conftrace_

overparameterized model

24 papers

Explore in graph

Co-occurring keywords

neural network (6616) generalization bound (652) linear regression (282) gradient descent (1144) ridge regression (134) linear model (94) stochastic gradient descent (1091) deep linear network (25) implicit regularization (93) generalization error (285)

Papers

Sketching for Distributed Deep Learning: A Sharper Analysis NIPS 2024
Efficient Low-Dimensional Compression of Overparameterized Models AISTATS 2024
The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective JMLR 2024
On the Limitations of Fractal Dimension as a Measure of Generalization NIPS 2024
Explicit Regularization in Overparametrized Models via Noise Injection AISTATS 2023
A Blessing of Dimensionality in Membership Inference through Regularization AISTATS 2023
Benign Overfitting of Constant-Stepsize SGD for Linear Regression JMLR 2023
Revisiting minimum description length complexity in overparameterized models JMLR 2023
Implicit Balancing and Regularization: Generalization and Convergence Guarantees for Overparameterized Asymmetric Matrix Sensing COLT 2023
The Implicit Regularization of Momentum Gradient Descent in Overparametrized Models AAAI 2023
Aiming towards the minimizers: fast convergence of SGD for overparametrized problems NIPS 2023
Precise asymptotic generalization for multiclass classification with overparameterized linear models NIPS 2023
Distributed Optimization for Overparameterized Problems: Achieving Optimal Dimension Independent Communication Complexity NIPS 2022
Memorize to generalize: on the necessity of interpolation in high dimensional linear regression COLT 2022
Mirror Descent Maximizes Generalized Margin and Can Be Implemented Efficiently NIPS 2022
Understanding Benign Overfitting in Gradient-Based Meta Learning NIPS 2022
Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction NIPS 2021
Understanding the Dynamics of Gradient Flow in Overparameterized Linear models ICML 2021
Asymptotics of Ridge(less) Regression under General Source Condition AISTATS 2021
Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence AISTATS 2021
Offline Contextual Bandits with Overparameterized Models ICML 2021
Characterizing Structural Regularities of Labeled Data in Overparameterized Models ICML 2021
Understanding Double Descent Requires A Fine-Grained Bias-Variance Decomposition NIPS 2020
Dissecting Non-Vacuous Generalization Bounds based on the Mean-Field Approximation ICML 2020