complexity analysis
Complexity analysis is the study of the computational resources required by algorithms, such as time and space complexity, helping to evaluate the feasibility and efficiency of AI methods.
- Accurate and Efficient Low-Rank Model Merging in Core Space
- Algorithms and SQ Lower Bounds for Robustly Learning Real-valued Multi-Index Models
- Hyperphantasia: A Benchmark for Evaluating the Mental Visualization Capabilities of Multimodal LLMs
- Learning Orthogonal Multi-Index Models: A Fine-Grained Information Exponent Analysis
- Learning from A Single Markovian Trajectory: Optimality and Variance Reduction
- Nearly Dimension-Independent Convergence of Mean-Field Black-Box Variational Inference
- On the Complexity of Finding Stationary Points in Nonconvex Simple Bilevel Optimization
- On the Optimal Construction of Unbiased Gradient Estimators for Zeroth-Order Optimization
- Revisiting Frank-Wolfe for Structured Nonconvex Optimization
- The Generative Leap: Tight Sample Complexity for Efficiently Learning Gaussian Multi-Index Models