conftrace_

implicit bia

107 papers

Explore in graph

Co-occurring keywords

gradient descent (1144) neural network (6616) gradient flow (142) stochastic gradient descent (1091) large language model (13587) relu network (143) language model (4599) gender bia (435) generalization bound (652) mirror descent (148)

Papers

Abide by the law and follow the flow: conservation laws for gradient flows NIPS 2023
On the Dynamics Under the Unhinged Loss and Beyond JMLR 2023
Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing ICML 2023
On the Implicit Bias of Linear Equivariant Steerable Networks NIPS 2023
Minimum norm interpolation by perceptra: Explicit regularization and implicit bias NIPS 2023
Learning a Neuron by a Shallow ReLU Network: Dynamics and Implicit Bias for Correlated Inputs NIPS 2023
Rethinking Gauss-Newton for learning over-parameterized models NIPS 2023
Faster Margin Maximization Rates for Generic Optimization Methods NIPS 2023
Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability NIPS 2023
Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models ICML 2023
On the Implicit Geometry of Cross-Entropy Parameterizations for Label-Imbalanced Data AISTATS 2023
The Interplay Between Implicit Bias and Benign Overfitting in Two-Layer Linear Networks JMLR 2022
Buy Tesla, Sell Ford: Assessing Implicit Stock Market Preference in Pre-trained Language Models ACL 2022
On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias NIPS 2022
Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs NIPS 2022
Professional Presentation and Projected Power: A Case Study of Implicit Gender Information in English CVs EMNLP 2022
Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent NIPS 2022
Stability vs Implicit Bias of Gradient Methods on Separable Data and Beyond COLT 2022
Label noise (stochastic) gradient descent implicitly solves the Lasso for quadratic parametrisation COLT 2022
On Implicit Bias in Overparameterized Bilevel Optimization ICML 2022
On Margin Maximization in Linear and ReLU Networks NIPS 2022
Gradient Methods Provably Converge to Non-Robust Networks NIPS 2022
Mirror Descent Maximizes Generalized Margin and Can Be Implemented Efficiently NIPS 2022
Implicit Bias of the Step Size in Linear Diagonal Neural Networks ICML 2022
Power-Law Escape Rate of SGD ICML 2022