numerical experiments
Numerical experiments involve evaluating AI concepts or hypotheses through computation and simulations, relying on mathematical models to approximate real-world phenomena or validate theoretical predictions.
- 3BASiL: An Algorithmic Framework for Sparse plus Low-Rank Compression of LLMs
- A Bayesian Approach to Contextual Dynamic Pricing using the Proportional Hazards Model with Discrete Price Data
- A Computationally Viable Numerical Gradient-based Technique for Optimal Covering Problems
- A Near-Optimal Algorithm for Decentralized Convex-Concave Finite-Sum Minimax Optimization
- A Near-optimal, Scalable and Parallelizable Framework for Stochastic Bandits Robust to Adversarial Corruptions and Beyond
- A geometric framework for momentum-based optimizers for low-rank training
- Adaptive Riemannian ADMM for Nonsmooth Optimization: Optimal Complexity without Smoothing
- Amortized Variational Transdimensional Inference
- Balanced Active Inference
- Beyond Average Value Function in Precision Medicine: Maximum Probability-Driven Reinforcement Learning for Survival Analysis
- Beyond Benign Overfitting in Nadaraya-Watson Interpolators
- Beyond Last-Click: An Optimal Mechanism for Ad Attribution
- Concentration and excess risk bounds for imbalanced classification with synthetic oversampling
- Controlling the Flow: Stability and Convergence for Stochastic Gradient Descent with Decaying Regularization
- Convergence Rates of Constrained Expected Improvement
- DSCS: Fast CPDAG-Based Verification of Collapsible Submodels in High-Dimensional Bayesian Networks
- Decreasing Entropic Regularization Averaged Gradient for Semi-Discrete Optimal Transport
- Distributed Multi-Agent Bandits Over Erdős-Rényi Random Networks
- Distributed mediation analysis with communication efficiency
- Distributionally Robust Performative Optimization
- Error Broadcast and Decorrelation as a Potential Artificial and Natural Learning Mechanism
- Fast Projection-Free Approach (without Optimization Oracle) for Optimization over Compact Convex Set
- Fine-Tuning Discrete Diffusion Models with Policy Gradient Methods
- Hamiltonian Descent Algorithms for Optimization: Accelerated Rates via Randomized Integration Time
- Heavy-Ball Momentum Method in Continuous Time and Discretization Error Analysis
- Improving Energy Natural Gradient Descent through Woodbury, Momentum, and Randomization
- Incentivizing Desirable Effort Profiles in Strategic Classification: The Role of Causality and Uncertainty
- Individually Fair Diversity Maximization
- Last Iterate Convergence in Monotone Mean Field Games
- Learning to price with resource constraints: from full information to machine-learned prices
- Multiplayer Federated Learning: Reaching Equilibrium with Less Communication
- Nonparametric Quantile Regression with ReLU-Activated Recurrent Neural Networks
- Nyström-Accelerated Primal LS-SVMs: Breaking the $O(an^3)$ Complexity Bottleneck for Scalable ODEs Learning
- On Minimax Estimation of Parameters in Softmax-Contaminated Mixture of Experts
- On Transferring Transferability: Towards a Theory for Size Generalization
- On the Robustness of Transformers against Context Hijacking for Linear Classification
- Optimal Nuisance Function Tuning for Estimating a Doubly Robust Functional under Proportional Asymptotics
- Optimal Spectral Transitions in High-Dimensional Multi-Index Models
- PALQO: Physics-informed model for Accelerating Large-scale Quantum Optimization
- Planning and Learning in Average Risk-aware MDPs
- Problem-Parameter-Free Decentralized Bilevel Optimization
- Provable Sample-Efficient Transfer Learning Conditional Diffusion Models via Representation Learning
- Provably Efficient Multi-Task Meta Bandit Learning via Shared Representations
- Regression Trees Know Calculus
- Rethinking Gradient Step Denoiser: Towards Truly Pseudo-Contractive Operator
- Revisiting Frank-Wolfe for Structured Nonconvex Optimization
- Risk-Averse Constrained Reinforcement Learning with Optimized Certainty Equivalents
- SAD Neural Networks: Divergent Gradient Flows and Asymptotic Optimality via o-minimal Structures
- Sample Complexity of Distributionally Robust Average-Reward Reinforcement Learning
- Solving Discrete (Semi) Unbalanced Optimal Transport with Equivalent Transformation Mechanism and KKT-Multiplier Regularization
- Sparse Polyak: an adaptive step size rule for high-dimensional M-estimation
- Statistical Inference under Performativity
- Time-uniform and Asymptotic Confidence Sequence of Quantile under Local Differential Privacy
- Two‑Stage Learning of Stabilizing Neural Controllers via Zubov Sampling and Iterative Domain Expansion
- Variational Inference with Mixtures of Isotropic Gaussians
- When Data Can't Meet: Estimating Correlation Across Privacy Barriers