4,439 records
- Two-Parameter Flows for Learning Population Dynamics of Physical Systems
- Classification and detection of multiple UAVs using rational Gaussian wavelet neural networks
- Semigroup Consistency as a Diagnostic for Learned Physics Simulators
- Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback
- Phantom Transitions in Language Model Fine-Tuning: A Density-Matrix Analysis
- Spectral origin of the topological gap exponent d + η: mechanism, kernel, decomposition, and scope
- Solving Combinatorial Counting Problems with Weighted First-Order Model Counting
- Efficient DP-SGD for LLMs with Randomized Clipping
- Global linear convergence of entropy-regularized softmax policy gradient beyond tabular MDPs
- Improved Johnson-type Bounds for Insertion-Deletion Codes
- Anarchy in the swarm: Testing informed and uninformed diversity-enhancing mechanisms within PSO framework
- RECTOR: Priority-Aware Rule-Based Reranking for Compliance-Aware Autonomous Driving Trajectory Selection
- Leveraging Gauge Freedom for Learning Non-Gradient Population Dynamics of Stochastic Systems
- Constraint-Anchored Attribution: Feasibility-Certified Counterfactuals and Bonferroni-PAC Sufficient Subsets for Neural CO Policies
- Algorithms with Polynomially-Improved Approximation Factors for the $2 \rightarrow q$ Norm, and Applications
- Adversarial Water-Filling: Theory, Algorithms, and a Domain-Specific Wireless Foundation Model
- Planning Neural Dynamics with Lie Group Embedding through Supervised Projective Manifold Learning
- A Geometric Gaussian Mixture Representation of Plane Curves
- The Normalized Maximum Likelihood for Regular Non-Smooth Models: Measure-Theoretic Foundations and Geometric Sampling
- Deep ZakaiJ: Structured Filtering for Jump-Diffusion Time Series Forecasting
- Feature Learning in Wide Neural Networks under $μ$P: Identifiability and Sparse-Dictionary Decomposition of the Mean-Field Limit
- A computational phase transition for learning-to-sample from Ising models
- Complement Submodular Information Measures for Balanced and Robust Data Selection
- The Closure of LCD-to-GI Reductions via Generalized Inner Products
- Any-Dimensional Invariant Universality
- Expand More, Shrink Less: Shaping Effective-Rank Dynamics for Dense Scaling in Recommendation
- Entropy Equivalence Testing
- Enhancing Blood Cells Classification using Hybrid Quantum Neural Networks
- On the Approximate Non-Deterministic Degree of Total Boolean Functions
- Instance-Optimal Estimation with Multiple LLM Judges on a Budget
- Coupling-Robust Accuracy in Multiphysics Physics Informed Neural Networks via Kronecker-Preconditioned Optimization
- Hybrid Quantum-Classical Corrective Diffusion Modeling for Meteorological Downscaling
- Weisfeiler-Leman Is Incomplete on Simple Spectrum Graphs, so Canonicalize Them
- Commutator-Induced Uncertainty in VAEs
- Non-normal spectral signatures of instability in neural network training dynamics
- Is Dimensionality a Barrier for Retrieval Models?
- Optimization of randomized neural networks for transfer operator approximation
- Entrywise Error Bounds for Spectral Ranking with Semi-Random Adversaries
- Training-Free Looped Transformers
- Efficient sampling of the unlabeled structure of uniform random mappings and surjections
- Riemannian Archetypal Analysis: Interpretable non-linear data analysis on deformed star distributions
- A Tight Bound on Localization of Electrical Flows
- On weighted partial triangulations of convex polygons
- From Sequential Nodes to GPU Batches: Parallel Branch and Bound for Optimal $k$-Sparse GLMs
- Holomorphic Neural ODEs with Kolmogorov-Arnold Networks for Interpretable Discovery of Complex Dynamics
- Exact Hidden Paths in Noisy High Dimensional Path Spaces
- When Stronger Triggers Backfire: A High-Dimensional Theory of Backdoor Attacks
- A Symbolic Homotopy Algorithm for Solving Composable Polynomial Systems
- Neural Flow Operators can Approximate any Operator: Abstract Frameworks and Universal Approximations
- A Formal Basis for Quantum Cryptographic Exposure Measurement under HNDL Threat