4,439 records
- Gradient Clipping Beyond Vector Norms: A Spectral Approach for Matrix-Valued Parameters
- NPAP: Network Partitioning and Aggregation Package for Python
- Fused Gromov-Wasserstein Distance with Feature Selection
- Expected Batch Optimal Transport Plans and Consequences for Flow Matching
- Sure-almost-sure and Sure-limit-sure Window Mean Payoff in Markov Decision Processes
- Angle Between Two Vectors over Finite Fields and an Application to Projective Unique Decoding
- Harness Engineering as Categorical Architecture
- Approximation of Maximally Monotone Operators : A Graph Convergence Perspective
- Learning Minimally Rigid Graphs with High Realization Counts
- Simultaneously Minimizing Storage and Bandwidth Under Exact Repair With Quantum Entanglement
- Ensuring Logic in the Fog: Sound POMDP Synthesis with LTL Objectives
- UFO: A Domain-Unification-Free Operator Framework for Generalized Operator Learning
- Center-Manifold Reduction of Learning at Bifurcations: Interference and Rich Learning in Recurrent Neural Networks
- Adaptive Smooth Tchebycheff Attention for Multi-Objective Policy Optimization
- Identifying the nonlinear string dynamics with port-Hamiltonian neural networks
- Quantum Precoded Polar Codes
- TriVAL: A Tri-Validation Framework for Faithful Automatic Optimization Modeling
- Higher-order Persistence Diagrams
- The Geometric Wall: Manifold Structure Predicts Layerwise Sparse Autoencoder Scaling Laws
- Consolidation-Expansion Operator Mechanics:A Unified Framework for Adaptive Learning
- Chebyshev Center-Based Direction Selection for Multi-Objective Optimization and Training PINNs
- Optimizer-Induced Mode Connectivity: From AdamW to Muon
- Learning to Sparsify Stochastic Linear Bandits
- jNO: A JAX Library for Neural Operator and Foundation Model Training
- Just Previsions
- The Vote-Left Equilibrium: A Deterministic Coordination Strategy for the Faithful in The Traitors
- Generalization Error Bounds for Picard-Type Operator Learning in Nonlinear Parabolic PDEs
- BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization
- Signature Approach for Contextual Bandits with Nonlinear and Path-dependent Rewards
- PowerStep: Memory-Efficient Adaptive Optimization via $\ell_p$-Norm Steepest Descent
- Learning-Based Spectrum Cartography in Low Earth Orbit Satellite Networks: A Survey
- LLM4Branch: Large Language Model for Discovering Efficient Branching Policies of Integer Programs
- Don't Fix the Basis -- Learn It: Spectral Representation with Adaptive Basis Learning for PDEs
- A Note on Banaszczyk's Inequality
- Optimal Repair Bandwidth and Repair I/O of $(n,n-2,2)$ MDS Array Codes
- A Spectral Framework for Closed-Form Relative Density Estimation
- Natural Policy Gradient as Doubly Smoothed Policy Iteration: A Bellman-Operator Framework
- Kernel-Gradient Drifting Models
- Constant time testability of first-order logic with modulo counting on finitary graphs
- GRAFT-ATHENA: Self-Improving Agentic Teams for Autonomous Discovery and Evolutionary Numerical Algorithms
- Steerable Neural ODEs on Homogeneous Spaces
- Oversmoothing as Representation Degeneracy in Neural Sheaf Diffusion
- Muon is Not That Special: Random or Inverted Spectra Work Just as Well
- Quotient-Categorical Representations for Bellman-Compatible Average-Reward Distributional Reinforcement Learning
- Error whitening: Why Gauss-Newton outperforms Newton
- Accurate Evaluation of Quickest Changepoint Detectors via Non-parametric Survival Analysis
- MC$^2$: Monte Carlo Correction for Fast Elliptic PDE Solving
- Adversary-Robust Learning from Fully Asynchronous Directional Derivative Estimates
- Learning-Augmented Scalable Linear Assignment Problem Optimization via Neural Dual Warm-Starts
- Universal Feature Selection with Noisy Observations and Weak Symmetry Conditions