4,439 records
- When Attention Beats Fourier: Multi-Scale Transformers for PDE Solving on Irregular Domains
- Convergence Analysis of Newton's Method for Neural Networks in the Overparameterized Limit
- Central Limit Theorem for Two-Time-Scale Approximate Distributionally Robust RL
- Generalized Wasserstein Flow Matching: Transport Plans, Everywhere, All at Once
- Transformers Can Implement Preconditioned Richardson Iteration for In-Context Gaussian Kernel Regression
- Scaling Limits of Long-Context Transformers
- Algorithmic Phase Transition for Large Independent Sets in Dense Hypergraphs
- From Dual Tracking to Clipping: Provably Faster Distributionally Robust Multi-Objective Optimization
- WARP: A Benchmark for Primal-Dual Warm-Starting of Interior-Point Solvers
- Discrete Optimal Transport: Rapid Convergence of Simulated Annealing Algorithms
- DBMSolver: A Training-free Diffusion Bridge Sampler for High-Quality Image-to-Image Translation
- Quadratic Objective Perturbation: Curvature-Based Differential Privacy
- PREFER: Personalized Review Summarization with Online Preference Learning
- Label Correcting Algorithms for the Multiobjective Temporal Shortest Path Problem
- Sharper Guarantees for Misspecified Kernelized Bandit Optimization
- A Fine-Grained Understanding of Uniform Convergence for Halfspaces
- Matrix-Decoupled Concentration for Autoregressive Sequences: Dimension-Free Guarantees for Sparse Long-Context Rewards
- Geometry-Aware Simplicial Message Passing
- Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes
- PACE: Prune-And-Compress Ensemble Models
- INEUS: Iterative Neural Solver for High-Dimensional PIDEs
- CoupleEvo: Evolving Heuristics for Coupled Optimization Problems Using Large Language Models
- A Unified Pair-GRPO Family: From Implicit to Explicit Preference Constraints for Stable and General RL Alignment
- Measuring Structure in Graph Benchmark Datasets Using Graph Invariants
- No Triangulation Without Representation: Generalization in Topological Deep Learning
- Affine Subcode Ensemble Decoding for Degeneracy-Aware Quantum Error Correction
- Criticality and Saturation in Orthogonal Neural Networks
- SNAPO: Smooth Neural Adjoint Policy Optimization for Optimal Control via Differentiable Simulation
- Solving Minimal Problems Without Matrix Inversion Using FFT-Based Interpolation
- Learning Distributionally Robust First-Order Methods for Convex Optimization
- When and Why SignSGD Outperforms SGD: A Theoretical Study Based on $\ell_1$-norm Lower Bounds
- Adjacency labelling for proper minor-closed graph classes
- Optimizer-Model Consistency: Full Finetuning with the Same Optimizer as Pretraining Forgets Less
- Why Global LLM Leaderboards Are Misleading: Small Portfolios for Heterogeneous Supervised ML
- Gated QKAN-FWP: Scalable Quantum-inspired Sequence Learning
- When Does Critique Improve AI-Assisted Theoretical Physics? SCALAR: Structured Critic--Actor Loop for Agentic Reasoning
- A Rod Flow Model for Adam at the Edge of Stability
- Christoffel-DPS: Optimal sensor placement in diffusion posterior sampling for arbitrary distributions
- A Sharp Finite-Iteration Theory for Asynchronous Categorical Distributional Temporal-Difference Learning
- When Descent Is Too Stable: Event-Triggered Hamiltonian Learning to Optimize
- EULER-ADAS: Energy-Efficient & SIMD-Unified Logarithmic-Posit Engine for Precision-Reconfigurable Approximate ADAS Acceleration
- Constrained Triple-Head Price Optimization (C3PO) Network for Discrete-Choice Models
- Adaptive auditing of AI systems with anytime-valid guarantees
- Online Nonstochastic Prediction: Logarithmic Regret via Predictive Online Least Squares
- $p$-adic Manifold Learning and Benchmark Tasks from Impartial Games
- Demystifying Manifold Constraints in LLM Pre-training
- Beyond Ability: The Four-Fold Spectrum of Power and the Logic of Full Inability
- From Video-to-PDE: Data-Driven Discovery of Nonlinear Dye Plume Dynamics
- A Queueing-Theoretic Framework for Stability Analysis of LLM Inference with KV Cache Memory Constraints
- CombOL: a Library for Practical Enumeration and Boltzmann Sampling of Combinatorial Classes