conftrace_

gradient descent dynamics

8 papers

Explore in graph

Co-occurring keywords · papers mentioning both

neural network (3) gradient descent (3) infinite-width limit (2) loss landscape (2) neural network optimization (2) neural tangent kernel (2) attention kernel (1) message passing algorithm (1) embedded ensemble (1) dropout ensemble (1)

Papers

Universal Sharpness Dynamics in Neural Network Training: Fixed Point Analysis, Edge of Stability, and Route to Chaos ICLR 2025 Towards Unbiased Exploration in Partial Label Learning JMLR 2024 Unraveling the Gradient Descent Dynamics of Transformers NeurIPS 2024 Embedded Ensembles: infinite width limit and operating regimes AISTATS 2022 Training Scale-Invariant Neural Networks on the Sphere Can Happen in Three Regimes NeurIPS 2022 Rank-one matrix estimation: analytic time evolution of gradient descent dynamics COLT 2021 Tensor Programs IIb: Architectural Universality Of Neural Tangent Kernel Training Dynamics ICML 2021 Passed & Spurious: Descent Algorithms and Local Minima in Spiked Matrix-Tensor Models ICML 2019