conftrace_

diagonal linear network

7 papers

Explore in graph

Co-occurring keywords · papers mentioning both

gradient flow (4) implicit bia (3) implicit regularization (3) stochastic gradient descent (3) sparse regression (2) overparameterized regression (1) edge of stability (1) gradient regularization (1) finite-difference computation (1) stochastic gradient flow (1)

Papers

Effects of Momentum in Implicit Bias of Gradient Flow for Diagonal Linear Networks AAAI 2025 Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks AISTATS 2024 Incremental Learning in Diagonal Linear Networks JMLR 2023 Saddle-to-Saddle Dynamics in Diagonal Linear Networks NeurIPS 2023 (S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability NeurIPS 2023 Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias ICML 2023 Implicit Bias of SGD for Diagonal Linear Networks: a Provable Benefit of Stochasticity NeurIPS 2021