global minimum

Characterizing Dynamical Stability of Stochastic Gradient Descent in Overparameterized Learning JMLR 2025 Global Convergence and Rich Feature Learning in L-Layer Infinite-Width Neural Networks under μ Parametrization ICML 2025 Interpretable Global Minima of Deep ReLU Neural Networks on Sequentially Separable Data JMLR 2025 LoRA Training Provably Converges to a Low-Rank Global Minimum Or It Fails Loudly (But it Probably Won’t Fail) ICML 2025 Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks ICML 2025 The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes: Sharp Estimates via Large Deviations ICML 2025 CRONOS: Enhancing Deep Learning with Scalable GPU Accelerated Convex Neural Networks NeurIPS 2024 Local to Global: Learning Dynamics and Effect of Initialization for Transformers NeurIPS 2024 S-SOS: Stochastic Sum-Of-Squares for Parametric Polynomial Optimization NeurIPS 2024 Understanding the difficulty of solving Cauchy problems with PINNs L4DC 2024 Special Properties of Gradient Descent with Large Learning Rates ICML 2023 Replica Exchange for Non-Convex Optimization JMLR 2021 Elimination of All Bad Local Minima in Deep Learning AISTATS 2020 A Convergence Theory for Deep Learning via Over-Parameterization ICML 2019 Gradient Descent Finds Global Minima of Deep Neural Networks ICML 2019 SGD Converges to Global Minimum in Deep Learning via Star-convex Path ICLR 2019 Width Provably Matters in Optimization for Deep Linear Neural Networks ICML 2019 Adding One Neuron Can Eliminate All Bad Local Minima NeurIPS 2018 Critical Points of Linear Neural Networks: Analytical Forms and Landscape Properties ICLR 2018 Deep Linear Networks with Arbitrary Loss: All Local Minima Are Global ICML 2018 How SGD Selects the Global Minima in Over-parameterized Learning: A Dynamical Stability Perspective NeurIPS 2018 Learning One-hidden-layer Neural Networks with Landscape Design ICLR 2018 Optimization, fast and slow: optimally switching between local and Bayesian optimization ICML 2018 Optimization Landscape and Expressivity of Deep CNNs ICML 2018 SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data ICLR 2018