4,439 records
- OptEMA: Adaptive Exponential Moving Average for Stochastic Optimization with Zero-Noise Optimality
- On the Width Scaling of Neural Optimizers Under Matrix Operator Norms I: Row/Column Normalization and Hyperparameter Transfer
- Stochastic Port-Hamiltonian Neural Networks: Universal Approximation with Passivity Guarantees
- Large Spikes in Stochastic Gradient Descent: A Large-Deviations View
- Unbalanced Optimal Transport Dictionary Learning for Unsupervised Hyperspectral Image Clustering
- Intrinsic Numerical Robustness and Fault Tolerance in a Neuromorphic Algorithm for Scientific Computing
- Large chirotopes with computable numbers of triangulations
- Estimating Condition Number with Graph Neural Networks
- Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference
- Drag-Aware Aerodynamic Manipulability for Torque-Limited Redundant Multirotors: Aerodynamic Promptness based on the Symmetric Acceleration Capacity
- A new proof of Delahan's induced-universality result
- Capacity of Non-Separable Networks with Restricted Adversaries
- Central Limits via Dilated Categories
- Learning efficient representations of complex constraints for scalable optimization
- Agentic Neurosymbolic Collaboration for Mathematical Discovery: A Case Study in Combinatorial Design
- NN-OpInf: an operator inference approach using structure-preserving composable neural networks
- WELLDOC property for words generated by morphisms
- Context-Free Trees
- Group Entropies and Mirror Duality: A Class of Flexible Mirror Descent Updates for Machine Learning
- Time warping with Hellinger elasticity
- Quantization of Ricci Curvature in Information Geometry
- Feed m Birds with One Scone: Accelerating Multi-task Gradient Balancing via Bi-level Optimization
- Cost-Driven Representation Learning for Linear Quadratic Gaussian Control: Part II
- Partial Differential Equations in the Age of Machine Learning: A Critical Synthesis of Classical, Machine Learning, and Hybrid Methods
- Step-Size Decay and Structural Stagnation in Greedy Sparse Learning
- Large Language Model for Discrete Optimization Problems: Evaluation and Step-by-step Reasoning
- Transferable Optimization Network for Cross-Domain Image Reconstruction
- A Lock-Free, Fully GPU-Resident Architecture for the Verification of Goldbach's Conjecture
- Margin in Abstract Spaces
- Design Experiments to Compare Multi-armed Bandit Algorithms
- Gradient Flow Polarizes Softmax Outputs towards Low-Entropy Solutions
- Learning Where the Physics Is: Probabilistic Adaptive Sampling for Stiff PDEs
- Adaptive Lipschitz-Free Conditional Gradient Methods for Stochastic Composite Nonconvex Optimization
- Toward Generative Quantum Utility via Correlation-Complexity Map
- The DNA Coverage Depth Problem: Duality, Weight Distributions, and Applications
- Three Fixed-Dimension Satisfiability Semantics for Quantum Logic: Implications and an Explicit Separator
- Latent Autoencoder Ensemble Kalman Filter for Nonlinear Data assimilation
- Implementation of Quantum Implicit Neural Representation in Deterministic and Probabilistic Autoencoders for Image Reconstruction/Generation Tasks
- Learning-Based Robust Control: Unifying Exploration and Distributional Robustness for Reliable Robotics via Free Energy
- An Extended Topological Model For High-Contrast Optical Flow
- Joint MDPs and Reinforcement Learning in Coupled-Dynamics Environments
- Multilevel Training for Kolmogorov Arnold Networks
- Set-Membership Localization via Range Measurements
- U-OBCA: Uncertainty-Aware Optimization-Based Collision Avoidance via Wasserstein Distributionally Robust Chance Constraints
- Non-Euclidean Gradient Descent Operates at the Edge of Stability
- Positional s-of-k games
- Modal Fragments
- The Complexity of the Constructive Master Modality
- What induces plane structures in complete graph drawings?
- ETH-Tight Complexity of Optimal Morse Matching on Bounded-Treewidth Complexes