non-convex optimization
Non-convex optimization refers to optimization problems where the objective function is not convex, meaning it may have multiple local minima and maxima. These problems are common in training deep learning models, complicating the search for optimal solutions.
- Exploring Landscapes for Better Minima along Valleys
- Faithful Dynamic Imitation Learning from Human Intervention with Dynamic Regret Minimization
- Gaussian Regression-Driven Tensorized Incomplete Multi-View Clustering with Dual Manifold Regularization
- Go With the Flow: Fast Diffusion for Gaussian Mixture Models
- Guarantees for Alternating Least Squares in Overparameterized Tensor Decompositions
- Learning from A Single Markovian Trajectory: Optimality and Variance Reduction
- Learning from Interval Targets
- On Linear Mode Connectivity of Mixture-of-Experts Architectures
- On Linear Mode Connectivity of Mixture-of-Experts Architectures
- Optimal Estimation of the Best Mean in Multi-Armed Bandits
- Quantum Speedups for Minimax Optimization and Beyond
- Stochastic Momentum Methods for Non-smooth Non-Convex Finite-Sum Coupled Compositional Optimization
- Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression
- Unsupervised Learning for Optimal Transport plan prediction between unbalanced graphs