optimization landscape

Landscape-Awareness for Geometric View Diffusion Model CVPR 2026 On the Convergence of Overparameterized Problems: Inherent Properties of the Compositional Structure of Neural Networks L4DC 2026 When Both Layers Learn: Training Dynamics of Representing Linear Models via ReLU Networks COLT 2026 Language-Based Bayesian Optimization Research Assistant (BORA) IJCAI 2025 On the Optimization Landscape of Low Rank Adaptation Methods for Large Language Models ICLR 2025 On Convergence in Wasserstein Distance and f-divergence Minimization Problems AISTATS 2024 The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof NeurIPS 2024 Connected Superlevel Set in (Deep) Reinforcement Learning and its Application to Minimax Theorems NeurIPS 2023 Demystify the Gravity Well in the Optimization Landscape (Student Abstract) AAAI 2023 Fractal Landscapes in Policy Optimization NeurIPS 2023 Geometric Analysis of Matrix Sensing over Graphs NeurIPS 2023 Optimizing Solution-Samplers for Combinatorial Problems: The Landscape of Policy-Gradient Method NeurIPS 2023 Annihilation of Spurious Minima in Two-Layer ReLU Networks NeurIPS 2022 Blessing of Depth in Linear Regression: Deeper Models Have Flatter Landscape Around the True Solution NeurIPS 2022 Cliff Diving: Exploring Reward Surfaces in Reinforcement Learning Environments ICML 2022 GradSign: Model Performance Inference with Theoretical Insights ICLR 2022 Inductive Matrix Completion: No Bad Local Minima and a Fast Algorithm ICML 2022 On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features ICML 2022 SGD Can Converge to Local Maxima ICLR 2022 Analysis of the Optimization Landscape of Linear Quadratic Gaussian (LQG) Control L4DC 2021 On the Stability Properties and the Optimization Landscape of Training Problems with Squared Loss for Neural Networks and General Nonlinear Conic Approximation Schemes JMLR 2021 Sparse linear networks with a fixed butterfly structure: theory and practice UAI 2021 The Effects of Mild Over-parameterization on the Optimization Landscape of Shallow ReLU Neural Networks COLT 2021 Understanding the effects of data parallelism and sparsity on neural network training ICLR 2021 When Expressivity Meets Trainability: Fewer than n Neurons Can Work NeurIPS 2021