implicit bia

On the Implicit Bias of Linear Equivariant Steerable Networks NeurIPS 2023 On the Implicit Geometry of Cross-Entropy Parameterizations for Label-Imbalanced Data AISTATS 2023 Regression as Classification: Influence of Task Formulation on Neural Network Features AISTATS 2023 Rethinking Gauss-Newton for learning over-parameterized models NeurIPS 2023 Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models ICML 2023 Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability ICLR 2023 Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks NeurIPS 2023 The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks NeurIPS 2023 The Implicit Bias of Batch Normalization in Linear Models and Two-layer Linear Convolutional Neural Networks COLT 2023 The Implicit Bias of Benign Overfitting JMLR 2023 The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks ICLR 2023 Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias ICML 2023 Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing ICML 2023 A Study of Implicit Bias in Pretrained Language Models against People with Disabilities COLING 2022 Buy Tesla, Sell Ford: Assessing Implicit Stock Market Preference in Pre-trained Language Models ACL 2022 Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs NeurIPS 2022 Gradient Methods Provably Converge to Non-Robust Networks NeurIPS 2022 Implicit Bias of Adversarial Training for Deep Neural Networks ICLR 2022 Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent NeurIPS 2022 Implicit Bias of Linear Equivariant Networks ICML 2022 Implicit Bias of Projected Subgradient Method Gives Provable Robust Recovery of Subspaces of Unknown Codimension ICLR 2022 Implicit Bias of the Step Size in Linear Diagonal Neural Networks ICML 2022 Label noise (stochastic) gradient descent implicitly solves the Lasso for quadratic parametrisation COLT 2022 Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect ICLR 2022 Mirror Descent Maximizes Generalized Margin and Can Be Implemented Efficiently NeurIPS 2022