conftrace_

gradient flow

142 papers

Explore in graph

Also known as

GF

Co-occurring keywords

neural network (6616) gradient descent (1144) optimal transport (948) implicit bia (107) relu network (143) neural network optimization (1293) stochastic gradient descent (1091) convergence analysis (395) variational inference (2069) wasserstein distance (417)

Papers

On the Impact of Overparameterization on the Training of a Shallow Neural Network in High Dimensions AISTATS 2024
On the geometry of Stein variational gradient descent JMLR 2023
Neural Wasserstein Gradient Flows for Discrepancies with Riesz Kernels ICML 2023
Unifying GANs and Score-Based Diffusion as Generative Particle Models NIPS 2023
Particle algorithms for maximum likelihood training of latent variable models AISTATS 2023
Understanding Multi-phase Optimization Dynamics and Rich Nonlinear Behaviors of ReLU Networks NIPS 2023
Fixing the NTK: From Neural Network Linearizations to Exact Convex Programs NIPS 2023
Abide by the law and follow the flow: conservation laws for gradient flows NIPS 2023
Learning a Neuron by a Shallow ReLU Network: Dynamics and Implicit Bias for Correlated Inputs NIPS 2023
Module-wise Training of Neural Networks via the Minimizing Movement Scheme NIPS 2023
Analyzing Generalization of Neural Networks through Loss Path Kernels NIPS 2023
Dynamic Flows on Curved Space Generated by Labeled Data IJCAI 2023
Critical Points and Convergence Analysis of Generative Deep Linear Networks Trained with Bures-Wasserstein Loss ICML 2023
Incremental Learning in Diagonal Linear Networks JMLR 2023
Meta-Learning with Adjoint Methods AISTATS 2023
The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks NIPS 2023
Perturbation Analysis of Neural Collapse ICML 2023
GANs as Gradient Flows that Converge JMLR 2023
Are GATs Out of Balance? NIPS 2023
Saddle-to-Saddle Dynamics in Diagonal Linear Networks NIPS 2023
How much does Initialization Affect Generalization? ICML 2023
Leveraging the two-timescale regime to demonstrate convergence of neural networks NIPS 2023
On the Convergence of Gradient Flow on Multi-layer Linear Models ICML 2023
Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond ICML 2023
A Dynamical Systems Perspective on Discrete Optimization L4DC 2023