad Emtiyaz Khan +3Replay-Based Continual Learning Adaptive Optimizers
Faculty of Mathematics and Computer Science, University of Bremen, Bremen, Germany · Department of Computer Science & AI, Jeonbuk National University, Republic of Korea · Department of Computer Science, TU Darmstadt, Darmstadt, Germany +3
Sublinearly Structured Deep Neural Networks Achieve Feature Learning Consistency for Compositional Functions
Jun 22, 2026Sehwan Kim, Yan Sun, Faming LiangModern Deep Networks Neural Network
Ewha Womans University, Seoul 03760, Republic of Korea · New Jersey Institute of Technology, Newark, NJ 07102, USA · Purdue University, West Lafayette, IN 47907, USA
Beyond the Thin-Layer Limit: Differentiable Volumetric Training for Visible-Range Diffractive Neural Networks
Jun 5, 2026Dineth Jayakody, Dushan N. WadduwageModern Deep Networks Differentiable Optimization
Department of Computer Science, Old Dominion University, Norfolk, VA 23529, USA · School of Data Science, Old Dominion University, Norfolk, VA 23529, USA · Department of Physics, Old Dominion University, Norfolk, VA 23529, USA
Structured Neuron Pruning in Deep Neural Networks Using Multi-Armed Bandits
May 29, 2026Salem Ameen, Sunil VaderaModern Deep Networks Unstructured Pruning
School of Science, Engineering and Environment, University of Salford, Salford, United Kingdom
TASER: Task-Aware Stein Regularisation for Geometry-Driven Robustness
May 28, 2026Michał Kozyra, Gesine ReinertAdversarial Training Regularization
Department of Statistics, University of Oxford, United Kingdom
LLMs Without Deep Neural Networks: New Architecture, Benefits and Case Study
May 28, 2026Vincent GranvilleModern Deep Networks Neural Network
CAIO
Towards the Connection between Activation Sparsity and Flat Minima
May 25, 2026Ze Peng, Jian Zhang, Lei Qi +2Sparsity Modern Deep Networks
State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China · Institute of Brain-Machine Interface, Nanjing University, Nanjing 210023, China · School of Computer Science and Engineering, Southeast University, Nanjing 211189, China
Soft Learning
May 16, 2026Mohammed Aledhari, Ali Aledhari, Fatimah Aledhari +1Support Vector Machines Singular Learning Theory
Department of Data Science & Department of Computer Science and Engineering, University of North Texas, Denton, TX 76207, USA · Department of Computer and Information Science, Fordham University, New York, NY 10458, USA
Enjoy Your Layer Normalization with the Computational Efficiency of RMSNorm
May 14, 2026Yuxin Guo, Yihao Yue, Yunhao Ni +4Batch Normalization Neural Network Inference
State Key Laboratory of Complex and Critical Software Environment (SKLCCSE), Beihang University, Beijing, China · Hangzhou International Innovation Institute, Beihang University, Hangzhou, China
Does Your Neural Network Extrapolate? Feature Engineering as Identifiability Bias for OOD Generalization
May 8, 2026Leonel Aguilar, Jan Nagler, Christoph Hoelscher +1Out-Of-Distribution Extrapolation
Chair of Cognitive Science, ETH Zürich · Centre for Human and Machine Intelligence, Frankfurt School · Aisot Technologies AG +1
Training-Time Batch Normalization Reshapes Local Partition Geometry in Piecewise-Affine Networks
May 6, 2026Xuan Qi, Yi Wei, Fanqi Yu +3Batch Normalization Rectified Linear Unit Networks
AI for Good Istituto Italiano di Tecnologia, Genoa, Italy Department of Computer Science University of Verona, Verona, Italy
Enhance the after-discharge mortality rate prediction via learning from the medical notes
May 5, 2026Zijiang YangIntensive Care Unit Mortality Prediction Electronic Health Records
University of Texas at Austin, Austin TX 78712, USA
Tessera: Secure, Near-Line-Rate Weight Streaming for UMA Edge Accelerators
Apr 25, 2026Animan NaskarEdge Devices Homomorphic Encryption
Indian Institute of Technology (IIT) Ropar
Towards a Systematic Risk Assessment of Deep Neural Network Limitations in Autonomous Driving Perception
Apr 21, 2026Svetlana Pavlitska, Christopher Gerking, J. Marius ZöllnerAutonomous Driving Perception Autonomous Driving
FZI Research Center for Information Technology, Germany · Karlsruhe Institute of Technology, Germany
Incremental learning for audio classification with Hebbian Deep Neural Networks
Apr 20, 2026Riccardo Casciotti, Francesco De Santis, Alberto Antonietti +1Hebbian Learning Class-Incremental Learning
Signal Processing Research Centre, Tampere University, Tampere, Finland · Department of Electronics, Information and Bioengineering (DEIB), Politecnico di Milano, Italy
Automatic Extraction of Road Networks by using Teacher-Student Adaptive Structural Deep Belief Network and Its Application to Landslide Disaster
Nov 4, 2025Shin Kamada, Takumi IchimuraLandslides Road Networks
S. Kamada is with Hiroshima City University, Hiroshima, Japan · T. Ichimura is with Prefectural University of Hiroshima, Hiroshima, Japan
Last Layer Hamiltonian Monte Carlo
Jul 11, 2025Koen Vellenga, H. Joe Steinhauer, Göran Falkman +2Modern Deep Networks Monte Carlo
University of Skövde & Volvo Car Corporation, Sweden · University of Skövde, Sweden · Volvo Car Corporation, Sweden
MetaMax: Improved Open-Set Deep Neural Networks via Weibull Calibration
Nov 20, 2022Zongyao Lyu, Nolan B. Gutierrez, William J. BeksiOpen-Set Recognition Modern Deep Networks
The University of Texas at Arlington Arlington, TX, USA
Theory of the Frequency Principle for General Deep Neural Networks
Jun 21, 2019Tao Luo, Zheng Ma, Zhi-Qin John Xu +1Modern Deep Networks Neural Network
Department of Mathematics, Zheng Ma Purdue University · Department of Mathematics, Purdue University · New York University Abu Dhabi and Courant Institute

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

Verifying Neural Networks with Reinforcement Learning

Hai Duong, Thanh Le, ThanhVu Nguyen

Department of Computer Science George Mason University Fairfax, VA, USA · Unaffiliated Yokosuka, Japan

Neural Network Verification Reinforcement Learning With Verifiable Reward Deep Q-Networks Modern Deep Networks Offline Reinforcement Learning Neural Network+2

Open paper AskPDF arXiv

Formal verification can play a key role in ensuring the reliability of Deep Neural Networks (DNNs) deployed in safety-critical systems. Modern DNN verifiers employ a branch-and-bound framework, which alternates between branching (splitting into smaller subproblems) and bounding (pruning subproblems) to efficiently explore the verification space. However, existing branching heuristics make greedy decisions based on static scoring functions. They do not anticipate long-term efficiency or leverage the growing availability of verification data to improve performance. This work introduces RSB, a reinforcement learning framework that learns to refine baseline branching heuristics. It trains an actor-critic architecture to maximize cumulative future rewards rather than immediate scores. The actor generates attention weights from observations of raw neuron features and learned graph embeddings, which rescale baseline heuristic scores to guide neuron branching. Evaluation on 600 challenging instances demonstrates that RSB consistently outperforms state-of-the-art branching heuristics, solving 11% more instances while reducing branch exploration by 50%.

Momentum

Related topics

Latest papers 31